Baseten LLM Inference API
OpenAI-compatible chat completions for Baseten's Model APIs catalog (DeepSeek V4, Qwen, GLM, Nemotron, etc.). Per-million-token pricing.
OpenAPI Specification
{
"openapi": "3.1.0",
"info": {
"title": "Baseten LLM Inference API",
"version": "1.0.0",
"description": "OpenAI-compatible API for Baseten Model APIs. Use this endpoint to interact with hosted LLMs."
},
"servers": [
{
"url": "https://inference.baseten.co",
"description": "Baseten Inference API."
}
],
"security": [
{
"ApiKeyAuth": []
}
],
"paths": {
"/v1/chat/completions": {
"post": {
"operationId": "createChatCompletion",
"summary": "Create a chat completion",
"description": "Creates a chat completion for the provided conversation. This endpoint is fully compatible with the OpenAI Chat Completions API, allowing you to use standard OpenAI SDKs by changing only the base URL and API key.",
"tags": [
"Chat Completions"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatCompletionRequest"
}
}
}
},
"responses": {
"200": {
"description": "Successful response",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ChatCompletionResponse"
}
}
}
},
"400": {
"description": "Bad request: invalid parameters."
},
"401": {
"description": "Unauthorized: invalid or missing API key."
},
"429": {
"description": "Rate limit exceeded."
},
"500": {
"description": "Internal server error."
}
},
"x-codeSamples": [
{
"lang": "python",
"label": "Python",
"source": "from openai import OpenAI\nimport os\n\nclient = OpenAI(\n base_url=\"https://inference.baseten.co/v1\",\n api_key=os.environ.get(\"BASETEN_API_KEY\"),\n)\n\nresponse = client.chat.completions.create(\n model=\"deepseek-ai/DeepSeek-V4-Pro\",\n messages=[\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Hello!\"},\n ],\n)\n\nprint(response.choices[0].message.content)"
},
{
"lang": "javascript",
"label": "JavaScript",
"source": "import OpenAI from \"openai\";\n\nconst client = new OpenAI({\n baseURL: \"https://inference.baseten.co/v1\",\n apiKey: process.env.BASETEN_API_KEY,\n});\n\nconst response = await client.chat.completions.create({\n model: \"deepseek-ai/DeepSeek-V4-Pro\",\n messages: [\n { role: \"system\", content: \"You are a helpful assistant.\" },\n { role: \"user\", content: \"Hello!\" },\n ],\n});\n\nconsole.log(response.choices[0].message.content);"
},
{
"lang": "bash",
"label": "cURL",
"source": "curl https://inference.baseten.co/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Api-Key $BASETEN_API_KEY\" \\\n -d '{\n \"model\": \"deepseek-ai/DeepSeek-V4-Pro\",\n \"messages\": [\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Hello!\"}\n ]\n }'"
}
]
}
}
},
"components": {
"schemas": {
"ChatCompletionContentPartImageParam": {
"additionalProperties": false,
"properties": {
"type": {
"const": "image_url",
"title": "Type",
"type": "string",
"description": "The content type, always `image_url`."
},
"image_url": {
"$ref": "#/components/schemas/ImageURL",
"description": "The image URL and detail settings."
}
},
"required": [
"type",
"image_url"
],
"title": "ChatCompletionContentPartImageParam",
"type": "object",
"description": "Image content part for vision models."
},
"ChatCompletionContentPartInputAudioParam": {
"additionalProperties": false,
"properties": {
"type": {
"const": "input_audio",
"title": "Type",
"type": "string",
"description": "The content type, always `input_audio`."
},
"input_audio": {
"$ref": "#/components/schemas/InputAudio",
"description": "The audio data and format."
}
},
"required": [
"type",
"input_audio"
],
"title": "ChatCompletionContentPartInputAudioParam",
"type": "object",
"description": "Audio content part for audio-capable models."
},
"ChatCompletionContentPartTextParam": {
"additionalProperties": false,
"properties": {
"type": {
"const": "text",
"title": "Type",
"type": "string",
"description": "The content type, always `text`."
},
"text": {
"title": "Text",
"type": "string",
"description": "The text content."
}
},
"required": [
"type",
"text"
],
"title": "ChatCompletionContentPartTextParam",
"type": "object",
"description": "Text content part."
},
"ChatCompletionMessageToolCallParam": {
"additionalProperties": false,
"properties": {
"id": {
"title": "Id",
"type": "string",
"description": "The ID of the tool call."
