Skip to main content
This page describes how to use Anthropic models through the AI Gateway. To learn more about the AI Gateway, see AI Gateway.

​
Quick Start

Access Anthropic’s Claude models through Orq’s unified API with automatic fallbacks, caching, and observability. 
const response = await openai.chat.completions.create({
  model: "anthropic/claude-sonnet-4-5-20250929",
  messages: [
    {
      role: "user",
      content: "Explain quantum computing in simple terms",
    },
  ],
  max_tokens: 1024,
});

​
Available Models

Orq supports all Anthropic Claude models across multiple providers for optimal availability and pricing:

​
Latest Models

ModelContextStrengthsBest For
claude-opus-4-5-20251101200KHighest intelligenceComplex reasoning, research
claude-3-5-sonnet-20241022200KBest balanceMost tasks, coding
claude-3-5-haiku-20241022200KFast responsesSimple tasks, chat

​
Provider Options

Anthropic models are available through multiple providers:
  • anthropic/ - Direct Anthropic API
  • aws/ - AWS Bedrock (enterprise features)
  • google/ - Google Vertex AI (GCP integration)
// Direct Anthropic
model: "anthropic/claude-sonnet-4-5-20250929"

// AWS Bedrock
model: "aws/anthropic/claude-sonnet-4-5-20250929"

// Google Vertex AI
model: "google/anthropic/claude-opus-4-5-20251101"

​
Key Features

​
Prompt Caching

Cache frequently used context (system prompts, documents) to reduce costs by up to 90% and latency by up to 85%. Learn more about Prompt Caching

​
Extended Thinking

Enable deep reasoning for complex problems with budget-based token allocation for internal analysis. Learn more about Extended Thinking

​
Vision Capabilities

All Claude 3+ models support image analysis with high accuracy. 
const response = await openai.chat.completions.create({
  model: "anthropic/claude-sonnet-4-5-20250929",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "What's in this image?" },
        {
          type: "image_url",
          image_url: { url: "https://example.com/image.jpg" }
        },
      ],
    },
  ],
});

​
Tool Use (Function Calling)

Claude excels at tool use with sophisticated planning and execution. 
const response = await openai.chat.completions.create({
  model: "anthropic/claude-sonnet-4-5-20250929",
  messages: [{ role: "user", content: "What's the weather in Tokyo?" }],
  tools: [
    {
      type: "function",
      function: {
        name: "get_weather",
        description: "Get current weather for a location",
        parameters: {
          type: "object",
          properties: {
            location: { type: "string" },
          },
          required: ["location"],
        },
      },
    },
  ],
});

​
Code Examples

curl -X POST https://api.orq.ai/v2/proxy/chat/completions \
  -H "Authorization: Bearer $ORQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4-5-20250929",
    "messages": [
      {
        "role": "user",
        "content": "Write a Python function to calculate Fibonacci numbers"
      }
    ],
    "max_tokens": 1024
  }'

​
Model Parameters

ParameterTypeDescriptionDefault
max_tokensnumberMaximum tokens to generate (required)-
temperaturenumberRandomness (0-1)1
top_pnumberNucleus sampling (0-1)-
top_knumberTop-K sampling-
stop_sequencesstring[]Custom stop sequences-
Note: max_tokens is required for Anthropic models. Typical values: 1024 for responses, 4096+ for long content.

​
Best Practices

Model selection:
  • Opus 4.5: Complex analysis, research, advanced reasoning
  • Sonnet 3.5: Most tasks, coding, general use (best price/performance)
  • Haiku 3.5: Simple queries, fast responses, high-volume tasks
Token management: 
// Set appropriate max_tokens based on task
const getMaxTokens = (taskType: string) => {
  const limits = {
    chat: 1024,
    summary: 500,
    generation: 4096,
    analysis: 2048,
  };
  return limits[taskType] || 1024;
};
Multi-provider strategy: 
// Use Orq's fallback system for reliability
const response = await openai.chat.completions.create({
  model: "anthropic/claude-sonnet-4-5-20250929",
  messages: [{ role: "user", content: "..." }],
  orq: {
    fallbacks: [
      { model: "aws/anthropic/claude-sonnet-4-5-20250929" },
      { model: "anthropic/claude-opus-4-5-20251101" },
    ],
  },
});

​
Response Structure

{
  "id": "msg_01ABC123",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "anthropic/claude-sonnet-4-5-20250929",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response content here"
      },
      "finish_reason": "end_turn"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 250,
    "total_tokens": 350
  }
}

​
Troubleshooting

Missing max_tokens error
  • Anthropic models require max_tokens parameter
  • Add to request: max_tokens: 1024 (or appropriate value)
High costs
  • Enable prompt caching for repeated context
  • Use smaller models (Haiku) for simple tasks
  • Monitor token usage and optimize prompts
Rate limits
  • Anthropic has tiered rate limits based on usage
  • Use Orq’s automatic retries and fallbacks
  • Consider AWS/Google providers for higher limits

​
Limitations

  • max_tokens required: Unlike OpenAI, must specify maximum output length
  • Rate limits: Vary by tier and provider
  • Context window: 200K tokens (may vary by provider)
  • System prompts: Handled differently than OpenAI (automatically converted by Orq)

​
Advanced Features

​
Streaming

const stream = await openai.chat.completions.create({
  model: "anthropic/claude-sonnet-4-5-20250929",
  messages: [{ role: "user", content: "Tell me a story" }],
  max_tokens: 2048,
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

​
PDF Input

Claude Opus 4.5 supports direct PDF analysis: 
const response = await openai.chat.completions.create({
  model: "anthropic/claude-opus-4-5-20251101",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Summarize this document" },
        {
          type: "document",
          document: {
            type: "pdf",
            url: "https://example.com/document.pdf"
          }
        },
      ],
    },
  ],
  max_tokens: 2048,
});

​
Reference