Anthropic Compatible API

Use this family when your application already speaks Anthropic's Messages API or when you need message-block semantics that are different from OpenAI chat completions.

Published routes

Route	Purpose
`POST https://gateway.api.anyint.ai/anthropic/v1/messages`	Create a Claude-style message response
`POST https://gateway.api.anyint.ai/anthropic/v1/messages/count_tokens`	Count tokens for a message payload before sending it

Required headers

x-api-key: <ANYINT_API_KEY>
anthropic-version: 2023-06-01
content-type: application/json

When to use this family

You want Anthropic-style messages and content blocks
You want text-plus-image inputs inside the same message format
You need token estimation before sending expensive prompts

Messages route

Use /messages when you want Anthropic-style request bodies and response objects.

Core request fields

Field	Type	Required	Meaning	Example
`model`	string	Yes	Claude-compatible model ID available to your account. Fetch valid IDs from the Models API.	`claude-sonnet-4-6`
`max_tokens`	integer	Yes	Maximum number of tokens to generate.	`512`
`messages`	array	Yes	Ordered conversation turns using Anthropic message format.	`[{"role":"user","content":"Hello"}]`
`system`	string or array	No	System instruction for the conversation. Use this instead of an OpenAI-style `system` role if your client follows Anthropic format.	`You are concise.`
`temperature`	number	No	Sampling temperature. Lower values are more deterministic.	`0.7`
`top_p`	number	No	Nucleus sampling control.	`1`
`top_k`	integer	No	Limits sampling to the top K tokens when supported by the model.	`40`
`stop_sequences`	array	No	Strings that stop generation when encountered.	`["\nHuman:"]`
`stream`	boolean	No	Set `true` for streaming when supported by the selected route and model.	`true`
`tools`	array	No	Anthropic-style tool definitions when supported by the model.	`[{"name":"lookup",...}]`
`tool_choice`	object	No	Anthropic-style control over which tool the model should use.	`{"type":"auto"}`

Each messages[].content value can be either:

a plain string
an array of content blocks such as text and image

Message fields

Field	Type	Required	Meaning	Example
`role`	string	Yes	Message author. Use `user` or `assistant`.	`user`
`content`	string or array	Yes	Plain text or an array of Anthropic content blocks.	`Summarize this image.`

Content block fields

Field	Type	Required	Meaning	Example
`type`	string	Yes	Block type. Common values are `text` and `image`.	`text`
`text`	string	For text blocks	Text content.	`Describe this image.`
`source.type`	string	For image blocks	Image source type.	`base64`
`source.media_type`	string	For image blocks	Image MIME type.	`image/png`
`source.data`	string	For base64 image blocks	Base64-encoded image bytes without a data URL prefix.	`<BASE64_IMAGE_DATA>`

Text-only example

curl https://gateway.api.anyint.ai/anthropic/v1/messages \
  -H "x-api-key: $ANYINT_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 512,
    "messages": [
      {"role": "user", "content": "Summarize why API gateways matter."}
    ]
  }'

Image input example

curl https://gateway.api.anyint.ai/anthropic/v1/messages \
  -H "x-api-key: $ANYINT_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 512,
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "image",
            "source": {
              "type": "base64",
              "media_type": "image/png",
              "data": "<BASE64_IMAGE_DATA>"
            }
          },
          {
            "type": "text",
            "text": "Describe what is in this image."
          }
        ]
      }
    ]
  }'

Response shape

Field	Meaning
`id`	Message identifier returned by the compatible API path
`type`	Object type, usually `message`
`role`	Assistant role for generated responses
`content[]`	Generated content blocks, usually text blocks
`model`	Model that handled the request
`stop_reason`	Why generation stopped, such as end turn, max tokens, or stop sequence
`usage.input_tokens`	Input tokens counted by the provider when available
`usage.output_tokens`	Output tokens counted by the provider when available

Token count route

Use /messages/count_tokens when you need token estimation before sending a real request.

Token count request fields

Field	Type	Required	Meaning
`model`	string	Yes	Model ID to estimate against
`messages`	array	Yes	Same message shape you plan to send to `/messages`
`system`	string or array	No	Optional system instruction included in token estimation
`tools`	array	No	Tool definitions included in token estimation when relevant

curl https://gateway.api.anyint.ai/anthropic/v1/messages/count_tokens \
  -H "x-api-key: $ANYINT_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {"role": "user", "content": "Count the tokens for this message."}
    ]
  }'

Typical use cases:

budget checks before high-context requests
UI previews that warn about large prompts
batching or queueing systems that need admission control

Common mistakes

Omitting the required anthropic-version header
Sending Authorization: Bearer instead of x-api-key
Assuming content must always be a string even though image blocks are supported
Treating /messages/count_tokens as a generation route

Anthropic Compatible API

On this page