},
"index": {
"title": "Index",
"description": "The index of the tool call.",
"type": "integer"
},
"function": {
"$ref": "#/components/schemas/Function",
"description": "The function that was called."
},
"type": {
"const": "function",
"title": "Type",
"type": "string",
"description": "The type, always `function`."
}
},
"required": [
"id",
"function",
"type"
],
"title": "ChatCompletionMessageToolCallParam",
"type": "object",
"description": "A tool call in an assistant message."
},
"ChatCompletionNamedFunction": {
"additionalProperties": false,
"properties": {
"name": {
"title": "Name",
"type": "string",
"description": "The name of the function to call."
}
},
"required": [
"name"
],
"title": "ChatCompletionNamedFunction",
"type": "object",
"description": "Specifies a function to call by name."
},
"ChatCompletionNamedToolChoiceParam": {
"additionalProperties": false,
"properties": {
"function": {
"$ref": "#/components/schemas/ChatCompletionNamedFunction",
"description": "The function to call."
},
"type": {
"const": "function",
"default": "function",
"title": "Type",
"type": "string",
"description": "The type, always `function`."
}
},
"required": [
"function"
],
"title": "ChatCompletionNamedToolChoiceParam",
"type": "object",
"description": "Forces the model to call a specific function."
},
"ChatCompletionToolsParam": {
"additionalProperties": false,
"properties": {
"type": {
"const": "function",
"default": "function",
"title": "Type",
"type": "string",
"description": "The type of tool, always `function`."
},
"function": {
"$ref": "#/components/schemas/FunctionDefinition",
"description": "The function definition."
}
},
"required": [
"function"
],
"title": "ChatCompletionToolsParam",
"type": "object",
"description": "A tool that the model can call."
},
"DisaggregatedParams": {
"additionalProperties": false,
"properties": {
"request_type": {
"title": "Request Type",
"type": "string",
"description": "The type of disaggregated request."
},
"first_gen_tokens": {
"default": null,
"title": "First Gen Tokens",
"description": "First generation tokens for continuation.",
"items": {
"type": "integer"
},
"type": "array"
},
"ctx_request_id": {
"default": null,
"title": "Ctx Request Id",
"description": "Context request identifier.",
"type": "integer"
},
"opaque_state": {
"default": null,
"title": "Opaque State",
"description": "Opaque state for continuation.",
"type": "string"
},
"draft_tokens": {
"default": null,
"title": "Draft Tokens",
"description": "Draft tokens for speculative decoding.",
"items": {
"type": "integer"
},
"type": "array"
},
"multimodal_embedding_handles": {
"default": null,
"title": "Multimodal Embedding Handles",
"description": "Handles for multimodal embeddings.",
"items": {
"additionalProperties": true,
"type": "object"
},
"type": "array"
},
"multimodal_hashes": {
"default": null,
"title": "Multimodal Hashes",
"description": "Hashes for multimodal content.",
"items": {
"items": {
"type": "integer"
},
"type": "array"
},
"type": "array"
}
},
"required": [
"request_type"
],
"title": "DisaggregatedParams",
"type": "object",
"description": "Advanced parameters for disaggregated serving. Used internally."
},
"File": {
"additionalProperties": false,
"properties": {
"type": {
"const": "file",
"title": "Type",
"type": "string",
"description": "The content type, always `file`."
},
"file": {
"$ref": "#/components/schemas/FileFile",
"description": "The file data."
}
},
"required": [
"type",
"file"
],
"title": "File",
"type": "object",
"description": "File content part."
},
"FileFile": {
"additionalProperties": false,
"properties": {
"file_data": {
"default": null,
"title": "File Data",
"description": "Base64-encoded file data.",
"type": "string"
},
"file_id": {
"default": null,
"title": "File Id",
"description": "A file ID for previously uploaded files.",
"type": "string"
},
"filename": {
"default": null,
"title": "Filename",
"description": "The filename.",
"type": "string"
}
},
"title": "FileFile",
"type": "object",
"description": "File data."
},
"Function": {
"additionalProperties": false,
"properties": {
"arguments": {
"anyOf": [
{
"type": "string"
},
{
"additionalProperties": true,
"type": "object"
}
],
"title": "Arguments",
"description": "The function arguments as a JSON string or object."
},
"name": {
"title": "Name",
"type": "string",
"description": "The name of the function."
}
},
"required": [
"arguments",
"name"
],
"title": "Function",
"type": "object",
"description": "The arguments to call the function with, as generated by the model in JSON format. The model may not always generate valid JSON and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function."
},
"FunctionDefinition": {
"additionalProperties": false,
"properties": {
"name": {
"title": "Name",
"type": "string",
"description": "The name of the function."
