{"data":[{"id":"deepseek/deepseek-v3-2","name":"DeepSeek V3.2","canonical_slug":"deepseek/deepseek-v3-2","description":"DeepSeek V3.2 — frontier open-source general-purpose model.","created":1775000000,"context_length":163840,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000004000","completion":"0.0000006000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":163840,"completion_tokens":16384},"top_provider":{"context_length":163840,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v3-2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"deepseek-ai/DeepSeek-V3.2","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek-v3-2","name":"DeepSeek V3.2","canonical_slug":"deepseek/deepseek-v3-2","description":"DeepSeek V3.2 — frontier open-source general-purpose model.","created":1775000000,"context_length":163840,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000004000","completion":"0.0000006000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":163840,"completion_tokens":16384},"top_provider":{"context_length":163840,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v3-2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"deepseek-ai/DeepSeek-V3.2","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"meta/llama-3.3-70b","name":"Llama 3.3 70B Instruct","canonical_slug":"meta/llama-3.3-70b","description":"Meta Llama 3.3 70B Instruct — strong general-purpose with tool use.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.0000003000","completion":"0.0000004000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":8192},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/llama-3.3-70b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"llama-3.3-70b","name":"Llama 3.3 70B Instruct","canonical_slug":"meta/llama-3.3-70b","description":"Meta Llama 3.3 70B Instruct — strong general-purpose with tool use.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":"0.0000003000","completion":"0.0000004000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":8192},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/llama-3.3-70b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"meta-llama/Llama-3.3-70B-Instruct","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"mistralai/mistral-large-3","name":"Mistral Large 3","canonical_slug":"mistralai/mistral-large-3","description":"Mistral Large 3 — flagship European model, instruction following.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.0000004000","completion":"0.0000012000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":8192},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/mistral-large-3"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"mistralai/Mistral-Large-3","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"mistral-large-3","name":"Mistral Large 3","canonical_slug":"mistralai/mistral-large-3","description":"Mistral Large 3 — flagship European model, instruction following.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.0000004000","completion":"0.0000012000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":8192},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/mistral-large-3"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"mistralai/Mistral-Large-3","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"openai/gpt-oss-120b","name":"GPT-OSS 120B","canonical_slug":"openai/gpt-oss-120b","description":"Microsoft GPT-OSS 120B — open-weight reasoning model.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000001500","completion":"0.0000006000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":16384},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-oss-120b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"gpt-oss-120b","name":"GPT-OSS 120B","canonical_slug":"openai/gpt-oss-120b","description":"Microsoft GPT-OSS 120B — open-weight reasoning model.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000001500","completion":"0.0000006000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":16384},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-oss-120b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"meta/llama-4-maverick","name":"Llama 4 Maverick 17B","canonical_slug":"meta/llama-4-maverick","description":"Meta Llama 4 Maverick — first Llama 4 generation, 1M context, 12 languages, image+text.","created":1775000000,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":"llama4"},"pricing":{"prompt":"0.0000005000","completion":"0.0000015000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":1000000,"completion_tokens":8192},"top_provider":{"context_length":1000000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/llama-4-maverick"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"llama-4-maverick","name":"Llama 4 Maverick 17B","canonical_slug":"meta/llama-4-maverick","description":"Meta Llama 4 Maverick — first Llama 4 generation, 1M context, 12 languages, image+text.","created":1775000000,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":"llama4"},"pricing":{"prompt":"0.0000005000","completion":"0.0000015000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":1000000,"completion_tokens":8192},"top_provider":{"context_length":1000000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/llama-4-maverick"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"cohere/cohere-command-a","name":"Cohere Command-A","canonical_slug":"cohere/cohere-command-a","description":"Cohere Command-A — multilingual (10 languages), strong RAG and tool-calling.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":"command"},"pricing":{"prompt":"0.0000025000","completion":"0.0000100000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":8192},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/cohere-command-a"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"cohere-command-a","name":"Cohere Command-A","canonical_slug":"cohere/cohere-command-a","description":"Cohere Command-A — multilingual (10 languages), strong RAG and tool-calling.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":"command"},"pricing":{"prompt":"0.0000025000","completion":"0.0000100000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":8192},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/cohere-command-a"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"x-ai/grok-4-1-fast","name":"xAI Grok 4.1 Fast","canonical_slug":"x-ai/grok-4-1-fast","description":"xAI Grok 4.1 Fast (reasoning) — fast Grok variant with reasoning + tool use.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000002000","completion":"0.0000005000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":16384},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/grok-4-1-fast"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"grok-4-1-fast","name":"xAI Grok 4.1 Fast","canonical_slug":"x-ai/grok-4-1-fast","description":"xAI Grok 4.1 Fast (reasoning) — fast Grok variant with reasoning + tool use.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000002000","completion":"0.0000005000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":16384},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/grok-4-1-fast"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"microsoft/phi-4-mini-reasoning","name":"Phi-4 Mini Reasoning","canonical_slug":"microsoft/phi-4-mini-reasoning","description":"Microsoft Phi-4 Mini — small, cheap reasoning model with thinking traces.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000001000","completion":"0.0000003000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":8192},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/phi-4-mini-reasoning"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"microsoft/Phi-4-mini-reasoning","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"phi-4-mini-reasoning","name":"Phi-4 Mini Reasoning","canonical_slug":"microsoft/phi-4-mini-reasoning","description":"Microsoft Phi-4 Mini — small, cheap reasoning model with thinking traces.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000001000","completion":"0.0000003000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":8192},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/phi-4-mini-reasoning"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"microsoft/Phi-4-mini-reasoning","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","canonical_slug":"deepseek/deepseek-v4-pro","description":"DeepSeek V4 Pro — flagship of the V4 generation, frontier open-source reasoning with prompt caching.","created":1775000000,"context_length":1048576,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000017400","completion":"0.0000034800","image":"0","request":"0","input_cache_read":"0.0000001450"},"per_request_limits":{"prompt_tokens":1048576,"completion_tokens":128000},"top_provider":{"context_length":1048576,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v4-pro"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","canonical_slug":"deepseek/deepseek-v4-pro","description":"DeepSeek V4 Pro — flagship of the V4 generation, frontier open-source reasoning with prompt caching.","created":1775000000,"context_length":1048576,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000017400","completion":"0.0000034800","image":"0","request":"0","input_cache_read":"0.0000001450"},"per_request_limits":{"prompt_tokens":1048576,"completion_tokens":128000},"top_provider":{"context_length":1048576,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v4-pro"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"deepseek-ai/DeepSeek-V4-Pro","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","canonical_slug":"deepseek/deepseek-v4-flash","description":"DeepSeek V4 Flash — fast, very cheap V4 variant for high-throughput work. Cached input at ~15% of the fresh rate.","created":1775000000,"context_length":1048576,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000001900","completion":"0.0000005100","image":"0","request":"0","input_cache_read":"0.0000000280"},"per_request_limits":{"prompt_tokens":1048576,"completion_tokens":128000},"top_provider":{"context_length":1048576,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v4-flash"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","canonical_slug":"deepseek/deepseek-v4-flash","description":"DeepSeek V4 Flash — fast, very cheap V4 variant for high-throughput work. Cached input at ~15% of the fresh rate.","created":1775000000,"context_length":1048576,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000001900","completion":"0.0000005100","image":"0","request":"0","input_cache_read":"0.0000000280"},"per_request_limits":{"prompt_tokens":1048576,"completion_tokens":128000},"top_provider":{"context_length":1048576,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v4-flash"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"deepseek-ai/DeepSeek-V4-Flash","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek/deepseek-v3-2-speciale","name":"DeepSeek V3.2 Speciale","canonical_slug":"deepseek/deepseek-v3-2-speciale","description":"DeepSeek V3.2 Speciale — reasoning-tuned V3.2 variant, stronger on maths and competition-style problems.