Connect to MiniMax text models via CCAPI's proxy routing. --- ## Authentication Use `Authorization: Bearer `. --- ## Recommended Endpoint - `POST /v1/chat/completions` --- ## Capabilities - OpenAI-compatible format - Streaming (SSE) - Tool calling --- ## Models Example: `minimax-m2.5`. See `GET /v1/models` for available models. --- ## Pricing Visit the [Pricing page](/pricing?vendor=MiniMax) to see full model pricing for this provider.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/ccapi-ai:ccapi-ai-minimax-llm-integration-api"curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: CCAPI MiniMax LLM Integration API
description: CCAPI Model Gateway — OpenAI-compatible unified API
version: 1.0.0
servers:
- url: https://api.ccapi.ai
description: CCAPI API Gateway
tags:
- name: MiniMax LLM Integration
description: 'Connect to MiniMax text models via CCAPI''s proxy routing.
---
## Authentication
Use `Authorization: Bearer `.
---
## Recommended Endpoint
- `POST /v1/chat/completions`
---
## Capabilities
- OpenAI-compatible format
- Streaming (SSE)
- Tool calling
---
## Models
Example: `minimax-m2.5`.
See `GET /v1/models` for available models.
---
## Pricing
Visit the Pricing page to see full model pricing for this provider.'
paths:
/v1/chat/completions:
post:
deprecated: false
description: Unified OpenAI-compatible chat endpoint. Select the matching oneOf request schema branch by `model`; provider-specific parameters, examples, and response fields remain available in their corresponding branches.
operationId: openai-compatible-chat-completion
parameters:
- description: CCAPI token, in the format `Bearer sk-...`.
example: Bearer sk-xxxx
in: header
name: Authorization
required: true
schema:
type: string
requestBody:
content:
application/json:
examples:
basic_chat:
summary: Basic conversation
value:
messages:
- content: You are a concise assistant.
role: system
- content: Explain in three sentences why SSE is suitable for LLM streaming output.
role: user
model: gpt-6-sol
deepseek-llm-integration_basic_chat:
summary: Basic chat request
value:
messages:
- content: Explain the trade-offs between Bloom filters and hash sets.
role: user
model: deepseek-v4-flash
reasoning_effort: high
thinking:
type: enabled
deepseek-llm-integration_streaming_chat:
description: Stream a response from deepseek-v4-flash for real-time output scenarios.
summary: Streaming chat request
value:
messages:
- content: Design a concurrency control strategy for inventory deduction.
role: user
model: deepseek-v4-flash
stream: true
stream_options:
include_usage: true
minimax-llm-integration_basic_chat:
summary: Basic chat
value:
messages:
- content: Compare the trade-offs between message queues and database polling for async tasks.
role: user
model: minimax-m2.5
minimax-llm-integration_highspeed_stream:
summary: Highspeed streaming
value:
messages:
- content: You are a concise DevOps assistant.
role: system
- content: Summarize the key differences between blue-green and canary deployments.
role: user
model: minimax-m2.5
stream: true
tool_calling:
summary: Tool calling
value:
messages:
- content: Help me query today's weather in Shanghai.
role: user
model: gpt-5.5
tool_choice: auto
tools:
- function:
description: Query weather for a specified city
name: get_weather
parameters:
properties:
city:
type: string
required:
- city
type: object
type: function
schema:
oneOf:
- properties:
max_completion_tokens:
description: Maximum output token field compatible with Responses/newer models.
type: integer
max_tokens:
description: Maximum number of output tokens.
type: integer
messages:
description: Conversation message list.
items:
properties:
content:
description: Message content, supports plain text or a multimodal content array.
oneOf:
- type: string
- items:
properties:
image_url:
properties:
url:
type: string
type: object
text:
type: string
type:
enum:
- text
- image_url
type: string
type: object
type: array
role:
enum:
- system
- user
- assistant
- tool
type: string
tool_call_id:
type: string
required:
- role
- content
type: object
type: array
model:
description: Model name, e.g. `gpt-6-sol`, `gpt-5.5`, `gpt-6-astra`.
