Claude 4 Sonnet
Claude 4 Sonnet 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
- Buyers comparing 2 tracked provider routes
Do not use it for
- New production launches
- Family
- Claude 4
- Released
- 2025-05-14
- Context
- 200k
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-10
- Specialization
- general
- License
- Proprietary
- Training
- finetuned
- Fine-tuning
- 1
Cheapest of 2 routes · Replicate API
This model is deprecated. Anthropic recommends switching to Claude Sonnet 4.6.
About
Anthropic Claude 4 Sonnet API snapshot (claude-sonnet-4-20250514), deprecated April 14, 2026 with Claude API retirement scheduled for June 15, 2026. Use Claude Sonnet 4.6 for current integrations.
Claude 4 Sonnet is a model in the Claude 4 family. The structured metadata tracks a 200k-token context window, multimodal input, function calling, and tool use. This page tracks provider routes through Snowflake Cortex and Replicate API, with the cheapest tracked route listed at $3 input and $15 output per 1M tokens. Headline tracked benchmarks include LiveCodeBench 68.5, Aider Polyglot 61.3, and MMLU PRO 83.7.
Top use-case fit: coding, agents, and build tasks
Coding
3 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
1 relevant benchmark in the decision map.
Provider price ladder
Compare all 2Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Replicate API | $3.00 | $15.00 | Serverless |
| Snowflake Cortex | - | - | ServerlessPartial |
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(4)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| LiveCodeBench | 68.5 | 2026-04 (with thinking) | https://livecodebench.github.io/performances_generation.json |
| Aider Polyglot | 61.3 | 2026-04 (32k thinking tokens) | https://aider.chat/docs/leaderboards |
| MMLU PRO | 83.7 | — | https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro |
| SWE-bench Verified | 72.7 | — | https://www.anthropic.com/news/claude-4 |
Migration checks
No linked migration route is available for this model yet.