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000005800","completion":"0.0000016800","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":32768},"top_provider":{"context_length":128000,"max_completion_tokens":32768,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v3-2-speciale"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Speciale","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek-v3-2-speciale","name":"DeepSeek V3.2 Speciale","canonical_slug":"deepseek/deepseek-v3-2-speciale","description":"DeepSeek V3.2 Speciale — reasoning-tuned V3.2 variant, stronger on maths and competition-style problems.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000005800","completion":"0.0000016800","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":32768},"top_provider":{"context_length":128000,"max_completion_tokens":32768,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v3-2-speciale"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"deepseek-ai/DeepSeek-V3.2-Speciale","powered_by":null,"hosting":"Azure AI Foundry"},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","canonical_slug":"moonshotai/kimi-k2.7-code","description":"Moonshot AI Kimi K2.7 Code — coding-specialised K2 variant with thinking traces and prompt caching.","created":1775000000,"context_length":262144,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000009500","completion":"0.0000040000","image":"0","request":"0","input_cache_read":"0.0000001900"},"per_request_limits":{"prompt_tokens":262144,"completion_tokens":65536},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kimi-k2.7-code"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","canonical_slug":"moonshotai/kimi-k2.7-code","description":"Moonshot AI Kimi K2.7 Code — coding-specialised K2 variant with thinking traces and prompt caching.","created":1775000000,"context_length":262144,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000009500","completion":"0.0000040000","image":"0","request":"0","input_cache_read":"0.0000001900"},"per_request_limits":{"prompt_tokens":262144,"completion_tokens":65536},"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kimi-k2.7-code"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"x-ai/grok-4.3","name":"xAI Grok 4.3","canonical_slug":"x-ai/grok-4.3","description":"xAI Grok 4.3 — latest frontier Grok, reasoning + tool use, image input, prompt caching.","created":1775000000,"context_length":200000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000012500","completion":"0.0000025000","image":"0","request":"0","input_cache_read":"0.0000002000"},"per_request_limits":{"prompt_tokens":200000,"completion_tokens":8192},"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/grok-4.3"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"grok-4.3","name":"xAI Grok 4.3","canonical_slug":"x-ai/grok-4.3","description":"xAI Grok 4.3 — latest frontier Grok, reasoning + tool use, image input, prompt caching.","created":1775000000,"context_length":200000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000012500","completion":"0.0000025000","image":"0","request":"0","input_cache_read":"0.0000002000"},"per_request_limits":{"prompt_tokens":200000,"completion_tokens":8192},"top_provider":{"context_length":200000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/grok-4.3"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"mistralai/mistral-medium-3.5","name":"Mistral Medium 3.5","canonical_slug":"mistralai/mistral-medium-3.5","description":"Mistral Medium 3.5 — European mid-tier, multimodal input, strong instruction following.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.0000015000","completion":"0.0000075000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/mistral-medium-3.5"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"mistral-medium-3.5","name":"Mistral Medium 3.5","canonical_slug":"mistralai/mistral-medium-3.5","description":"Mistral Medium 3.5 — European mid-tier, multimodal input, strong instruction following.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.0000015000","completion":"0.0000075000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/mistral-medium-3.5"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"cohere/cohere-command-a-plus","name":"Cohere Command-A Plus","canonical_slug":"cohere/cohere-command-a-plus","description":"Cohere Command-A Plus — upgraded Command-A: multilingual, agentic RAG and tool-calling.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":"command"},"pricing":{"prompt":"0.0000008000","completion":"0.0000032000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":64000},"top_provider":{"context_length":128000,"max_completion_tokens":64000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/cohere-command-a-plus"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"cohere-command-a-plus","name":"Cohere Command-A Plus","canonical_slug":"cohere/cohere-command-a-plus","description":"Cohere Command-A Plus — upgraded Command-A: multilingual, agentic RAG and tool-calling.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":"command"},"pricing":{"prompt":"0.0000008000","completion":"0.0000032000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":64000},"top_provider":{"context_length":128000,"max_completion_tokens":64000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/cohere-command-a-plus"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"openai/gpt-5","name":"GPT-5","canonical_slug":"openai/gpt-5","description":"OpenAI GPT-5 — flagship proprietary model.","created":1775000000,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000100000","image":"0","request":"0","input_cache_read":"0.0000002500"},"per_request_limits":{"prompt_tokens":400000,"completion_tokens":16384},"top_provider":{"context_length":400000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-5","name":"GPT-5","canonical_slug":"openai/gpt-5","description":"OpenAI GPT-5 — flagship proprietary model.","created":1775000000,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000100000","image":"0","request":"0","input_cache_read":"0.0000002500"},"per_request_limits":{"prompt_tokens":400000,"completion_tokens":16384},"top_provider":{"context_length":400000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-5.2","name":"GPT-5.2","canonical_slug":"openai/gpt-5.2","description":"OpenAI GPT-5.2 — improved reasoning and speed.","created":1775000000,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000140000","image":"0","request":"0","input_cache_read":"0.0000002500"},"per_request_limits":{"prompt_tokens":400000,"completion_tokens":16384},"top_provider":{"context_length":400000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-5.2","name":"GPT-5.2","canonical_slug":"openai/gpt-5.2","description":"OpenAI GPT-5.2 — improved reasoning and speed.","created":1775000000,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000140000","image":"0","request":"0","input_cache_read":"0.0000002500"},"per_request_limits":{"prompt_tokens":400000,"completion_tokens":16384},"top_provider":{"context_length":400000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-5.5","name":"GPT-5.5","canonical_slug":"openai/gpt-5.5","description":"OpenAI GPT-5.5 — flagship, 1.05M context, image+text reasoning.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000050000","completion":"0.0000300000","image":"0","request":"0","input_cache_read":"0.0000005000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.5"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-5.5","name":"GPT-5.5","canonical_slug":"openai/gpt-5.5","description":"OpenAI GPT-5.5 — flagship, 1.05M context, image+text reasoning.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000050000","completion":"0.0000300000","image":"0","request":"0","input_cache_read":"0.0000005000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.5"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-5.4","name":"GPT-5.4","canonical_slug":"openai/gpt-5.4","description":"OpenAI GPT-5.4 — production workhorse, 1.05M context, strong agentic + long-doc.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000150000","image":"0","request":"0","input_cache_read":"0.0000002500"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.4"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-5.4","name":"GPT-5.4","canonical_slug":"openai/gpt-5.4","description":"OpenAI GPT-5.4 — production workhorse, 1.05M context, strong agentic + long-doc.