How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Need help?

Contact us
Baseten

Baseten Chat Completions API

The Chat Completions API from Baseten — 1 operation(s) for chat completions.

Documentation Provider Profile APIs.io OpenAPI GitHub

Baseten Chat Completions API is one of 3 APIs that Baseten publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Chat Completions. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, and pricing.

This API exposes 1 operation across 1 path, and defines 32 schemas. It is described by OpenAPI 3.1.0, at version 1.0.0.

Requests are made against a single base URL, https://inference.baseten.co.

1 operations 1 paths 32 schemas 1 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.1.0
API Version
1.0.0
Base URL
https://inference.baseten.co/v1
Authentication
API Key
Resource Areas
1

Authentication & Security 1

Baseten Chat Completions API declares 1 security scheme for authenticating requests. An API key is passed in the header as Authorization (ApiKeyAuth). By default, every request must be authenticated.

  • ApiKeyAuth — Use Api-Key as the scheme in the Authorization header: Authorization: Api-Key YOURAPIKEY.

Paths & Operations 1

Across 1 path, the API surfaces 1 operation — 1 POST. Each is listed below with its method, path, parameters, and response codes.

Chat Completions 1
POST
/v1/chat/completions
Create a chat completion
createChatCompletion body → 200400401429500

Schemas 32

The contract defines 32 schemas that model the data the API accepts and returns. The most detailed are ChatCompletionRequest (43 properties), DisaggregatedParams (7 properties), ChatCompletionResponse (6 properties), UsageInfo (5 properties). Each schema is shown below with its type and property counts.

Function
object
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…
2 properties 2 required
JsonSchema
object
A JSON schema for structured output.
4 properties 2 required
ResponseFormatText
object
Plain text response format.
1 property 1 required
InputAudio
object
Audio input data.
2 properties 2 required
ChatCompletionNamedToolChoiceParam
object
Forces the model to call a specific function.
2 properties 1 required
ChatCompletionRequest
object
Request body for creating a chat completion.
43 properties 2 required
ChatCompletionToolsParam
object
A tool that the model can call.
2 properties 1 required
ChatCompletionNamedFunction
object
Specifies a function to call by name.
1 property 1 required
ChatCompletionLogProb
object
Log probability information for a token.
3 properties 1 required
ResponseFormatJson
object
JSON schema response format for structured outputs.
2 properties 2 required
UsageInfo
object
Token usage statistics for the request.
5 properties
FunctionDefinition
object
A function definition that the model can call.
4 properties 1 required
DisaggregatedParams
object
Advanced parameters for disaggregated serving. Used internally.
7 properties 1 required
ChatCompletionMessageToolCallParam
object
A tool call in an assistant message.
4 properties 3 required
ResponseFormatGrammar
object
Grammar-based response format.
2 properties 2 required
ChatCompletionLogProbsContent
object
Log probability information for a token in the content.
4 properties 1 required
CompletionTokensDetails
object
Breakdown of tokens used in the completion.
4 properties
DeltaMessage
object
A delta message chunk in a streaming response.
3 properties
ChatCompletionResponseStreamChoice
object
A choice in the chat completion response.
5 properties 2 required
StreamOptions
object
Options for streaming responses.
2 properties
ChatCompletionLogProbs
object
Log probability information for the completion.
1 property
ImageURL
object
An image URL with optional detail settings.
2 properties 1 required
FunctionCall
object
The name and arguments of a function that should be called, as generated by the model.
2 properties 1 required
ChatCompletionMessage
object
A message in the conversation. Supports roles: system, user, assistant, and tool.
5 properties 1 required
ChatCompletionContentPartInputAudioParam
object
Audio content part for audio-capable models.
2 properties 2 required
ChatCompletionResponse
object
A chat completion response returned by the model.
6 properties 2 required
ChatCompletionContentPartTextParam
object
Text content part.
2 properties 2 required
ResponseFormatStructuralTag
object
Structural tag response format.
2 properties 2 required
ResponseFormatJsonObject
object
JSON object response format.
1 property 1 required
ChatCompletionContentPartImageParam
object
Image content part for vision models.
2 properties 2 required
PromptTokensDetails
object
Breakdown of tokens used in the prompt.
2 properties
ToolCall
object
A tool call generated by the model.
4 properties 2 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

baseten-chat-completions-api-openapi.yml Raw ↑

Other APIs Baseten publishes across the network.

Baseten Management & Async API
AE Profile APIs.io
Baseten Messages API
AE Profile APIs.io
#Chat Completions
← Back to B APIs
API Details
ID
baseten:baseten-chat-completions-api
Base URL
https://inference.baseten.co/v1
Docs
https://docs.baseten.co/reference/inference-api/llm-openapi-spec
Provider
Baseten
APIs.io →  GitHub →
Explore more
All APIs Providers APIs.io Network
Work with this as data

Every API here is available over the API and to AI agents over MCP. APIs is not yet its own endpoint on the v1 API. Reach this content through network search and the tag graph, or the MCP server below.

Installs https://mcp.apievangelist.com/mcp in Claude, Cursor, VS Code and the rest — one button, every client.

MCP tools for apis
4 tools reach this content
  • search_api_evangelistSearch every content type across the network at once.
  • find_relatedThe shared-tag relevance graph — what else covers this.
  • get_tagEverything one tag labels, across all content types.
  • guide_topicPRO — a curated bundle for a topic: area, guidance, rules, papers, stories, services.
All tools & prompts
Call it yourself
curl for this page
Search the network for this 
curl "https://api.apievangelist.com/v1/search?q=baseten-chat-completions-api&limit=10"
Everything under a tag 
curl "https://api.apievangelist.com/v1/tags/baseten-chat-completions-api"

Discovery needs no key. Full bodies and the synthesis endpoints are Pro.

Get an API key

Free tier, no email required. Sign in with whichever identity you already have.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have. Your account

Where this information came from

This is an independent, third-party profile of Baseten Chat Completions API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.