Claude Sonnet 4
Claude Sonnet 4 is a legacy integration reference; evaluate Claude Sonnet 4.6 before starting new work.
Use it for
- Teams maintaining an existing integration
- Workloads that can use a 200k context window
Do not use it for
- New production launches
- Cost-sensitive launches that need sourced token pricing
- Family
- Claude 4
- Released
- 2025-08-01
- Context
- 200k
- Max output
- 64,000
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
No tracked provider token pricing is available yet.
This model is deprecated. Anthropic recommends switching to Claude Sonnet 4.6.
About
Claude Sonnet 4 API snapshot (claude-sonnet-4-20250514) is deprecated and scheduled to retire from Anthropic-operated platforms on June 15, 2026. Use Claude Sonnet 4.6 for current integrations.
Claude Sonnet 4 is a proprietary model in the Claude 4 family. The structured metadata tracks a 200k-token context window, multimodal input, and structured outputs. This page tracks provider routes through Anthropic, AWS Bedrock, OpenRouter, and 1 more, with the cheapest tracked route listed at $3 input and $15 output per 1M tokens. Headline tracked benchmarks include Massive Multi-discipline Multimodal Understanding 74.4.
Top use-case fit
RAG
Included by capability and metadata signals in the decision map.
Long context
Included by capability and metadata signals in the decision map.
Vision
1 relevant benchmark in the decision map.
Provider price ladder
Compare all 4No tracked provider token pricing is available for this model yet.
Available via routers & gateways(15)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.
Helicone
GatewayObservability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Capabilities
Benchmark peer barsfor Vision
Benchmark scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| Massive Multi-discipline Multimodal Understanding | 74.4 | — | https://mmmu-benchmark.github.io/ |
Migration checks
No linked migration route is available for this model yet.
Frequently asked questions
What is the context window of Claude Sonnet 4?
Claude Sonnet 4 has a context window of 200k tokens.
What is the max output of Claude Sonnet 4?
Claude Sonnet 4 can generate up to 64,000 output tokens.
How much does Claude Sonnet 4 cost?
Claude Sonnet 4 pricing ranges from $3.00/1M to $8.0/1M input tokens depending on the provider.
When was Claude Sonnet 4 released?
Claude Sonnet 4 was released on 2025-08-01.
Which providers offer Claude Sonnet 4?
Claude Sonnet 4 is available from 4 providers: Anthropic, AWS Bedrock, OpenRouter, Vercel AI Gateway.
What benchmarks has Claude Sonnet 4 been tested on?
Claude Sonnet 4 has been evaluated on 1 benchmark, including Massive Multi-discipline Multimodal Understanding.
No tracked provider token pricing is available yet.