Anthropic Messages API

curl -X POST https://router.toqan.ai/eu/v3/anthropic/v1/messages \
  -H "Authorization: Bearer $TOQAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Explain the AI Gateway in one paragraph." }
    ]
  }'

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

const client = new Anthropic({
  apiKey: process.env.TOQAN_API_KEY,
  baseURL: "https://router.toqan.ai/eu/v3/anthropic",
});

const message = await client.messages.create({
  model: "anthropic/claude-sonnet-5",
  max_tokens: 1024,
  messages: [
    { role: "user", content: "Explain the AI Gateway in one paragraph." },
  ],
});

console.log(message.content[0].text);

import anthropic
import os

client = anthropic.Anthropic(
    api_key=os.environ.get("TOQAN_API_KEY"),
    base_url="https://router.toqan.ai/eu/v3/anthropic",
)

message = client.messages.create(
    model="anthropic/claude-sonnet-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the AI Gateway in one paragraph."}],
)

print(message.content[0].text)

# First call: writes the prefix to cache
curl -X POST https://router.toqan.ai/eu/v3/anthropic/v1/messages \
  -H "Authorization: Bearer $TOQAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "max_tokens": 1024,
    "system": [
      {
        "type": "text",
        "text": "You are a senior legal assistant. The following is our complete contract template library...",
        "cache_control": { "type": "ephemeral", "ttl": "1h" }
      }
    ],
    "messages": [
      { "role": "user", "content": "Summarize clause 7 of the NDA template." }
    ]
  }'

# Second call with the same prefix: reads from cache
curl -X POST https://router.toqan.ai/eu/v3/anthropic/v1/messages \
  -H "Authorization: Bearer $TOQAN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "max_tokens": 1024,
    "system": [
      {
        "type": "text",
        "text": "You are a senior legal assistant. The following is our complete contract template library...",
        "cache_control": { "type": "ephemeral", "ttl": "1h" }
      }
    ],
    "messages": [
      { "role": "user", "content": "Summarize clause 8 of the NDA template." }
    ]
  }'

// Uses the client from the Quick Start above
const system = [
  {
    type: "text",
    text: "You are a senior legal assistant. The following is our complete contract template library...",
    cache_control: { type: "ephemeral", ttl: "1h" },
  },
];

// First call: writes the prefix to cache
await client.messages.create({
  model: "anthropic/claude-sonnet-5",
  max_tokens: 1024,
  system,
  messages: [
    { role: "user", content: "Summarize clause 7 of the NDA template." },
  ],
});

// Second call with the same prefix: reads from cache
const message = await client.messages.create({
  model: "anthropic/claude-sonnet-5",
  max_tokens: 1024,
  system,
  messages: [
    { role: "user", content: "Summarize clause 8 of the NDA template." },
  ],
});

console.log(message.usage.cache_read_input_tokens);

# Uses the client from the Quick Start above
system = [
    {
        "type": "text",
        "text": "You are a senior legal assistant. The following is our complete contract template library...",
        "cache_control": {"type": "ephemeral", "ttl": "1h"},
    }
]

# First call: writes the prefix to cache
client.messages.create(
    model="anthropic/claude-sonnet-5",
    max_tokens=1024,
    system=system,
    messages=[{"role": "user", "content": "Summarize clause 7 of the NDA template."}],
)

# Second call with the same prefix: reads from cache
message = client.messages.create(
    model="anthropic/claude-sonnet-5",
    max_tokens=1024,
    system=system,
    messages=[{"role": "user", "content": "Summarize clause 8 of the NDA template."}],
)

print(message.usage.cache_read_input_tokens)