},
"description": {
"default": null,
"title": "Description",
"description": "A description of what the function does.",
"type": "string"
},
"parameters": {
"default": null,
"title": "Parameters",
"description": "The parameters the function accepts, as a JSON Schema object.",
"additionalProperties": true,
"type": "object"
},
"strict": {
"default": false,
"title": "Strict",
"description": "If `true`, enables strict schema adherence.",
"type": "boolean"
}
},
"required": [
"name"
],
"title": "FunctionDefinition",
"type": "object",
"description": "A function definition that the model can call."
},
"ImageURL": {
"additionalProperties": false,
"properties": {
"url": {
"title": "Url",
"type": "string",
"description": "The URL of the image, or a base64-encoded data URL."
},
"detail": {
"default": null,
"title": "Detail",
"description": "The detail level: `auto` (default), `low` (512px max), or `high` (full resolution).",
"enum": [
"auto",
"low",
"high"
],
"type": "string"
}
},
"required": [
"url"
],
"title": "ImageURL",
"type": "object",
"description": "An image URL with optional detail settings."
},
"InputAudio": {
"additionalProperties": false,
"properties": {
"data": {
"title": "Data",
"type": "string",
"description": "Base64-encoded audio data."
},
"format": {
"enum": [
"wav",
"mp3"
],
"title": "Format",
"type": "string",
"description": "The audio format: `wav` or `mp3`."
}
},
"required": [
"data",
"format"
],
"title": "InputAudio",
"type": "object",
"description": "Audio input data."
},
"JsonSchema": {
"additionalProperties": false,
"properties": {
"name": {
"title": "Name",
"type": "string",
"description": "The name of the schema."
},
"description": {
"default": null,
"title": "Description",
"description": "A description of the schema.",
"type": "string"
},
"schema": {
"additionalProperties": true,
"title": "Schema",
"type": "object",
"description": "The JSON Schema definition."
},
"strict": {
"default": true,
"title": "Strict",
"description": "If `true`, enables strict schema adherence.",
"const": true,
"type": "boolean"
}
},
"required": [
"name",
"schema"
],
"title": "JsonSchema",
"type": "object",
"description": "A JSON schema for structured output."
},
"ResponseFormatGrammar": {
"additionalProperties": false,
"properties": {
"type": {
"const": "grammar",
"title": "Type",
"type": "string",
"description": "The response format type, always `grammar`."
},
"grammar": {
"title": "Grammar",
"type": "string",
"description": "The grammar definition string."
}
},
"required": [
"type",
"grammar"
],
"title": "ResponseFormatGrammar",
"type": "object",
"description": "Grammar-based response format."
},
"ResponseFormatJson": {
"additionalProperties": false,
"properties": {
"type": {
"const": "json_schema",
"title": "Type",
"type": "string",
"description": "The response format type, always `json_schema`."
},
"json_schema": {
"$ref": "#/components/schemas/JsonSchema",
"description": "The JSON schema definition."
}
},
"required": [
"type",
"json_schema"
],
"title": "ResponseFormatJson",
"type": "object",
"description": "JSON schema response format for structured outputs."
},
"ResponseFormatJsonObject": {
"additionalProperties": false,
"properties": {
"type": {
"const": "json_object",
"title": "Type",
"type": "string",
"description": "The response format type, always `json_object`."
}
},
"required": [
"type"
],
"title": "ResponseFormatJsonObject",
"type": "object",
"description": "JSON object response format."
},
"ResponseFormatStructuralTag": {
"additionalProperties": false,
"properties": {
"type": {
"const": "structural_tag",
"title": "Type",
"type": "string",
"description": "The response format type, always `structural_tag`."
},
"structural_tag": {
"title": "Structural Tag",
"type": "string",
"description": "The structural tag definition."
}
},
"required": [
"type",
"structural_tag"
],
"title": "ResponseFormatStructuralTag",
"type": "object",
"description": "Structural tag response format."
},
"ResponseFormatText": {
"additionalProperties": false,
"properties": {
"type": {
"const": "text",
"title": "Type",
"type": "string",
"description": "The response format type, always `text`."
}
},
"required": [
"type"
],
"title": "ResponseFormatText",
"type": "object",
"description": "Plain text response format."
},
"StreamOptions": {
"additionalProperties": false,
"properties": {
"include_usage": {
"default": true,
"title": "Include Usage",
"description": "If `true`, includes token usage statistics in the final streaming chunk.",
"type": "boolean"
},
"continuous_usage_stats": {
"default": true,
"title": "Continuous Usage Stats",
"description": "If `true`, includes running token usage statistics in each streaming chunk.",
"type": "boolean"
}
},
"title": "StreamOptions",
"type": "object",
"description": "Options for streaming responses."
