Messages (Anthropic)

curl https://gateway.toolken.ai/v1/messages \
  -H "X-Toolken-Key: tk_live_..." \
  -H "x-api-key: sk-ant-api03-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Summarize the Toolken pricing model."}]
  }'

import anthropic

client = anthropic.Anthropic(
    api_key="sk-ant-api03-...",
    base_url="https://gateway.toolken.ai",
    default_headers={"X-Toolken-Key": "tk_live_..."},
)
client.messages.create(
    model="claude-opus-4-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarize the Toolken pricing model."}],
)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "sk-ant-api03-...",
  baseURL: "https://gateway.toolken.ai",
  defaultHeaders: { "X-Toolken-Key": "tk_live_..." },
});
await client.messages.create({
  model: "claude-opus-4-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize the Toolken pricing model." }],
});

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4-5",
  "content": [
    {
      "type": "text",
      "text": "Toolken charges per token proxied through the gateway, with costs attributed by feature and customer."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 11,
    "output_tokens": 32
  }
}

POST

messages

curl https://gateway.toolken.ai/v1/messages \
  -H "X-Toolken-Key: tk_live_..." \
  -H "x-api-key: sk-ant-api03-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Summarize the Toolken pricing model."}]
  }'

import anthropic

client = anthropic.Anthropic(
    api_key="sk-ant-api03-...",
    base_url="https://gateway.toolken.ai",
    default_headers={"X-Toolken-Key": "tk_live_..."},
)
client.messages.create(
    model="claude-opus-4-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarize the Toolken pricing model."}],
)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "sk-ant-api03-...",
  baseURL: "https://gateway.toolken.ai",
  defaultHeaders: { "X-Toolken-Key": "tk_live_..." },
});
await client.messages.create({
  model: "claude-opus-4-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize the Toolken pricing model." }],
});

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4-5",
  "content": [
    {
      "type": "text",
      "text": "Toolken charges per token proxied through the gateway, with costs attributed by feature and customer."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 11,
    "output_tokens": 32
  }
}

Pass-through to Anthropic’s Messages API. Requests to /v1/messages are automatically routed to Anthropic. Use your Anthropic SDK with base_url set to https://gateway.toolken.ai — the SDK appends /v1/messages automatically.

Headers

string

required

Your Toolken API key. Validated by the gateway and stripped before forwarding.

string

required

Your Anthropic API key (e.g. sk-ant-api03-...). The Anthropic SDK injects this header automatically. Forwarded verbatim by the gateway, never stored.

string

Primary attribution channel. JSON object of key-value pairs (e.g. {"agent":"research-agent","customer_id":"cust_abc"}). Each key becomes a groupable dimension in the dashboard.

string

Flat-header shorthand. X-Toolken-Metadata-Agent: research-agent writes metadata key agent. Equivalent to sending the same key in X-Toolken-Metadata.

string

Sets the feature metadata key. Use to group costs by agent name, workflow, UI surface, or job type.

string

Sets the customer_id metadata key. Use to attribute costs to an end-customer, org slug, or account ID.

Body

string

required

Anthropic model identifier. Must begin with claude- (e.g. claude-opus-4-5).

array

required

Conversation turns. Follows the standard Anthropic Messages schema. Each item has role (user or assistant) and content.

integer

required

Maximum tokens to generate. Required by Anthropic. The gateway enforces an upper cap configured per workspace.

string

System prompt. Forwarded verbatim to Anthropic.

boolean

If true, the gateway streams Server-Sent Events back from Anthropic.

Response

string

Unique message ID (e.g. msg_abc123).

string

Always message.

string

Always assistant.

string

The Anthropic model that produced the response.

array

Array of content blocks. Each block has type (e.g. text) and text.

string

Reason generation stopped (e.g. end_turn).

object

Token counts: input_tokens and output_tokens.

curl https://gateway.toolken.ai/v1/messages \
  -H "X-Toolken-Key: tk_live_..." \
  -H "x-api-key: sk-ant-api03-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Summarize the Toolken pricing model."}]
  }'

import anthropic

client = anthropic.Anthropic(
    api_key="sk-ant-api03-...",
    base_url="https://gateway.toolken.ai",
    default_headers={"X-Toolken-Key": "tk_live_..."},
)
client.messages.create(
    model="claude-opus-4-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Summarize the Toolken pricing model."}],
)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "sk-ant-api03-...",
  baseURL: "https://gateway.toolken.ai",
  defaultHeaders: { "X-Toolken-Key": "tk_live_..." },
});
await client.messages.create({
  model: "claude-opus-4-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize the Toolken pricing model." }],
});

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4-5",
  "content": [
    {
      "type": "text",
      "text": "Toolken charges per token proxied through the gateway, with costs attributed by feature and customer."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 11,
    "output_tokens": 32
  }
}

Gateway API

AI Gateway

Models

Toolken API

Messages (Anthropic)

Headers

Body

Response

​Headers

​Body

​Response

Headers

Body

Response