Text modelsAdvanced usersUpdated
POST/v1/chat/completions

API console

POST/v1/chat/completions
View keys

Requests use the API key you enter and follow standard API billing.

MiniMax M3

Request ID MiniMax-M3

Protocols

Authentication

Requests require an API key from API key management. For JSON requests, set Content-Type: application/json.

  • Authorization: Bearer YOUR_API_KEY
  • Anthropic Messages · x-api-key: YOUR_API_KEY

Request parameters

POST /v1/chat/completions

FieldTypeRequiredDescription
modelstringRequiredSet the model ID to MiniMax-M3.
messagesobject[]RequiredSend messages in conversation order. Each message has a role and content.
messages[].contentstring / object[]ConditionalThe message body. Use plain text or an array of content blocks defined by the protocol.
streambooleanOptionaltrue requests an SSE stream. false requests a JSON response. Available modes depend on the endpoint.
max_completion_tokensintegerConditionalCaps generated tokens, including reasoning tokens where applicable. Use on endpoints that accept this field.
max_tokensintegerConditionalCompatibility field for the output token limit. Choose this field or max_completion_tokens according to the endpoint.
temperaturenumberConditionalControls sampling randomness. Accepted values and whether the field takes effect depend on the model and endpoint.
top_pnumberConditionalLimits sampling candidates by cumulative probability. Use when the model and endpoint support it.
response_formatobjectConditionalFor structured output, use type: json_object, or use type: json_schema with json_schema when the endpoint supports schemas.
toolsobject[]ConditionalTool definitions available to the model. Tool types and parameter formats depend on the protocol and endpoint.
tool_choicestring / objectConditionalControls tool selection. Use a forced or named choice only when the selected endpoint supports it.

POST /v1/messages

FieldTypeRequiredDescription
modelstringRequiredSet the model ID to MiniMax-M3.
messagesobject[]RequiredSend user and assistant messages in order. Put system instructions in the top-level system field.
messages[].contentstring / object[]RequiredThe message body. Use plain text or an array of content blocks defined by the protocol.
systemstring / object[]OptionalSystem instructions as text or an array of text blocks.
max_tokensintegerRequiredCaps output tokens. The accepted limit depends on the model and endpoint.
streambooleanOptionaltrue requests an SSE stream. false requests a JSON response. Available modes depend on the endpoint.
temperaturenumberConditionalControls sampling randomness. Accepted values and whether the field takes effect depend on the model and endpoint.
top_pnumberConditionalLimits sampling candidates by cumulative probability. Use when the model and endpoint support it.
toolsobject[]ConditionalTool definitions available to the model. Tool types and parameter formats depend on the protocol and endpoint.
tool_choiceobjectConditionalControls tool selection. Use a forced or named choice only when the selected endpoint supports it.

POST /v1/messages/count_tokens

FieldTypeRequiredDescription
modelstringRequiredSet the model ID to MiniMax-M3.
messagesobject[]RequiredSend user and assistant messages in order. Put system instructions in the top-level system field.
messages[].contentstring / object[]RequiredThe message body. Use plain text or an array of content blocks defined by the protocol.
systemstring / object[]OptionalSystem instructions as text or an array of text blocks.
toolsobject[]ConditionalTool definitions to include in the input token count. Send the same tools as in the Messages request.

Request examples

Set your API key in the local ICODEEASY_API_KEY environment variable and choose an endpoint that accepts direct HTTP calls. For endpoints that require a specific client, follow that client’s setup guide.

Chat Completions

bash
curl -sS 'https://api.icodeeasy.cc/v1/chat/completions' \
  -H "Authorization: Bearer $ICODEEASY_API_KEY" \
  -H 'Content-Type: application/json' \
  --data '{
  "model": "MiniMax-M3",
  "messages": [
    {
      "role": "user",
      "content": "Explain how a rainbow forms in one sentence."
    }
  ],
  "stream": false
}'

Anthropic Messages

bash
curl -sS 'https://api.icodeeasy.cc/v1/messages' \
  -H "x-api-key: $ICODEEASY_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'anthropic-version: 2023-06-01' \
  --data '{
  "model": "MiniMax-M3",
  "max_tokens": 256,
  "messages": [
    {
      "role": "user",
      "content": "Explain how a rainbow forms in one sentence."
    }
  ]
}'

Count Tokens

bash
curl -sS 'https://api.icodeeasy.cc/v1/messages/count_tokens' \
  -H "x-api-key: $ICODEEASY_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'anthropic-version: 2023-06-01' \
  --data '{
  "model": "MiniMax-M3",
  "messages": [
    {
      "role": "user",
      "content": "Explain how a rainbow forms in one sentence."
    }
  ]
}'

Read the response

  • Chat Completions · Read text from choices[].message.content. In an SSE stream, incremental output appears in choices[].delta. JSON · SSE
  • Anthropic Messages · Read blocks of type text in content[]. In a stream, process SSE content block events in order. JSON · SSE
  • Count Tokens · Read the input token count from input_tokens.

Full integration guide

Capabilities and limits

  • streaming · Supported
  • tool_calling · Conditional — Depends on the compatible protocol and request format
  • image_input · Not published
  • video_input · Not supported

Model Capability Catalog · View pricing

Related guides

MiniMax Setup

Connect MiniMax through a Claude-compatible client, configure the model, Base URL, and API key, and diagnose common connection problems.

Chat Completions

Send a conversation using the OpenAI Chat format. Check that your model and selected endpoint support the Chat protocol before sending the request.

Anthropic Messages

Send a request in the Anthropic Messages format. This page covers direct HTTP calls, with Claude Code setup covered in the related guides.

Sign up and get an API key