},
"ChatCompletionRequest": {
"additionalProperties": false,
"properties": {
"messages": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ChatCompletionMessage"
},
"description": "A list of messages representing the conversation history. Supports roles: `system`, `user`, `assistant`, and `tool`."
},
"model": {
"title": "Model",
"type": "string",
"description": "The model slug to use for completion, such as `deepseek-ai/DeepSeek-V4-Pro`. Find available models at [Model APIs](https://app.baseten.co/model-apis/create)."
},
"frequency_penalty": {
"default": 0,
"title": "Frequency Penalty",
"description": "Penalizes tokens based on how frequently they appear in the text so far. Positive values decrease repetition. Support varies by model.",
"type": "number"
},
"logit_bias": {
"default": null,
"title": "Logit Bias",
"description": "A map of token IDs to bias values (-100 to 100). Use this to increase or decrease the likelihood of specific tokens appearing in the output.",
"additionalProperties": {
"type": "number"
},
"type": "object"
},
"logprobs": {
"default": false,
"title": "Logprobs",
"description": "If `true`, returns log probabilities of the output tokens. Log probability support varies by model.",
"type": "boolean"
},
"top_logprobs": {
"default": 0,
"title": "Top Logprobs",
"description": "Number of most likely tokens to return at each position (0-20). Requires `logprobs: true`. Log probability support varies by model.",
"type": "integer"
},
"max_tokens": {
"default": 4096,
"maximum": 262144,
"minimum": 1,
"title": "Max Tokens",
"type": "integer",
"description": "Maximum number of tokens to generate. If your request input plus `max_tokens` exceeds the model's context length, `max_tokens` is truncated. If your request exceeds the context length by more than 16k tokens or if `max_tokens` signals no preference, context reservation is throttled to 49512 tokens. Higher `max_tokens` values slightly deprioritize request scheduling."
},
"n": {
"default": 1,
"title": "N",
"description": "Number of completions to generate. Only `1` is supported.",
"type": "integer"
},
"presence_penalty": {
"default": 0,
"title": "Presence Penalty",
"description": "Penalizes tokens based on whether they have appeared in the text so far. Positive values encourage the model to discuss new topics. Support varies by model.",
"type": "number"
},
"response_format": {
"anyOf": [
{
"$ref": "#/components/schemas/ResponseFormatText"
},
{
"$ref": "#/components/schemas/ResponseFormatJson"
},
{
"$ref": "#/components/schemas/ResponseFormatJsonObject"
},
{
"$ref": "#/components/schemas/ResponseFormatGrammar"
},
{
"$ref": "#/components/schemas/ResponseFormatStructuralTag"
}
],
"default": null,
"title": "Response Format",
"description": "Specifies the output format. Use `{\"type\": \"json_object\"}` for JSON mode, or `{\"type\": \"json_schema\", \"json_schema\": {...}}` for structured outputs with a specific schema."
},
"seed": {
"default": null,
"title": "Seed",
"description": "Random seed for deterministic generation. Determinism is not guaranteed across different hardware or model versions.",
"type": "integer"
},
"stop": {
"anyOf": [
{
"maxLength": 1000,
"minLength": 1,
"type": "string"
},
{
"items": {
"maxLength": 1000,
"minLength": 1,
"type": "string"
},
"maxItems": 32,
"type": "array"
}
],
"title": "Stop",
"description": "Up to 32 sequences where the API stops generating further tokens. Can be a string or array of strings."