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000150000","image":"0","request":"0","input_cache_read":"0.0000002500"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.4"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 Mini","canonical_slug":"openai/gpt-5.4-mini","description":"OpenAI GPT-5.4 Mini — drop-in mid-tier, 400K context, reasoning.","created":1775000000,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000007500","completion":"0.0000045000","image":"0","request":"0","input_cache_read":"0.0000000750"},"per_request_limits":{"prompt_tokens":400000,"completion_tokens":128000},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.4-mini"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-5.4-mini","name":"GPT-5.4 Mini","canonical_slug":"openai/gpt-5.4-mini","description":"OpenAI GPT-5.4 Mini — drop-in mid-tier, 400K context, reasoning.","created":1775000000,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000007500","completion":"0.0000045000","image":"0","request":"0","input_cache_read":"0.0000000750"},"per_request_limits":{"prompt_tokens":400000,"completion_tokens":128000},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","tools","tool_choice","structured_outputs","response_format","reasoning","reasoning_effort","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.4-mini"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","canonical_slug":"openai/gpt-5.6-sol","description":"OpenAI GPT-5.6 Sol — flagship coding + agentic workhorse, 1.05M context. Sol Ultra mode via reasoning_effort=high.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000050000","completion":"0.0000300000","image":"0","request":"0","input_cache_read":"0.0000005000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls","prompt_cache_key"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.6-sol"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-5.6-sol","name":"GPT-5.6 Sol","canonical_slug":"openai/gpt-5.6-sol","description":"OpenAI GPT-5.6 Sol — flagship coding + agentic workhorse, 1.05M context. Sol Ultra mode via reasoning_effort=high.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000050000","completion":"0.0000300000","image":"0","request":"0","input_cache_read":"0.0000005000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls","prompt_cache_key"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.6-sol"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","canonical_slug":"openai/gpt-5.6-terra","description":"OpenAI GPT-5.6 Terra — balanced tier for everyday coding + reasoning, 1.05M context.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000150000","image":"0","request":"0","input_cache_read":"0.0000002500"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls","prompt_cache_key"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.6-terra"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-5.6-terra","name":"GPT-5.6 Terra","canonical_slug":"openai/gpt-5.6-terra","description":"OpenAI GPT-5.6 Terra — balanced tier for everyday coding + reasoning, 1.05M context.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000150000","image":"0","request":"0","input_cache_read":"0.0000002500"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls","prompt_cache_key"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.6-terra"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","canonical_slug":"openai/gpt-5.6-luna","description":"OpenAI GPT-5.6 Luna — fastest, cheapest GPT-5.6 variant for high-throughput chat.","created":1775000000,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000010000","completion":"0.0000060000","image":"0","request":"0","input_cache_read":"0.0000001000"},"per_request_limits":{"prompt_tokens":400000,"completion_tokens":128000},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls","prompt_cache_key"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.6-luna"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-5.6-luna","name":"GPT-5.6 Luna","canonical_slug":"openai/gpt-5.6-luna","description":"OpenAI GPT-5.6 Luna — fastest, cheapest GPT-5.6 variant for high-throughput chat.","created":1775000000,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000010000","completion":"0.0000060000","image":"0","request":"0","input_cache_read":"0.0000001000"},"per_request_limits":{"prompt_tokens":400000,"completion_tokens":128000},"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls","prompt_cache_key"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-5.6-luna"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","canonical_slug":"openai/gpt-6-astra","description":"OpenAI GPT-6 Astra — frontier reasoning and agentic model, 1.05M context. Function tools are available on /v1/responses only; /v1/chat/completions rejects them for this model.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000100000","completion":"0.0000500000","image":"0","request":"0","input_cache_read":"0.0000010000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","reasoning_effort","structured_outputs","response_format","reasoning","prompt_cache_key"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-6-astra"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-6-astra","name":"GPT-6 Astra","canonical_slug":"openai/gpt-6-astra","description":"OpenAI GPT-6 Astra — frontier reasoning and agentic model, 1.05M context. Function tools are available on /v1/responses only; /v1/chat/completions rejects them for this model.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000100000","completion":"0.0000500000","image":"0","request":"0","input_cache_read":"0.0000010000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","frequency_penalty","presence_penalty","reasoning_effort","structured_outputs","response_format","reasoning","prompt_cache_key"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-6-astra"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","canonical_slug":"openai/gpt-6-sol","description":"OpenAI GPT-6 Sol — coding and agentic workhorse, 1.05M context. Chat function tools use reasoning_effort=none; use /v1/responses for tools with reasoning.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000020000","completion":"0.0000100000","image":"0","request":"0","input_cache_read":"0.0000002000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["max_tokens","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-6-sol"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-6-sol","name":"GPT-6 Sol","canonical_slug":"openai/gpt-6-sol","description":"OpenAI GPT-6 Sol — coding and agentic workhorse, 1.05M context. Chat function tools use reasoning_effort=none; use /v1/responses for tools with reasoning.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000020000","completion":"0.0000100000","image":"0","request":"0","input_cache_read":"0.0000002000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["max_tokens","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-6-sol"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","canonical_slug":"openai/gpt-6-luna","description":"OpenAI GPT-6 Luna — efficient model for focused, high-volume tasks, 1.05M context. Chat function tools use reasoning_effort=none; use /v1/responses for tools with reasoning.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000001000","completion":"0.0000005000","image":"0","request":"0","input_cache_read":"0.0000000100"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["max_tokens","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-6-luna"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-6-luna","name":"GPT-6 Luna","canonical_slug":"openai/gpt-6-luna","description":"OpenAI GPT-6 Luna — efficient model for focused, high-volume tasks, 1.05M context. Chat function tools use reasoning_effort=none; use /v1/responses for tools with reasoning.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000001000","completion":"0.0000005000","image":"0","request":"0","input_cache_read":"0.0000000100"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["max_tokens","reasoning_effort","tools","tool_choice","structured_outputs","response_format","reasoning","parallel_tool_calls"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-6-luna"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","canonical_slug":"openai/gpt-6.1-sol","description":"OpenAI GPT-6.1 Sol — near-Astra coding and agentic model at a fifth of the price, 1.05M context. Function tools are available on /v1/responses only; /v1/chat/completions rejects them for this model.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000020000","completion":"0.0000100000","image":"0","request":"0","input_cache_read":"0.0000001000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["max_tokens","reasoning_effort","structured_outputs","response_format","reasoning"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-6.1-sol"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-6.1-sol","name":"GPT-6.1 Sol","canonical_slug":"openai/gpt-6.1-sol","description":"OpenAI GPT-6.1 Sol — near-Astra coding and agentic model at a fifth of the price, 1.05M context. Function tools are available on /v1/responses only; /v1/chat/completions rejects them for this model.","created":1775000000,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000020000","completion":"0.0000100000","image":"0","request":"0","input_cache_read":"0.0000001000"},"per_request_limits":{"prompt_tokens":1050000,"completion_tokens":128000},"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"supported_parameters":["max_tokens","reasoning_effort","structured_outputs","response_format","reasoning"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-6.1-sol"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","canonical_slug":"moonshotai/kimi-k2.5","description":"Moonshot AI Kimi K2.5 — strong reasoning model with thinking traces.