--- title: "Send a conversation to a model and get a completion back. Works exactly like the OpenAI chat completions endpoint. Pass messages and a model slug, get a response with the assistant's reply. Supports streaming for real-time token delivery, tool calling for function execution, structured outputs via response_format, and controllable reasoning depth on supported models." method: POST path: "/baseten/v1/chat/completions" tags: ["Baseten"] --- # Send a conversation to a model and get a completion back. Works exactly like the OpenAI chat completions endpoint. Pass messages and a model slug, get a response with the assistant's reply. Supports streaming for real-time token delivery, tool calling for function execution, structured outputs via response_format, and controllable reasoning depth on supported models. `POST /baseten/v1/chat/completions` ## Request - Base URL: `https://api.orthogonal.com/mpp` - URL: `https://api.orthogonal.com/mpp/baseten/v1/chat/completions` - Auth: none declared - TypeScript: (a function with typed inputs; its response is checked against the schema) ## Request body - object - `messages` string[], required: Array of message objects, each with a 'role' (system, user, assistant, tool) and 'content' (string or array of content parts). This is the conversation history sent to the model. - `model` string, required: Model slug to run inference against. Available models: deepseek-ai/DeepSeek-V3-0324 (164k context, reasoning), deepseek-ai/DeepSeek-V3.1 (164k context, reasoning), zai-org/GLM-4.6 (200k context, reasoning), zai-org/GLM-4.7 (200k context, reasoning), moonshotai/Kimi-K2-Instruct-0905 (128k context), moonshotai/Kimi-K2-Thinking (262k context, always-on reasoning), moonshotai/Kimi-K2.5 (262k context), openai/gpt-oss-120b (128k context). Reasoning models support the reasoning_effort parameter for controlling thinking depth. - `frequency_penalty` number: Penalize tokens based on how often they've appeared so far. Range -2.0 to 2.0. Positive values reduce repetition. Default: 0. - `logit_bias` object: Map of token IDs to bias values (-100 to 100). Increase or decrease the likelihood of specific tokens appearing in the output. - `logprobs` boolean: If true, returns the log probabilities of each output token in the response. - `top_logprobs` number: How many of the most likely tokens (0-20) to return log probabilities for at each position. Requires logprobs to be true. - `max_tokens` number: Maximum number of tokens to generate in the response. Default is 4096. - `n` number: Number of completions to generate. Currently only supports 1. - `presence_penalty` number: Penalize tokens based on whether they've appeared at all. Range -2.0 to 2.0. Positive values encourage the model to explore new topics. Default: 0. - `response_format` object: Constrain the output format. Use {"type": "json_object"} for JSON mode, or {"type": "json_schema", "json_schema": {"name": "...", "schema": {...}}} for structured outputs with a specific schema. - `seed` number: Integer for deterministic sampling. Same seed with same parameters should return the same result. Not guaranteed across model versions. - `stop` string: Up to 4 sequences where the model will stop generating. Can be a string or array of strings. - `stream` boolean: If true, returns server-sent events (SSE) with partial message deltas as tokens are generated, instead of waiting for the full response. - `stream_options` object: Options for streaming. Use {"include_usage": true} to get a final chunk with token usage statistics. - `temperature` number: Sampling temperature between 0 and 4. Lower values (e.g. 0.2) produce more focused, deterministic output. Higher values (e.g. 1.5) increase creativity. Default is 1. - `top_p` number: Nucleus sampling threshold between 0 and 1. Only tokens within this cumulative probability mass are considered. 0.1 means only the top 10%. Use as an alternative to temperature. - `tools` string[]: Array of tool/function definitions the model can call. Each tool has {"type": "function", "function": {"name": "...", "description": "...", "parameters": {...}}}. The model may respond with tool_calls instead of content. - `tool_choice` string: Controls tool calling behavior. 'auto' lets the model decide, 'none' disables tools, 'required' forces a tool call, or pass {"type": "function", "function": {"name": "..."}} to force a specific tool. - `parallel_tool_calls` boolean: Whether the model can make multiple tool calls in parallel in a single response. Default: true. - `user` string: A unique string identifying the end user. Useful for abuse monitoring and rate limiting. - `top_k` number: Top-K sampling. Only the K most likely next tokens are considered. Lower values make output more focused. - `top_p_min` number: Minimum dynamic nucleus sampling threshold. Sets a floor for top_p when using adaptive sampling. - `min_p` number: Minimum probability threshold. Tokens below this probability relative to the most likely token are filtered out. - `repetition_penalty` number: Multiplicative penalty for repeated tokens. Values > 1.0 discourage repetition, < 1.0 encourage it. - `length_penalty` number: Penalty applied during beam search. Values > 1.0 favor longer sequences, < 1.0 favor shorter ones. - `early_stopping` boolean: In beam search, stop as soon as the required number of complete candidates are found. - `bad` string: Words or phrases the model should avoid generating. Passed as a string. - `bad_token_ids` string[]: Array of token IDs that should never appear in the output. - `stop_token_ids` string[]: Array of token IDs that will cause generation to stop when produced. - `include_stop_str_in_output` boolean: If true, includes the stop string in the generated output rather than trimming it. - `ignore_eos` boolean: If true, the model continues generating past the end-of-sequence token. - `min_tokens` number: Minimum number of tokens to generate before any stop condition can trigger. - `skip_special_tokens` boolean: If true, special tokens are removed from the output text. Default: true. - `spaces_between_special_tokens` boolean: If true, adds spaces between special tokens in the detokenized output. - `truncate_prompt_tokens` number: Truncate the prompt to this many tokens if it exceeds the limit, keeping the most recent tokens. - `echo` boolean: If true, prepends the last input message to the generated output. - `add_generation_prompt` boolean: If true, applies the model's generation prompt template. Usually needed for chat models. - `add_special_tokens` boolean: If true, adds special tokens (like BOS) to the input. Default: true. - `documents` string[]: Array of document objects for retrieval-augmented generation (RAG). Each document has content the model can reference when responding. - `chat_template` string: Custom Jinja2 template for formatting the conversation. Overrides the model's default chat template. - `chat_template_args` object: Additional arguments passed to the chat template as template variables. - `best_of` number: Number of candidate completions to generate server-side, returning the best. Currently only supports 1. - `disaggregated_params` object: Advanced parameters for distributed inference. Only relevant for disaggregated serving configurations. - `reasoning_effort` string: Controls thinking depth for reasoning models. Options: 'low', 'medium', 'high'. Default: 'medium'. Higher effort uses more tokens but produces more thorough reasoning. Supported on DeepSeek V3/V3.1, GLM 4.6/4.7, and Kimi K2 Thinking. ## Response `200` Successful response ## Other responses - `402`: Payment Required (x402 / MPP / np) ## Changes - **2026-11-08** `857e915717f4`: 1 breaking - added required request body - **2026-08-25** `806e279c8d50`: 2 info - api tag `Baseten` added - api tag `Baseten Model APIs` removed [Operation history](https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace/changes/baseten/v1/chat/completions/post.md) --- [API](https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace.md) - [All operations](https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace/llms.txt) - [OpenAPI document](https://skmtc.dev/orthogonal/apis/orthogonal-api-marketplace/revisions/f89fb77710bc?raw)