Anthropic Compatible API

Use the Anthropic-compatible endpoint to interact with MiMo models via the Messages API format.

Endpoint

POST https://api.mimo-v2.com/anthropic/v1/messages

Authentication

Authenticate requests using the following header:

Header	Format
`api-key`	`<your-api-key>`

You can generate API keys from Settings → API Keys in your Mimo dashboard.

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID. Options: `mimo-v2-pro`, `mimo-v2-omni`, `mimo-v2-flash`
`messages`	array	Yes	Array of message objects
`max_tokens`	integer	Yes	Maximum tokens to generate
`system`	string	No	System prompt
`temperature`	number	No	Sampling temperature (default: 1.0)
`top_p`	number	No	Nucleus sampling (default: 0.95)
`stream`	boolean	No	Enable streaming (default: false)
`stop_sequences`	array	No	Stop sequences

Message Object

Field	Type	Description
`role`	string	One of: `user`, `assistant`
`content`	string/array	Message content (text or content block array)

Example Request

curl https://api.mimo-v2.com/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "api-key: YOUR_API_KEY" \
  -d '{
    "model": "mimo-v2-pro",
    "max_tokens": 1024,
    "system": "You are a helpful assistant.",
    "messages": [
      {"role": "user", "content": "Hello, who are you?"}
    ]
  }'

Response Format

{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! I am MiMo..."
    }
  ],
  "model": "mimo-v2-pro",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 50,
    "output_tokens": 100
  }
}

Response Fields

Field	Description
`id`	Unique identifier for the message
`type`	Always `message`
`role`	Always `assistant`
`content`	Array of content blocks
`content[].type`	Content block type (e.g., `text`)
`content[].text`	The generated text
`model`	The model used
`stop_reason`	Why the model stopped: `end_turn`, `max_tokens`, or `stop_sequence`
`usage`	Token usage statistics

Streaming Response

When stream is set to true, the API returns Server-Sent Events (SSE). The stream consists of a sequence of typed events.

Streaming Request Example

curl https://api.mimo-v2.com/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "api-key: YOUR_API_KEY" \
  -d '{
    "model": "mimo-v2-pro",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "stream": true
  }'

Streaming Event Format

The stream emits a series of SSE events with different types:

event: message_start
data: {"type":"message_start","message":{"id":"msg_xxx","type":"message","role":"assistant","content":[],"model":"mimo-v2-pro","stop_reason":null,"usage":{"input_tokens":50,"output_tokens":0}}}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello"}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"!"}}

event: content_block_stop
data: {"type":"content_block_stop","index":0}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":15}}

event: message_stop
data: {"type":"message_stop"}

Stream Event Types

Event	Description
`message_start`	Indicates the start of the message with metadata
`content_block_start`	Marks the beginning of a new content block
`content_block_delta`	Contains incremental text content
`content_block_stop`	Marks the end of a content block
`message_delta`	Contains message-level updates (e.g., stop reason)
`message_stop`	Indicates the end of the stream

Unlike the OpenAI streaming format, Anthropic-compatible streaming uses typed events with an event: field followed by a data: field for each SSE event.

Endpoint

POST https://api.mimo-v2.com/anthropic/v1/messages

Authentication

Authenticate requests using the following header:

Header	Format
`api-key`	`<your-api-key>`

You can generate API keys from Settings → API Keys in your Mimo dashboard.

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	Model ID. Options: `mimo-v2-pro`, `mimo-v2-omni`, `mimo-v2-flash`
`messages`	array	Yes	Array of message objects
`max_tokens`	integer	Yes	Maximum tokens to generate
`system`	string	No	System prompt
`temperature`	number	No	Sampling temperature (default: 1.0)
`top_p`	number	No	Nucleus sampling (default: 0.95)
`stream`	boolean	No	Enable streaming (default: false)
`stop_sequences`	array	No	Stop sequences

Message Object

Field	Type	Description
`role`	string	One of: `user`, `assistant`
`content`	string/array	Message content (text or content block array)

Example Request

curl https://api.mimo-v2.com/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "api-key: YOUR_API_KEY" \
  -d '{
    "model": "mimo-v2-pro",
    "max_tokens": 1024,
    "system": "You are a helpful assistant.",
    "messages": [
      {"role": "user", "content": "Hello, who are you?"}
    ]
  }'

Response Format

{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! I am MiMo..."
    }
  ],
  "model": "mimo-v2-pro",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 50,
    "output_tokens": 100
  }
}

Response Fields

Field	Description
`id`	Unique identifier for the message
`type`	Always `message`
`role`	Always `assistant`
`content`	Array of content blocks
`content[].type`	Content block type (e.g., `text`)
`content[].text`	The generated text
`model`	The model used
`stop_reason`	Why the model stopped: `end_turn`, `max_tokens`, or `stop_sequence`
`usage`	Token usage statistics

Streaming Response

When stream is set to true, the API returns Server-Sent Events (SSE). The stream consists of a sequence of typed events.

Streaming Request Example

curl https://api.mimo-v2.com/anthropic/v1/messages \
  -H "Content-Type: application/json" \
  -H "api-key: YOUR_API_KEY" \
  -d '{
    "model": "mimo-v2-pro",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "stream": true
  }'

Streaming Event Format

The stream emits a series of SSE events with different types:

event: message_start
data: {"type":"message_start","message":{"id":"msg_xxx","type":"message","role":"assistant","content":[],"model":"mimo-v2-pro","stop_reason":null,"usage":{"input_tokens":50,"output_tokens":0}}}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello"}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"!"}}

event: content_block_stop
data: {"type":"content_block_stop","index":0}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":15}}

event: message_stop
data: {"type":"message_stop"}

Stream Event Types

Event	Description
`message_start`	Indicates the start of the message with metadata
`content_block_start`	Marks the beginning of a new content block
`content_block_delta`	Contains incremental text content
`content_block_stop`	Marks the end of a content block
`message_delta`	Contains message-level updates (e.g., stop reason)
`message_stop`	Indicates the end of the stream

Unlike the OpenAI streaming format, Anthropic-compatible streaming uses typed events with an event: field followed by a data: field for each SSE event.

Endpoint

Authentication

Request Parameters

Message Object

Example Request

Response Format

Response Fields

Streaming Response

Streaming Request Example

Streaming Event Format

Stream Event Types

Table of Contents

Anthropic Compatible API

Endpoint

Authentication

Request Parameters

Message Object

Example Request

Response Format

Response Fields

Streaming Response

Streaming Request Example

Streaming Event Format

Stream Event Types

Table of Contents