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000006000","completion":"0.0000024000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":16384},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kimi-k2.5"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"kimi-k2.5","name":"Kimi K2.5","canonical_slug":"moonshotai/kimi-k2.5","description":"Moonshot AI Kimi K2.5 — strong reasoning model with thinking traces.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000006000","completion":"0.0000024000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":16384},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kimi-k2.5"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","canonical_slug":"moonshotai/kimi-k2.6","description":"Moonshot AI Kimi K2.6 — latest frontier reasoning model with thinking traces.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000006000","completion":"0.0000024000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":16384},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kimi-k2.6"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"kimi-k2.6","name":"Kimi K2.6","canonical_slug":"moonshotai/kimi-k2.6","description":"Moonshot AI Kimi K2.6 — latest frontier reasoning model with thinking traces.","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000006000","completion":"0.0000024000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":16384},"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kimi-k2.6"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"x-ai/grok-4.7","name":"Grok 4.7","canonical_slug":"x-ai/grok-4.7","description":"xAI Grok 4.7 — reasoning chat. Provisional pricing based on Azure Grok 4.6; a published 4.7 price is pending.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000075000","image":"0","request":"0","input_cache_read":"0.0000006250"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":16384},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["max_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/grok-4.7"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"grok-4.7","name":"Grok 4.7","canonical_slug":"x-ai/grok-4.7","description":"xAI Grok 4.7 — reasoning chat. Provisional pricing based on Azure Grok 4.6; a published 4.7 price is pending.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000025000","completion":"0.0000075000","image":"0","request":"0","input_cache_read":"0.0000006250"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":16384},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["max_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/grok-4.7"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","canonical_slug":"deepseek/deepseek-v4.1-flash","description":"DeepSeek V4.1 Flash — preview with tool use and prompt caching; Azure inference retirement 2026-12-15.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000004688","completion":"0.0000018750","image":"0","request":"0","input_cache_read":"0.0000000100"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":16384},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v4.1-flash"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","canonical_slug":"deepseek/deepseek-v4.1-flash","description":"DeepSeek V4.1 Flash — preview with tool use and prompt caching; Azure inference retirement 2026-12-15.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek"},"pricing":{"prompt":"0.0000004688","completion":"0.0000018750","image":"0","request":"0","input_cache_read":"0.0000000100"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":16384},"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"supported_parameters":["temperature","top_p","max_tokens","stop","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/deepseek-v4.1-flash"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"openai/gpt-image-2.5-flare","name":"GPT-Image-2.5 Flare","canonical_slug":"openai/gpt-image-2.5-flare","description":"GPT-Image-2.5 Flare — image generation billed by actual text input and image output tokens. Size defaults to 1024x1024; quality defaults to medium.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000062500","completion":"0.0000000000","image":"0","image_output_tokens":"0.0000375000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["n","size","quality"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-image-2.5-flare"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-image-2.5-flare","name":"GPT-Image-2.5 Flare","canonical_slug":"openai/gpt-image-2.5-flare","description":"GPT-Image-2.5 Flare — image generation billed by actual text input and image output tokens. Size defaults to 1024x1024; quality defaults to medium.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000062500","completion":"0.0000000000","image":"0","image_output_tokens":"0.0000375000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["n","size","quality"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-image-2.5-flare"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-image-2.5-sunburst","name":"GPT-Image-2.5 Sunburst","canonical_slug":"openai/gpt-image-2.5-sunburst","description":"GPT-Image-2.5 Sunburst — image generation billed by actual text input and image output tokens. Size defaults to 1024x1024; quality defaults to medium.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000062500","completion":"0.0000000000","image":"0","image_output_tokens":"0.0000375000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["n","size","quality"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-image-2.5-sunburst"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-image-2.5-sunburst","name":"GPT-Image-2.5 Sunburst","canonical_slug":"openai/gpt-image-2.5-sunburst","description":"GPT-Image-2.5 Sunburst — image generation billed by actual text input and image output tokens. Size defaults to 1024x1024; quality defaults to medium.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000062500","completion":"0.0000000000","image":"0","image_output_tokens":"0.0000375000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["n","size","quality"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-image-2.5-sunburst"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-image-2","name":"GPT-Image-2","canonical_slug":"openai/gpt-image-2","description":"OpenAI GPT-Image-2 — flagship image generation model, photoreal + editorial.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","image_output":"0.0800000000","image_output_high":"0.1600000000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["n","size","quality","style","response_format"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-image-2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-image-2","name":"GPT-Image-2","canonical_slug":"openai/gpt-image-2","description":"OpenAI GPT-Image-2 — flagship image generation model, photoreal + editorial.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"GPT-5","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","image_output":"0.0800000000","image_output_high":"0.1600000000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["n","size","quality","style","response_format"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-image-2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-image-1-mini","name":"GPT-Image-1 Mini","canonical_slug":"openai/gpt-image-1-mini","description":"OpenAI GPT-Image-1 Mini — cheap image generation, good for thumbnails and batch.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","image_output":"0.0110000000","image_output_high":"0.0220000000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["n","size","quality","response_format"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-image-1-mini"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-image-1-mini","name":"GPT-Image-1 Mini","canonical_slug":"openai/gpt-image-1-mini","description":"OpenAI GPT-Image-1 Mini — cheap image generation, good for thumbnails and batch.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","image_output":"0.0110000000","image_output_high":"0.0220000000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["n","size","quality","response_format"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-image-1-mini"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"black-forest-labs/flux-2-pro","name":"FLUX.2 Pro","canonical_slug":"black-forest-labs/flux-2-pro","description":"Black Forest Labs FLUX.2 Pro — open frontier image gen, strong typography + composition.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","image_output_megapixel":"0.0400000000","image_output_min":"0.0400000000","image_output_max":"0.1600000000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["size","output_format"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/flux-2-pro"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"flux-2-pro","name":"FLUX.2 Pro","canonical_slug":"black-forest-labs/flux-2-pro","description":"Black Forest Labs FLUX.2 Pro — open frontier image gen, strong typography + composition.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","image_output_megapixel":"0.0400000000","image_output_min":"0.0400000000","image_output_max":"0.1600000000","request":"0"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["size","output_format"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/flux-2-pro"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure AI Foundry"},{"id":"openai/whisper-large-v3-turbo","name":"Whisper Large V3 Turbo","canonical_slug":"openai/whisper-large-v3-turbo","description":"OpenAI Whisper Large V3 Turbo — V3 distilled to ~6× faster decoding with near-identical WER. Self-hosted on our own GPU fleet.