anthropic/claude-sonnet-4-5 logo

anthropic/claude-sonnet-4-5

Claude Sonnet 4.5 is a strong multimodal model for vision-enabled reasoning, with a default 200k token context window and longer-context access via beta headers.

Anthropic Vision Up to 200K Tokens (1M via beta header `context-1m-2025-08-07`)
Get API Key
Try in Playground
Free Trial Credit On first TopUp of minimum $5
$1.00

api_example.sh

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "anthropic/claude-sonnet-4-5",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image? Describe the main elements."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
          }
        }
      ]
    }
  ],
  "max_tokens": 8192,
  "temperature": 0.2,
  "stream": true,
  "top_p": 0
}'

Technical Specifications

Model Architecture & Performance

Variant Claude Sonnet 4.5
Context Length Up to 200K Tokens (1M via beta header `context-1m-2025-08-07`)
Architecture Claude 4.x multimodal model with thinking + context-aware token budgeting (internal architecture not publicly disclosed)
Developers Anthropic

Pricing

Pay-per-use, no commitments

Input Tokens $3.00/1M Tokens
Output Tokens $15.00/1M Tokens
Cached Input Tokens $0.30/1M Tokens

API Reference

Complete parameter documentation

Parameter Type Default Description
stream boolean true Enable streaming responses for real-time output.
temperature number 0.2 Controls randomness. Higher values can increase creativity.
max_tokens number 8192 Maximum number of tokens to generate in the response.
top_p number 0 Nucleus sampling: considers tokens with top_p probability mass.
reasoning_effort select medium Controls how much reasoning depth Claude applies (quality vs latency).

Explore the full request and response schema in our external API documentation

Performance

Strengths & considerations

Strengths Considerations
Context awareness for better long-context execution
Vision support
Strong quality and speed balance
Longest context tier requires beta header usage for requests beyond 200k

Use cases

Recommended applications for this model

Vision-assisted analysis and structured extraction
Agentic workflows that need context awareness
Long-running customer support and ops automation

Enterprise
Platform Integration

Docker

Docker Support

Official Docker images for containerized deployments

Kubernetes

Kubernetes Ready

Production-grade KBS manifests and Helm charts

SDK

SDK Libraries

Official SDKs for Python, Javascript, Go, and Java

Don't let your AI control you. Control your AI the Qubrid way!

Have questions? Want to Partner with us? Looking for larger deployments or custom fine-tuning? Let's collaborate on the right setup for your workloads.

"Qubrid enabled us to deploy production AI agents with reliable tool-calling and step tracing. We now ship agents faster with full visibility into every decision and API call."

AI Agents Team

Agent Systems & Orchestration