{"data":[{"id":"deepseek-v3.2-maas","hugging_face_id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek V3.2 Chat","created":1745011200,"description":"DeepSeek V3 model hosted on Vertex AI.","context_length":128000,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.0000002268","completion":"0.0000003402","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"deepseek/deepseek-v3.2","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"deepseek-r1-0528-maas","hugging_face_id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1 (0528)","created":1751328000,"description":"DeepSeek R1 (0528) — advanced reasoning model with chain-of-thought, hosted on Vertex AI. Excels at math, coding, and complex reasoning tasks.","context_length":163840,"max_output_length":32768,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.00000135","completion":"0.0000054","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"}],"canonical_slug":"deepseek/deepseek-r1-0528","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"top_provider":{"context_length":163840,"max_completion_tokens":32768,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"gemini-2.5-flash","hugging_face_id":"","name":"Gemini 2.5 Flash","created":1745011200,"description":"Google's Gemini 2.5 Flash via proxy.","context_length":1048576,"max_output_length":8192,"input_modalities":["text","image"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.00000027","completion":"0.00000225","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed","frequency_penalty","presence_penalty"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"google/gemini-2.5-flash","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","json_mode","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"gemini-2.5-flash-lite","hugging_face_id":"","name":"Gemini 2.5 Flash Lite","created":1745011200,"description":"Google's ultra-fast Gemini 2.5 Flash Lite via proxy.","context_length":1048576,"max_output_length":8192,"input_modalities":["text","image"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.00000009","completion":"0.00000036","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed","frequency_penalty","presence_penalty"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"google/gemini-2.5-flash-lite","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","json_mode","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"gemini-2.5-pro","hugging_face_id":"","name":"Gemini 2.5 Pro","created":1745011200,"description":"Google's flagship Gemini 2.5 Pro via proxy.","context_length":2097152,"max_output_length":8192,"input_modalities":["text","image"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.000001125","completion":"0.000009","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed","frequency_penalty","presence_penalty"],"supported_features":["tools","json_mode","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"google/gemini-2.5-pro","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"top_provider":{"context_length":2097152,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","json_mode","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"gemini-3-flash-preview","hugging_face_id":"","name":"Gemini 3 Flash Preview","created":1745011200,"description":"Preview of Gemini 3 Flash.","context_length":1048576,"max_output_length":8192,"input_modalities":["text","image"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.00000045","completion":"0.0000027","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed","frequency_penalty","presence_penalty"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"google/gemini-3-flash-preview","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","json_mode","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"gemini-3.1-flash-lite-preview","hugging_face_id":"","name":"Gemini 3.1 Flash Lite Preview","created":1745011200,"description":"Preview of Gemini 3.1 Flash Lite.","context_length":1048576,"max_output_length":8192,"input_modalities":["text","image"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.000000225","completion":"0.00000135","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed","frequency_penalty","presence_penalty"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"google/gemini-3.1-flash-lite-preview","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"top_provider":{"context_length":1048576,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","json_mode","max_tokens","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"gemini-3.1-pro-preview","hugging_face_id":"","name":"Gemini 3.1 Pro Preview","created":1745011200,"description":"Preview of Gemini 3.1 Pro.","context_length":2097152,"max_output_length":8192,"input_modalities":["text","image"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.0000018","completion":"0.0000108","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed","frequency_penalty","presence_penalty"],"supported_features":["tools","json_mode","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"google/gemini-3.1-pro-preview","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"top_provider":{"context_length":2097152,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["frequency_penalty","json_mode","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"gpt-oss-120b-maas","hugging_face_id":"","name":"GPT OSS 120B","created":1745011200,"description":"OpenAI open-weight 120B model via Vertex MaaS.","context_length":131072,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.0000000351","completion":"0.000000171","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"openai/gpt-oss-120b","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"gpt-oss-20b-maas","hugging_face_id":"","name":"GPT OSS 20B","created":1745011200,"description":"OpenAI open-weight 20B model via Vertex MaaS.","context_length":131072,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.000000027","completion":"0.000000126","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"openai/gpt-oss-20b","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"grok-4.1-fast-non-reasoning","hugging_face_id":"","name":"Grok 4.1 Fast (non-reasoning)","created":1745011200,"description":"xAI Grok 4.1 Fast non-reasoning via Vertex MaaS.","context_length":131072,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.00000018","completion":"0.00000045","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"x-ai/grok-4.1-fast","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"grok-4.1-fast-reasoning","hugging_face_id":"","name":"Grok 4.1 Fast (reasoning)","created":1745011200,"description":"xAI Grok 4.1 Fast reasoning via Vertex MaaS.","context_length":131072,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.00000018","completion":"0.00000045","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"x-ai/grok-4.1-fast","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"grok-4.20-non-reasoning","hugging_face_id":"","name":"Grok 4.20 (non-reasoning)","created":1745011200,"description":"xAI Grok 4.20 non-reasoning via Vertex MaaS.","context_length":262144,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.0000018","completion":"0.0000054","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"x-ai/grok-4.20","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"top_provider":{"context_length":262144,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"grok-4.20-reasoning","hugging_face_id":"","name":"Grok 4.20 (reasoning)","created":1745011200,"description":"xAI Grok 4.20 reasoning via Vertex MaaS.","context_length":262144,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.0000018","completion":"0.0000054","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"x-ai/grok-4.20","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"top_provider":{"context_length":262144,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"qwen3-235b-a22b-instruct-2507-maas","hugging_face_id":"","name":"Qwen3 235B A22B Instruct 2507","created":1745011200,"description":"Alibaba Qwen3 235B MoE instruct via Vertex MaaS.","context_length":262144,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.0000000639","completion":"0.00000009","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"qwen/qwen3-235b-a22b-2507","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"top_provider":{"context_length":262144,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"qwen3-coder-480b-a35b-instruct-maas","hugging_face_id":"","name":"Qwen3 Coder 480B A35B","created":1745011200,"description":"Alibaba Qwen3 Coder 480B MoE via Vertex MaaS.","context_length":262144,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.000000198","completion":"0.00000162","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"qwen/qwen3-coder","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"top_provider":{"context_length":262144,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"qwen3-next-80b-a3b-instruct-maas","hugging_face_id":"","name":"Qwen3 Next 80B A3B Instruct","created":1745011200,"description":"Alibaba Qwen3 Next 80B MoE instruct via Vertex MaaS.","context_length":262144,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.000000081","completion":"0.00000099","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"qwen/qwen3-next-80b-a3b-instruct","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"top_provider":{"context_length":262144,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}},{"id":"qwen3-next-80b-a3b-thinking-maas","hugging_face_id":"","name":"Qwen3 Next 80B A3B Thinking","created":1745011200,"description":"Alibaba Qwen3 Next 80B MoE reasoning via Vertex MaaS.","context_length":262144,"max_output_length":8192,"input_modalities":["text"],"output_modalities":["text"],"quantization":"fp16","pricing":{"prompt":"0.00000008775","completion":"0.000000702","image":"0","request":"0","input_cache_read":"0"},"supported_sampling_parameters":["temperature","top_p","top_k","stop","max_tokens","seed"],"supported_features":["tools","json_mode","structured_outputs","reasoning"],"datacenters":[{"country_code":"US"},{"country_code":"EU"}],"canonical_slug":"qwen/qwen3-next-80b-a3b-thinking","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"top_provider":{"context_length":262144,"max_completion_tokens":8192,"is_moderated":true},"per_request_limits":null,"supported_parameters":["json_mode","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"default_parameters":{"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}}]}