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Whisper","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0030000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature","timestamp_granularities"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/whisper-large-v3-turbo"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"openai/whisper-large-v3-turbo","powered_by":null,"hosting":null},{"id":"whisper-large-v3-turbo","name":"Whisper Large V3 Turbo","canonical_slug":"openai/whisper-large-v3-turbo","description":"OpenAI Whisper Large V3 Turbo — V3 distilled to ~6× faster decoding with near-identical WER. Self-hosted on our own GPU fleet.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Whisper","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0030000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature","timestamp_granularities"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/whisper-large-v3-turbo"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"openai/whisper-large-v3-turbo","powered_by":null,"hosting":null},{"id":"openai/whisper-large-v3-turbo-stream","name":"Whisper Large V3 Turbo (streaming)","canonical_slug":"openai/whisper-large-v3-turbo-stream","description":"Real-time streaming ASR over WebSocket. Deepgram-shape protocol at /v1/listen. Same Whisper Turbo model, VAD-segmented, partial + final transcripts. Self-hosted on our own GPU fleet.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Whisper","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0033000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","encoding","sample_rate","interim_results","endpointing"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/whisper-large-v3-turbo-stream"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"openai/whisper-large-v3-turbo","powered_by":null,"hosting":null},{"id":"whisper-large-v3-turbo-stream","name":"Whisper Large V3 Turbo (streaming)","canonical_slug":"openai/whisper-large-v3-turbo-stream","description":"Real-time streaming ASR over WebSocket. Deepgram-shape protocol at /v1/listen. Same Whisper Turbo model, VAD-segmented, partial + final transcripts. Self-hosted on our own GPU fleet.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Whisper","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0033000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","encoding","sample_rate","interim_results","endpointing"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/whisper-large-v3-turbo-stream"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"openai/whisper-large-v3-turbo","powered_by":null,"hosting":null},{"id":"nvidia/parakeet-tdt-0-6b-stream","name":"Parakeet TDT 0.6B v2 (streaming)","canonical_slug":"nvidia/parakeet-tdt-0-6b-stream","description":"Real-time streaming ASR over WebSocket. Deepgram-shape protocol at /v1/listen. NVIDIA NeMo Parakeet-TDT-0.6B v2 — English-only, SOTA Open-ASR-Leaderboard WER, VAD-segmented chunked decode. Self-hosted on our own GPU fleet.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"SentencePiece","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0033000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","encoding","sample_rate","interim_results","endpointing"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/parakeet-tdt-0-6b-stream"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"nvidia/parakeet-tdt-0.6b-v2","powered_by":null,"hosting":null},{"id":"parakeet-tdt-0-6b-stream","name":"Parakeet TDT 0.6B v2 (streaming)","canonical_slug":"nvidia/parakeet-tdt-0-6b-stream","description":"Real-time streaming ASR over WebSocket. Deepgram-shape protocol at /v1/listen. NVIDIA NeMo Parakeet-TDT-0.6B v2 — English-only, SOTA Open-ASR-Leaderboard WER, VAD-segmented chunked decode. Self-hosted on our own GPU fleet.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"SentencePiece","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0033000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","encoding","sample_rate","interim_results","endpointing"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/parakeet-tdt-0-6b-stream"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"nvidia/parakeet-tdt-0.6b-v2","powered_by":null,"hosting":null},{"id":"duguetlabs/piper-tts","name":"Piper TTS (multilingual)","canonical_slug":"duguetlabs/piper-tts","description":"Neural text-to-speech in 10 languages (EN, DE, FR, ES, NL, SV, DA, IT, FI, RU). Streams PCM16 audio; powers the speech output of /v1/realtime. Self-hosted.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0100000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","voice","sample_rate"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/piper-tts"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"rhasspy/piper-voices","powered_by":null,"hosting":null},{"id":"piper-tts","name":"Piper TTS (multilingual)","canonical_slug":"duguetlabs/piper-tts","description":"Neural text-to-speech in 10 languages (EN, DE, FR, ES, NL, SV, DA, IT, FI, RU). Streams PCM16 audio; powers the speech output of /v1/realtime. Self-hosted.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0100000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","voice","sample_rate"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/piper-tts"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"rhasspy/piper-voices","powered_by":null,"hosting":null},{"id":"duguetlabs/kataleptic-realtime","name":"Kataleptic Realtime (speech-to-speech)","canonical_slug":"duguetlabs/kataleptic-realtime","description":"OpenAI Realtime API-compatible voice agent endpoint: WebSocket at /v1/realtime. Cascade of streaming Whisper STT, any Kataleptic chat model (pick via ?model=), and Piper TTS — first reply audio in roughly 250 ms after turn detection. Server-side VAD with barge-in, per-utterance language auto-detection across 10 languages, transcript events both directions (incl. detected language). Billed per audio minute (STT in + TTS out) plus chat tokens at the selected model's rate. Self-hosted. Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["audio","text"],"output_modalities":["audio","text"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_input_minute":"0.0033000000","audio_output_minute":"0.0100000000"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":4096},"top_provider":{"context_length":131072,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["model","instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kataleptic-realtime"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"kataleptic-realtime","name":"Kataleptic Realtime (speech-to-speech)","canonical_slug":"duguetlabs/kataleptic-realtime","description":"OpenAI Realtime API-compatible voice agent endpoint: WebSocket at /v1/realtime. Cascade of streaming Whisper STT, any Kataleptic chat model (pick via ?model=), and Piper TTS — first reply audio in roughly 250 ms after turn detection. Server-side VAD with barge-in, per-utterance language auto-detection across 10 languages, transcript events both directions (incl. detected language). Billed per audio minute (STT in + TTS out) plus chat tokens at the selected model's rate. Self-hosted. Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":131072,"architecture":{"input_modalities":["audio","text"],"output_modalities":["audio","text"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_input_minute":"0.0033000000","audio_output_minute":"0.0100000000"},"per_request_limits":{"prompt_tokens":131072,"completion_tokens":4096},"top_provider":{"context_length":131072,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["model","instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kataleptic-realtime"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"duguetlabs/kataleptic-realtime-hd","name":"Kataleptic Realtime HD (Azure Voice Live)","canonical_slug":"duguetlabs/kataleptic-realtime-hd","description":"Premium tier of /v1/realtime: same OpenAI Realtime-compatible WebSocket, served by Azure Voice Live — studio-grade HD neural voices (600+), deep noise suppression and echo cancellation, semantic turn detection. Accepts G.711 μ-law/A-law for telephony alongside PCM16. Exact transcripts. Higher latency than the standard cascade (~1.2 s to first audio vs ~0.25 s). Billed per token at Azure rates with a service margin (≈$0.03/min typical). Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["audio","text"],"output_modalities":["audio","text"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000009900","completion":"0.0000039600","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kataleptic-realtime-hd"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"kataleptic-realtime-hd","name":"Kataleptic Realtime HD (Azure Voice Live)","canonical_slug":"duguetlabs/kataleptic-realtime-hd","description":"Premium tier of /v1/realtime: same OpenAI Realtime-compatible WebSocket, served by Azure Voice Live — studio-grade HD neural voices (600+), deep noise suppression and echo cancellation, semantic turn detection. Accepts G.711 μ-law/A-law for telephony alongside PCM16. Exact transcripts. Higher latency than the standard cascade (~1.2 s to first audio vs ~0.25 s). Billed per token at Azure rates with a service margin (≈$0.03/min typical). Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["audio","text"],"output_modalities":["audio","text"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000009900","completion":"0.0000039600","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/kataleptic-realtime-hd"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"openai/gpt-realtime-2","name":"GPT Realtime 2 (native speech-to-speech)","canonical_slug":"openai/gpt-realtime-2","description":"Native speech-to-speech tier of /v1/realtime: OpenAI gpt-realtime-2 served from Azure AI Foundry behind the same WebSocket protocol. Best-in-class prosody and expressiveness — the model hears tone, not just words. Accepts G.711 μ-law/A-law for telephony alongside PCM16. Notes: transcripts are model approximations, and caller transcripts require enabling input_audio_transcription in session.update. For exact call logs use the standard or HD tiers. Billed per text + audio token, and per image token if you send images (≈$0.07/min typical for voice). Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":32000,"architecture":{"input_modalities":["audio","text","image"],"output_modalities":["audio","text"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000050000","completion":"0.0000300000","image_input_tokens":"0.0000062500","request":"0","input_cache_read":"0.0000005000"},"per_request_limits":{"prompt_tokens":32000,"completion_tokens":4096},"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-realtime-2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"gpt-realtime-2","name":"GPT Realtime 2 (native speech-to-speech)","canonical_slug":"openai/gpt-realtime-2","description":"Native speech-to-speech tier of /v1/realtime: OpenAI gpt-realtime-2 served from Azure AI Foundry behind the same WebSocket protocol. Best-in-class prosody and expressiveness — the model hears tone, not just words. Accepts G.711 μ-law/A-law for telephony alongside PCM16. Notes: transcripts are model approximations, and caller transcripts require enabling input_audio_transcription in session.update. For exact call logs use the standard or HD tiers. Billed per text + audio token, and per image token if you send images (≈$0.07/min typical for voice). Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":32000,"architecture":{"input_modalities":["audio","text","image"],"output_modalities":["audio","text"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000050000","completion":"0.0000300000","image_input_tokens":"0.0000062500","request":"0","input_cache_read":"0.0000005000"},"per_request_limits":{"prompt_tokens":32000,"completion_tokens":4096},"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-realtime-2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"openai/gpt-realtime-2.1","name":"GPT Realtime 2.1 (native speech-to-speech)","canonical_slug":"openai/gpt-realtime-2.1","description":"Latest native speech-to-speech tier of /v1/realtime: OpenAI gpt-realtime-2.1 served from Azure AI Foundry behind the same WebSocket protocol. Successor to gpt-realtime-2 — better instruction following and turn-taking at the same token price, with image input alongside audio and text. Accepts G.711 μ-law/A-law for telephony alongside PCM16. Notes: transcripts are model approximations, and caller transcripts require enabling input_audio_transcription in session.update. For exact call logs use the standard or HD tiers. Billed per text + audio token, and per image token if you send images (≈$0.07/min typical for voice). Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["audio","text","image"],"output_modalities":["audio","text"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000050000","completion":"0.0000300000","image_input_tokens":"0.0000062500","request":"0","input_cache_read":"0.0000005000"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-realtime-2.1"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"gpt-realtime-2.1","name":"GPT Realtime 2.1 (native speech-to-speech)","canonical_slug":"openai/gpt-realtime-2.1","description":"Latest native speech-to-speech tier of /v1/realtime: OpenAI gpt-realtime-2.1 served from Azure AI Foundry behind the same WebSocket protocol. Successor to gpt-realtime-2 — better instruction following and turn-taking at the same token price, with image input alongside audio and text. Accepts G.711 μ-law/A-law for telephony alongside PCM16. Notes: transcripts are model approximations, and caller transcripts require enabling input_audio_transcription in session.update. For exact call logs use the standard or HD tiers. Billed per text + audio token, and per image token if you send images (≈$0.07/min typical for voice). Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["audio","text","image"],"output_modalities":["audio","text"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000050000","completion":"0.0000300000","image_input_tokens":"0.0000062500","request":"0","input_cache_read":"0.0000005000"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-realtime-2.1"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"openai/gpt-realtime-2.1-mini","name":"GPT Realtime 2.1 Mini (native speech-to-speech)","canonical_slug":"openai/gpt-realtime-2.1-mini","description":"Cheap native speech-to-speech tier of /v1/realtime: OpenAI gpt-realtime-2.1-mini served from Azure AI Foundry. Roughly a third the audio-token cost of gpt-realtime-2.1 with the same protocol, voices and telephony codec support — the volume tier for call handling. Notes: transcripts are model approximations, and caller transcripts require enabling input_audio_transcription in session.update. Billed per text + audio token, and per image token if you send images (≈$0.02/min typical for voice). Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["audio","text","image"],"output_modalities":["audio","text"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000007500","completion":"0.0000030000","image_input_tokens":"0.0000010000","request":"0","input_cache_read":"0.0000000750"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-realtime-2.1-mini"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"gpt-realtime-2.1-mini","name":"GPT Realtime 2.1 Mini (native speech-to-speech)","canonical_slug":"openai/gpt-realtime-2.1-mini","description":"Cheap native speech-to-speech tier of /v1/realtime: OpenAI gpt-realtime-2.1-mini served from Azure AI Foundry. Roughly a third the audio-token cost of gpt-realtime-2.1 with the same protocol, voices and telephony codec support — the volume tier for call handling. Notes: transcripts are model approximations, and caller transcripts require enabling input_audio_transcription in session.update. Billed per text + audio token, and per image token if you send images (≈$0.02/min typical for voice). Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["audio","text","image"],"output_modalities":["audio","text"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000007500","completion":"0.0000030000","image_input_tokens":"0.0000010000","request":"0","input_cache_read":"0.0000000750"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["instructions","voice","turn_detection","temperature","max_output_tokens"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-realtime-2.1-mini"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"openai/gpt-4o-transcribe","name":"GPT-4o Transcribe","canonical_slug":"openai/gpt-4o-transcribe","description":"OpenAI GPT-4o Transcribe — higher-accuracy ASR with semantic context.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0060000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-4o-transcribe"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-4o-transcribe","name":"GPT-4o Transcribe","canonical_slug":"openai/gpt-4o-transcribe","description":"OpenAI GPT-4o Transcribe — higher-accuracy ASR with semantic context.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0060000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-4o-transcribe"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-4o-transcribe-diarize","name":"GPT-4o Transcribe (diarized)","canonical_slug":"openai/gpt-4o-transcribe-diarize","description":"OpenAI GPT-4o Transcribe with speaker diarization — multi-speaker meetings.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0240000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-4o-transcribe-diarize"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-4o-transcribe-diarize","name":"GPT-4o Transcribe (diarized)","canonical_slug":"openai/gpt-4o-transcribe-diarize","description":"OpenAI GPT-4o Transcribe with speaker diarization — multi-speaker meetings.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0240000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-4o-transcribe-diarize"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-transcribe","name":"GPT Transcribe","canonical_slug":"openai/gpt-transcribe","description":"OpenAI GPT Transcribe — current-generation ASR, higher accuracy than GPT-4o Transcribe at a lower rate.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0060000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-transcribe"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-transcribe","name":"GPT Transcribe","canonical_slug":"openai/gpt-transcribe","description":"OpenAI GPT Transcribe — current-generation ASR, higher accuracy than GPT-4o Transcribe at a lower rate.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0060000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-transcribe"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-4o-mini-transcribe","name":"GPT-4o Mini Transcribe","canonical_slug":"openai/gpt-4o-mini-transcribe","description":"OpenAI GPT-4o Mini Transcribe — fast, low-cost speech-to-text; the cheapest Azure transcription model we serve. Returns json or text. Billed per audio minute; a request whose prompt makes Azure's own token charge exceed that is billed at the token charge.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0045000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-4o-mini-transcribe"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"gpt-4o-mini-transcribe","name":"GPT-4o Mini Transcribe","canonical_slug":"openai/gpt-4o-mini-transcribe","description":"OpenAI GPT-4o Mini Transcribe — fast, low-cost speech-to-text; the cheapest Azure transcription model we serve. Returns json or text. Billed per audio minute; a request whose prompt makes Azure's own token charge exceed that is billed at the token charge.