type: string
reasoning_effort:
description: Reasoning effort, e.g. `low`, `medium`, `high`.
type: string
response_format:
description: Response format, e.g. `{"type":"json_object"}`.
properties:
type:
enum:
- text
- json_object
type: string
type: object
stream:
default: false
description: Whether to enable streaming output.
type: boolean
temperature:
description: Sampling temperature.
type: number
tool_choice:
description: Tool calling strategy.
oneOf:
- enum:
- none
- auto
- required
type: string
- properties:
function:
properties:
name:
type: string
required:
- name
type: object
type:
enum:
- function
type: string
type: object
tools:
description: OpenAI function calling format.
items:
properties:
function:
properties:
description:
type: string
name:
type: string
parameters:
type: object
required:
- name
type: object
type:
enum:
- function
type: string
required:
- type
- function
type: object
type: array
top_p:
description: Top-p sampling parameter.
type: number
required:
- model
- messages
title: OpenAI LLM Integration
type: object
- properties:
max_tokens:
description: Maximum number of tokens to generate.
type: integer
messages:
description: List of conversation messages.
items:
properties:
content:
description: Message content.
type: string
role:
enum:
- system
- user
- assistant
- tool
type: string
tool_call_id:
description: Tool call ID (used when role=tool).
type: string
required:
- role
- content
type: object
type: array
model:
description: Use Flash for high-throughput workloads and Pro for complex reasoning or agentic coding.
enum:
- deepseek-v4-flash
- deepseek-v4-pro
example: deepseek-v4-flash
type: string
reasoning_effort:
description: Reasoning effort used while thinking mode is enabled.
enum:
- high
- max
type: string
response_format:
description: Set type=json_object for JSON output and also request JSON in the prompt.
properties:
type:
enum:
- text
- json_object
type: string
type: object
stream:
default: false
description: Enable streaming response (SSE).
type: boolean
stream_options:
description: Only use with stream=true.
properties:
include_usage:
description: Emit total usage in a final chunk before [DONE].
type: boolean
type: object
temperature:
description: Sampling temperature, range 0-2.
maximum: 2
minimum: 0
type: number
thinking:
description: Thinking mode is enabled by default.
properties:
type:
default: enabled
enum:
- enabled
- disabled
type: string
type: object
tool_choice:
description: 'Tool selection mode: `none`, `auto`, `required`, or a specific tool object.'
oneOf:
- enum:
- none
- auto
- required
type: string
- type: object
tools:
description: List of tool/function definitions.
items:
properties:
function:
properties:
description:
type: string
name:
type: string
parameters:
type: object
type: object
type:
enum:
- function
type: string
type: object
type: array
top_p:
description: Nucleus sampling probability mass.
maximum: 1
minimum: 0
type: number
required:
- model
- messages
title: DeepSeek LLM Integration
type: object
- properties:
max_tokens:
description: Maximum number of tokens to generate.
type: integer
messages:
description: List of conversation messages.
items:
properties:
content:
description: Message content.
type: string
role:
enum:
- system
- user
- assistant
- tool
type: string
tool_call_id:
description: Tool call ID (used when role=tool).
type: string
required:
- role
- content
type: object
type: array
model:
description: Model name, e.g. `minimax-m2.5`.
example: minimax-m2.5
type: string
stream:
default: false
description: Enable streaming response (SSE).
type: boolean
temperature:
description: Sampling temperature, range 0-2.
maximum: 2
minimum: 0
type: number
tool_choice:
description: 'Tool selection mode: `none`, `auto`, `required`, or a specific tool object.'
oneOf:
- enum:
- none
- auto
- required
type: string
- type: object
tools:
description: List of tool/function definitions.
items:
properties:
function:
properties:
description:
type: string
name:
type: string
parameters:
type: object
type: object
type:
enum:
- function
type: string
type: object
type: array
top_p:
description: Nucleus sampling probability mass.
