Send a conversation to a model and get a completion back

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. | ERROR: Unable to calculate price.

Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.

Endpoint

POST https://x402.orthogonal.com/baseten/v1/chat/completions

Our checks, last 30 days

We never call tools that send, buy, move money or file anything, not even without paying.

Example input (from the provider)

{
  "body": {
    "messages": [],
    "model": "model"
  },
  "bodyType": "json",
  "method": "POST",
  "type": "http"
}

Promised output schema (from the provider)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "input": {
      "additionalProperties": false,
      "properties": {
        "body": {
          "properties": {
            "add_generation_prompt": {
              "description": "If true, applies the model's generation prompt template. Usually needed for chat models.",
              "type": "boolean"
            },
            "add_special_tokens": {
              "description": "If true, adds special tokens (like BOS) to the input. Default: true.",
              "type": "boolean"
            },
            "bad": {
              "description": "Words or phrases the model should avoid generating. Passed as a string.",
              "type": "string"
            },
            "bad_token_ids": {
              "description": "Array of token IDs that should never appear in the output.",
              "type": "array"
            },
            "best_of": {
              "description": "Number of candidate completions to generate server-side, returning the best. Currently only supports 1.",
              "type": "number"
            },
            "chat_template": {
              "description": "Custom Jinja2 template for formatting the conversation. Overrides the model's default chat template.",
              "type": "string"
            },
            "chat_template_args": {
              "description": "Additional arguments passed to the chat template as template variables.",
              "type": "object"
            },
            "disaggregated_params": {
              "description": "Advanced parameters for distributed inference. Only relevant for disaggregated serving configurations.",
              "type": "object"
            },
            "documents": {
              "description": "Array of document objects for retrieval-augmented generation (RAG). Each document has content the model can reference when responding.",
              "type": "array"
            },
            "early_stopping": {
              "description": "In beam search, stop as soon as the required number of complete candidates are found.",
              "type": "boolean"
            },
            "echo": {
              "description": "If true, prepends the last input message to the generated output.",
              "type": "boolean"
            },
            "frequency_penalty": {
              "description": "Penalize tokens based on how often they've appeared so far. Range -2.0 to 2.0. Positive values reduce repetition. Default: 0.",
              "type": "number"
            },
            "ignore_eos": {
              "description": "If true, the model continues generating past the end-of-sequence token.",
              "type": "boolean"
            },
            "include_stop_str_in_output": {
              "description": "If true, includes the stop string in the generated output rather than trimming it.",
              "type": "boolean"
            },
            "length_penalty": {
              "description": "Penalty applied during beam search. Values > 1.0 favor longer sequences, < 1.0 favor shorter ones.",
              "type": "number"
            },
            "logit_bias": {
              "description": "Map of token IDs to bias values (-100 to 100). Increase or decrease the likelihood of specific tokens appearing in the output.",
              "type": "object"
            },
            "logprobs": {
              "description": "If true, returns the log probabilities of each output token in the response.",
              "type": "boolean"
            },
            "max_tokens": {
              "description": "Maximum number of tokens to generate in the response. Default is 4096.",
              "type": "number"
            },
            "messages": {
              "description": "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.",
              "type": "array"
            },
            "min_p": {
              "description": "Minimum probability threshold. Tokens below this probability relative to the most likely token are filtered out.",
              "type": "number"
            },
            "min_tokens": {
              "description": "Minimum number of tokens to generate before any stop condition can trigger.",
              "type": "number"
            },
            "model": {
              "description": "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.",
              "type": "string"
            },
            "n": {
              "description": "Number of completions to generate. Currently only supports 1.",
              "type": "number"
            },
            "parallel_tool_calls": {
              "description": "Whether the model can make multiple tool calls in parallel in a single response. Default: true.",
              "type": "boolean"
            },
            "presence_penalty": {
              "description": "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.",
              "type": "number"
            },
            "reasoning_effort": {
              "description": "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

This page as JSON