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0045000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-4o-mini-transcribe"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/whisper-large-v2","name":"Whisper Large V2","canonical_slug":"openai/whisper-large-v2","description":"OpenAI Whisper large-v2 served by Azure — the transcription model with timestamps: verbose_json (segments), srt and vtt. Azure retires it on 2026-12-15; for plain text use gpt-4o-mini-transcribe.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Whisper","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0097000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature","timestamp_granularities"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/whisper-large-v2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"openai/whisper-large-v2","powered_by":null,"hosting":"Azure OpenAI"},{"id":"whisper-large-v2","name":"Whisper Large V2","canonical_slug":"openai/whisper-large-v2","description":"OpenAI Whisper large-v2 served by Azure — the transcription model with timestamps: verbose_json (segments), srt and vtt. Azure retires it on 2026-12-15; for plain text use gpt-4o-mini-transcribe.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Whisper","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0097000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt","response_format","temperature","timestamp_granularities"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/whisper-large-v2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"openai/whisper-large-v2","powered_by":null,"hosting":"Azure OpenAI"},{"id":"openai/gpt-live-transcribe","name":"GPT Live Transcribe (streaming)","canonical_slug":"openai/gpt-live-transcribe","description":"OpenAI GPT Live Transcribe — streaming speech-to-text over a realtime transcription session: WebSocket /v1/realtime?intent=transcription (OpenAI Realtime protocol), partial transcripts as you speak; send input_audio_buffer.commit to finalise each item (no server VAD on this model). Billed per minute of audio sent. Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0212500000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-live-transcribe"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"gpt-live-transcribe","name":"GPT Live Transcribe (streaming)","canonical_slug":"openai/gpt-live-transcribe","description":"OpenAI GPT Live Transcribe — streaming speech-to-text over a realtime transcription session: WebSocket /v1/realtime?intent=transcription (OpenAI Realtime protocol), partial transcripts as you speak; send input_audio_buffer.commit to finalise each item (no server VAD on this model). Billed per minute of audio sent. Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"GPT-4o","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0212500000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-live-transcribe"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"openai/gpt-realtime-whisper","name":"GPT Realtime Whisper (streaming)","canonical_slug":"openai/gpt-realtime-whisper","description":"OpenAI GPT Realtime Whisper — streaming speech-to-text over a realtime transcription session: WebSocket /v1/realtime?intent=transcription (OpenAI Realtime protocol), partial transcripts as you speak; send input_audio_buffer.commit to finalise each item (no server VAD on this model). Billed per minute of audio sent. Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Whisper","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0212500000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-realtime-whisper"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"gpt-realtime-whisper","name":"GPT Realtime Whisper (streaming)","canonical_slug":"openai/gpt-realtime-whisper","description":"OpenAI GPT Realtime Whisper — streaming speech-to-text over a realtime transcription session: WebSocket /v1/realtime?intent=transcription (OpenAI Realtime protocol), partial transcripts as you speak; send input_audio_buffer.commit to finalise each item (no server VAD on this model). Billed per minute of audio sent. Docs: kataleptic.com/docs/realtime/","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio"],"output_modalities":["text"],"tokenizer":"Whisper","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0212500000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["language","prompt"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-realtime-whisper"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"openai/gpt-live-1","name":"GPT Live 1 (full-duplex voice)","canonical_slug":"openai/gpt-live-1","description":"OpenAI GPT-Live — full-duplex speech-to-speech: it listens while it speaks, so interruptions and backchannels are handled by the model itself. WebSocket /v1/live/sessions, OpenAI GPT-Live protocol (session.start, session.input_audio.append, session.output_audio.delta, session.close). Hand hard turns to a Kataleptic chat model with delegation type responses (function tools only), or to your own code with delegation type client. PCM16 at 24 kHz, or G.711 μ-law/A-law at 8 kHz for telephony. Billed per second of session time, which starts at the first input audio; delegated responses bill separately at their chat model's token rates.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio","text"],"output_modalities":["audio","text"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0937500000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["instructions","voice","audio_format","delegation"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-live-1"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"gpt-live-1","name":"GPT Live 1 (full-duplex voice)","canonical_slug":"openai/gpt-live-1","description":"OpenAI GPT-Live — full-duplex speech-to-speech: it listens while it speaks, so interruptions and backchannels are handled by the model itself. WebSocket /v1/live/sessions, OpenAI GPT-Live protocol (session.start, session.input_audio.append, session.output_audio.delta, session.close). Hand hard turns to a Kataleptic chat model with delegation type responses (function tools only), or to your own code with delegation type client. PCM16 at 24 kHz, or G.711 μ-law/A-law at 8 kHz for telephony. Billed per second of session time, which starts at the first input audio; delegated responses bill separately at their chat model's token rates.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["audio","text"],"output_modalities":["audio","text"],"tokenizer":"GPT","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","audio_minute":"0.0937500000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["instructions","voice","audio_format","delegation"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gpt-live-1"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":null},{"id":"openai/sora-2","name":"Sora 2","canonical_slug":"openai/sora-2","description":"OpenAI Sora 2 — text-to-video and image-to-video. Async: POST /v1/videos, poll GET /v1/videos/{id} until status=completed, then GET /v1/videos/{id}/content for the MP4. Sizes: 720x1280, 1280x720, 1024x1792, 1792x1024. For image-to-video, POST multipart/form-data with an `input_reference` file part (PNG, JPEG or WebP) — upstream requires the image to match the requested size, and only 720x1280 and 1280x720 accept one.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","video_second":"0.2000000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["prompt","size","seconds","model","input_reference"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/sora-2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"sora-2","name":"Sora 2","canonical_slug":"openai/sora-2","description":"OpenAI Sora 2 — text-to-video and image-to-video. Async: POST /v1/videos, poll GET /v1/videos/{id} until status=completed, then GET /v1/videos/{id}/content for the MP4. Sizes: 720x1280, 1280x720, 1024x1792, 1792x1024. For image-to-video, POST multipart/form-data with an `input_reference` file part (PNG, JPEG or WebP) — upstream requires the image to match the requested size, and only 720x1280 and 1280x720 accept one.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text","image"],"output_modalities":["video"],"tokenizer":"Other","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","video_second":"0.2000000000"},"per_request_limits":{"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["prompt","size","seconds","model","input_reference"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/sora-2"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure OpenAI"},{"id":"qwen/qwen3-8b","name":"Qwen 3 8B","canonical_slug":"qwen/qwen3-8b","description":"Qwen 3 8B — fast multilingual model, self-hosted on our own GPU fleet.","created":1775000000,"context_length":32768,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.0000000500","completion":"0.0000000800","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":32768,"completion_tokens":8192},"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/qwen3-8b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"Qwen/Qwen3-8B","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"qwen3-8b","name":"Qwen 3 8B","canonical_slug":"qwen/qwen3-8b","description":"Qwen 3 8B — fast multilingual model, self-hosted on our own GPU fleet.","created":1775000000,"context_length":32768,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.0000000500","completion":"0.0000000800","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":32768,"completion_tokens":8192},"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/qwen3-8b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"Qwen/Qwen3-8B","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"qwen/qwen2.5-coder-7b","name":"Qwen 