Anthropic Messages

Create messages using Anthropic Messages API format

POST /v1/messages

Create message (Anthropic format)

cURL

curl --request POST \
  --url https://api.edgee.ai/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "claude-sonnet-4.5",
  "max_tokens": 1024,
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "system": "<string>",
  "stream": false,
  "tools": [
    {
      "name": "<string>",
      "input_schema": {},
      "description": "<string>"
    }
  ],
  "tool_choice": {}
}
'

200

{
  "id": "<string>",
  "model": "<string>",
  "content": [
    {
      "text": "<string>"
    }
  ],
  "usage": {
    "input_tokens": 1,
    "output_tokens": 1,
    "cache_read_input_tokens": 1,
    "cache_creation_input_tokens": 1
  }
}

Creates a message using Anthropic’s native Messages API format. This endpoint provides the same API format as Anthropic’s official API, making it easy to migrate existing integrations or use Anthropic-specific features.

Authorizations

bearerAuthapiKeyAuth

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your API key. More info here

Headers

X-Edgee-Tags · string

Comma-separated list of tags for categorizing and filtering requests in analytics and logs. Example: production,agent,codex

X-Edgee-Debug · boolean

Enable debug mode to include additional debugging information in the response.

X-Edgee-Compression-Model · enum<string>

Compression bundle to apply.

Available options: claude, opencode, cursor, codex

x-edgee-api-key · string

Claude CLI passthrough authentication. When set, the gateway uses this key instead of x-api-key / Authorization to authenticate the request. Used by the Claude Code CLI when proxying requests through Edgee.

x-edgee-session-id · string

Claude CLI session identifier. Used to group all messages from a single CLI session in analytics.

Body

application/json

model · string · required

The model ID to use (Anthropic format, without provider prefix)

Example:

"claude-sonnet-4.5"

max_tokens · integer · required

Maximum number of tokens to generate

Required range: x >= 1

Example:

1024

messages · object[] · required

Array of message objects

Minimum array length: 1

Show child attributes

system · string object[]

System prompt as a string

stream · boolean · default: false

Enable streaming responses

tools · object[]

Tool definitions

Show child attributes

tool_choice · object

Option 1

Option 2

Option 3

Show child attributes

Response

200

application/json

Message created successfully

id · string · required

Unique identifier for this message

model · string · required

The model that generated the response

content · object[] · required

Array of content blocks

Option 1

Option 2

Option 3

Show child attributes

usage · object · required

Show child attributes

stop_reason · enum<string>

Why the model stopped generating

Available options: end_turn, max_tokens, tool_use