maximum: 1
minimum: 0
type: number
required:
- model
- messages
title: MiniMax LLM Integration
type: object
required: true
responses:
'200':
content:
application/json:
example:
choices:
- finish_reason: stop
index: 0
message:
content: SSE allows the server to push content incrementally, reduces time-to-first-byte, and is well-suited for long text generation scenarios.
role: assistant
created: 1741852800
id: chatcmpl_example
model: gpt-6-sol
object: chat.completion
usage:
completion_tokens: 25
prompt_tokens: 42
total_tokens: 67
schema:
oneOf:
- properties:
choices:
items:
properties:
finish_reason:
type: string
index:
type: integer
message:
properties:
content:
type: string
role:
enum:
- assistant
type: string
tool_calls:
type: array
type: object
type: object
type: array
created:
type: integer
id:
type: string
model:
type: string
object:
enum:
- chat.completion
type: string
usage:
properties:
completion_tokens:
type: integer
prompt_tokens:
type: integer
total_tokens:
type: integer
type: object
title: OpenAI LLM Integration
type: object
- properties:
choices:
items:
properties:
finish_reason:
type: string
index:
type: integer
message:
properties:
content:
type: string
reasoning_content:
description: Thinking content returned before the final answer.
type:
- string
- 'null'
role:
type: string
tool_calls:
items:
properties:
function:
properties:
arguments:
type: string
name:
type: string
type: object
id:
type: string
type:
type: string
type: object
type: array
type: object
type: object
type: array
created:
type: integer
id:
type: string
model:
type: string
object:
enum:
- chat.completion
type: string
usage:
properties:
completion_tokens:
type: integer
prompt_cache_hit_tokens:
type: integer
prompt_cache_miss_tokens:
type: integer
prompt_tokens:
type: integer
total_tokens:
type: integer
type: object
title: DeepSeek LLM Integration
type: object
- properties:
choices:
items:
properties:
finish_reason:
type: string
index:
type: integer
message:
properties:
content:
type: string
role:
type: string
tool_calls:
items:
properties:
function:
properties:
arguments:
type: string
name:
type: string
type: object
id:
type: string
type:
type: string
type: object
type: array
type: object
type: object
type: array
created:
type: integer
id:
type: string
model:
type: string
object:
enum:
- chat.completion
type: string
usage:
properties:
completion_tokens:
type: integer
prompt_tokens:
type: integer
total_tokens:
type: integer
type: object
title: MiniMax LLM Integration
type: object
text/event-stream:
schema:
description: Returns an SSE data stream when `stream=true`.
type: string
description: Success
'401':
description: Authentication failed
summary: Create Chat Completion
tags:
- MiniMax LLM Integration
x-apifox-folder: OpenAI
components:
securitySchemes:
bearer:
description: 'CCAPI API Key. Format: `Bearer sk-xxx`'
scheme: bearer
type: http
x-tagGroups:
- name: Integration Guides
tags:
- OpenClaw Integration
- Hermes Integration
- Claude Code Integration
- Codex CLI Integration
- Gemini CLI Integration
- name: Chat
tags:
- Claude / Anthropic LLM Integration
- OpenAI LLM Integration
- Google Gemini LLM Integration
- DeepSeek LLM Integration
- MiniMax LLM Integration
- name: Image
tags:
- GPT Image 2 Per-Call Image Generation
- Midjourney Imagine API
- Gemini Per-Call Image Generation
- CCAPI Image Upscale
- Z-Image Turbo
- Doubao Seedream Official Image API
- name: Video
tags:
- Gemini Video (Veo 3.1 / Omni Flash)
- Grok Imagine Video
- MiniMax H3 Family Video Generation
- Seedance Trusted Asset Library
- Seedance 2.5 / 2.0 Video Generation
- Vidu Video Generation API
- name: Audio
tags:
- Producer Task API
- Suno Task API