2.5 Coder 7B","canonical_slug":"qwen/qwen2.5-coder-7b","description":"Qwen 2.5 Coder 7B — code-specialised self-hosted model.","created":1775000000,"context_length":32768,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.0000000500","completion":"0.0000000800","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":32768,"completion_tokens":8192},"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/qwen2.5-coder-7b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"Qwen/Qwen2.5-Coder-7B-Instruct","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"qwen2.5-coder-7b","name":"Qwen 2.5 Coder 7B","canonical_slug":"qwen/qwen2.5-coder-7b","description":"Qwen 2.5 Coder 7B — code-specialised self-hosted model.","created":1775000000,"context_length":32768,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":"0.0000000500","completion":"0.0000000800","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":32768,"completion_tokens":8192},"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/qwen2.5-coder-7b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"Qwen/Qwen2.5-Coder-7B-Instruct","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"mistralai/mistral-nemo-12b","name":"Mistral Nemo 12B","canonical_slug":"mistralai/mistral-nemo-12b","description":"Mistral Nemo 12B — strong reasoning, self-hosted on our own GPU fleet.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.0000001000","completion":"0.0000001500","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":8192},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/mistral-nemo-12b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"mistralai/Mistral-Nemo-Instruct-2407","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"mistral-nemo-12b","name":"Mistral Nemo 12B","canonical_slug":"mistralai/mistral-nemo-12b","description":"Mistral Nemo 12B — strong reasoning, self-hosted on our own GPU fleet.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":"0.0000001000","completion":"0.0000001500","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":8192},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/mistral-nemo-12b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"mistralai/Mistral-Nemo-Instruct-2407","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"google/gemma3-27b","name":"Gemma 3 27B","canonical_slug":"google/gemma3-27b","description":"Google Gemma 3 27B — strong vision + text model, self-hosted on our own GPU fleet.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":"gemma"},"pricing":{"prompt":"0.0000001500","completion":"0.0000002000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":8192},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gemma3-27b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"google/gemma-3-27b-it","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"gemma3-27b","name":"Gemma 3 27B","canonical_slug":"google/gemma3-27b","description":"Google Gemma 3 27B — strong vision + text model, self-hosted on our own GPU fleet.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":"gemma"},"pricing":{"prompt":"0.0000001500","completion":"0.0000002000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":8192},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/gemma3-27b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"google/gemma-3-27b-it","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"thudm/glm4-9b","name":"GLM-4 9B","canonical_slug":"thudm/glm4-9b","description":"Zhipu AI GLM-4 9B — bilingual (EN/ZH) chat model, self-hosted.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GLM","instruct_type":"chatglm"},"pricing":{"prompt":"0.0000000500","completion":"0.0000000800","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/glm4-9b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"THUDM/glm-4-9b-chat","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"glm4-9b","name":"GLM-4 9B","canonical_slug":"thudm/glm4-9b","description":"Zhipu AI GLM-4 9B — bilingual (EN/ZH) chat model, self-hosted.","created":1775000000,"context_length":128000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GLM","instruct_type":"chatglm"},"pricing":{"prompt":"0.0000000500","completion":"0.0000000800","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":128000,"completion_tokens":4096},"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"supported_parameters":["temperature","top_p","stop","max_tokens","seed","tools","tool_choice"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/glm4-9b"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"THUDM/glm-4-9b-chat","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"nomic-ai/nomic-embed","name":"Nomic Embed Text","canonical_slug":"nomic-ai/nomic-embed","description":"High-quality text embeddings, self-hosted.","created":1775000000,"context_length":8192,"architecture":{"input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000000200","completion":"0.0000000000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":8192,"completion_tokens":0},"top_provider":{"context_length":8192,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":[],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/nomic-embed"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"nomic-ai/nomic-embed-text-v1.5","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"nomic-embed","name":"Nomic Embed Text","canonical_slug":"nomic-ai/nomic-embed","description":"High-quality text embeddings, self-hosted.","created":1775000000,"context_length":8192,"architecture":{"input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":"0.0000000200","completion":"0.0000000000","image":"0","request":"0"},"per_request_limits":{"prompt_tokens":8192,"completion_tokens":0},"top_provider":{"context_length":8192,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":[],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/nomic-embed"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":"nomic-ai/nomic-embed-text-v1.5","powered_by":"xinity-ai · github.com/xinity-ai","hosting":"self-hosted (sovereign fleet, orchestrated by xinity-ai)"},{"id":"microsoft/azure-speech-neural","name":"Azure Speech Neural","canonical_slug":"microsoft/azure-speech-neural","description":"Microsoft first-party text-to-speech via /v1/audio/speech. Select a voice from /v1/audio/voices. Binary audio streaming, including PCM and G.711 for telephony. Billed per input character; Han characters count twice. Available voices depend on the resource.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","input_character":"0.0000187500"},"per_request_limits":{"input_characters":4096,"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["voice","response_format","sample_rate"],"type":"tts","endpoints":["/v1/audio/speech","/v1/audio/voices"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/azure-speech-neural"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure Speech"},{"id":"azure-speech-neural","name":"Azure Speech Neural","canonical_slug":"microsoft/azure-speech-neural","description":"Microsoft first-party text-to-speech via /v1/audio/speech. Select a voice from /v1/audio/voices. Binary audio streaming, including PCM and G.711 for telephony. Billed per input character; Han characters count twice. Available voices depend on the resource.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","input_character":"0.0000187500"},"per_request_limits":{"input_characters":4096,"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["voice","response_format","sample_rate"],"type":"tts","endpoints":["/v1/audio/speech","/v1/audio/voices"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/azure-speech-neural"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure Speech"},{"id":"microsoft/azure-speech-hd","name":"Azure Speech DragonHD","canonical_slug":"microsoft/azure-speech-hd","description":"Microsoft first-party text-to-speech via /v1/audio/speech. Select a voice from /v1/audio/voices. Binary audio streaming, including PCM and G.711 for telephony. Billed per input character; Han characters count twice. Available voices depend on the resource.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","input_character":"0.0000275000"},"per_request_limits":{"input_characters":4096,"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["voice","response_format","sample_rate"],"type":"tts","endpoints":["/v1/audio/speech","/v1/audio/voices"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/azure-speech-hd"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure Speech"},{"id":"azure-speech-hd","name":"Azure Speech DragonHD","canonical_slug":"microsoft/azure-speech-hd","description":"Microsoft first-party text-to-speech via /v1/audio/speech. Select a voice from /v1/audio/voices. Binary audio streaming, including PCM and G.711 for telephony. Billed per input character; Han characters count twice. Available voices depend on the resource.","created":1775000000,"context_length":0,"architecture":{"input_modalities":["text"],"output_modalities":["audio"],"tokenizer":"none","instruct_type":"none"},"pricing":{"prompt":"0.0000000000","completion":"0.0000000000","image":"0","request":"0","input_character":"0.0000275000"},"per_request_limits":{"input_characters":4096,"prompt_tokens":0,"completion_tokens":0},"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"supported_parameters":["voice","response_format","sample_rate"],"type":"tts","endpoints":["/v1/audio/speech","/v1/audio/voices"],"default_parameters":{},"links":{"details":"https://duguetlabs.com/models/azure-speech-hd"},"knowledge_cutoff":null,"expiration_date":null,"hugging_face_id":null,"powered_by":null,"hosting":"Azure Speech"}]}