},
"stream": {
"default": false,
"title": "Stream",
"description": "If `true`, responses are streamed back as server-sent events (SSE) as they are generated.",
"type": "boolean"
},
"stream_options": {
"default": null,
"description": "Options for streaming responses. Set `include_usage: true` to receive token usage statistics in the final chunk.",
"$ref": "#/components/schemas/StreamOptions"
},
"temperature": {
"default": null,
"title": "Temperature",
"description": "Controls randomness in the output. Lower values like 0.2 produce more focused and deterministic responses. Higher values like 1.5 produce more creative and varied output.",
"maximum": 4,
"minimum": 0,
"type": "number"
},
"top_p": {
"default": 1,
"title": "Top P",
"description": "Nucleus sampling: only consider tokens with cumulative probability up to this value. Lower values like 0.1 produce more focused output.",
"exclusiveMinimum": 0,
"maximum": 1,
"type": "number"
},
"tools": {
"default": null,
"title": "Tools",
"description": "A list of tools (functions) the model may call. Each tool should have a `type: \"function\"` and a `function` object with `name`, `description`, and `parameters`.",
"items": {
"$ref": "#/components/schemas/ChatCompletionToolsParam"
},
"type": "array"
},
"tool_choice": {
"anyOf": [
{
"enum": [
"none",
"required",
"auto"
],
"type": "string"
},
{
"$ref": "#/components/schemas/ChatCompletionNamedToolChoiceParam"
}
],
"default": null,
"title": "Tool Choice",
"description": "Controls which tool (if any) the model calls.\n\n- `none`: Never call a tool.\n- `auto`: Model decides whether to call a tool.\n- `required`: Model must call at least one tool.\n- `{\"type\": \"function\", \"function\": {\"name\": \"...\"}}`: Call a specific function."
},
"parallel_tool_calls": {
"default": true,
"title": "Parallel Tool Calls",
"description": "If `true`, the model can call multiple tools in a single response.",
"type": "boolean"
},
"user": {
"default": null,
"title": "User",
"description": "A unique identifier for the end-user, useful for tracking and abuse detection.",
"type": "string"
},
"best_of": {
"default": null,
"title": "Best Of",
"description": "Number of candidate sequences to generate and return the best from. Only a value of 1 is supported.",
"maximum": 1,
"minimum": 1,
"type": "integer"
},
"top_k": {
"default": 50,
"title": "Top K",
"description": "Limits token selection to the top K most probable tokens at each step. Lower values like 10 produce more focused output. Set to -1 to disable.",
"type": "integer"
},
"top_p_min": {
"default": 0,
"title": "Top P Min",
"type": "number",
"description": "Minimum value for dynamic `top_p`. When set, `top_p` dynamically adjusts but does not go below this value."
},
"min_p": {
"default": 0,
"title": "Min P",
"type": "number",
"description": "Minimum probability threshold for token selection. Filters out tokens with probability below `min_p * max_probability`."
},
"repetition_penalty": {
"default": 1,
"title": "Repetition Penalty",
"type": "number",
"description": "Multiplicative penalty for repeated tokens. Values greater than 1.0 discourage repetition, values less than 1.0 encourage it."
},
"length_penalty": {
"default": 1,
"title": "Length Penalty",
"type": "number",
"description": "Exponential penalty applied to sequence length during beam search. Values greater than 1.0 favor longer sequences."
},
"early_stopping": {
"default": false,
"title": "Early Stopping",
"type": "boolean",
"description": "If `true`, stops generation when at least `n` complete candidates are found."
},
"bad": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"title": "Bad",
"description": "Words or phrases to avoid in the output. Support varies by model."
},
"bad_token_ids": {
"title": "Bad Token Ids",
"description": "Token IDs to avoid in the output. Support varies by model.",
"items": {
"type": "integer"
},
"type": "array"
},
"stop_token_ids": {
"title": "Stop Token Ids",
"description": "List of token IDs that cause generation to stop when encountered.",
"items": {
"type": "integer"
},
"type": "array"
},
"include_stop_str_in_output": {
"default": false,
"title": "Include Stop Str In Output",
"type": "boolean",
"description": "If `true`, includes the matched stop string in the output."
},
"ignore_eos": {
"default": false,
"title": "Ignore Eos",
"type": "boolean",
"description": "If `true`, continues generating past the end-of-sequence token."
},
"min_tokens": {
"default": 0,
"title": "Min Tokens",
"type": "integer",
"description": "Minimum number of tokens to generate before stopping. Useful for ensuring responses are not too short."
},
"skip_special_tokens": {
"default": true,
"title": "Skip Special Tokens",
"type": "boolean",
"description": "If `true`, removes special tokens from the generated output."
},
"spaces_between_special_tokens": {
"default": true,
"title": "Spaces Between Special Tokens",
"type": "boolean",
"description": "If `true`, adds spaces between special tokens in the output."
},
"truncate_prompt_tokens": {
"default": null,
"title": "Truncate Prompt Tokens",
"description": "If set, truncates the prompt to this many tokens. Useful for handling inputs that may exceed context limits.",
"minimum": 1,
"type": "integer"
},
"echo": {
"default": false,
"description": "If `true` and the last message role matches the generation role, prepends that message to the output.",
"title": "Echo",
"type": "boolean"
},
"add_g
# --- truncated at 32 KB (47 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/baseten/refs/heads/main/openapi/baseten-llm-openapi.json