LLM Reference

Claude 4 Sonnet

Released
2025-05-14
Last refreshed
2026-05-15
Status
Researched 64d ago
DeprecatedProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool useHighlight

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
Specifications
Family
Claude 4
Released
2025-05-14
Context
200k
Architecture
Decoder Only
Knowledge cutoff
2025-10
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by

Developing safe and ethical AI systems.

San Francisco, California, United States
Founded 2021
Website
Pricing
Output / 1M
$15.00
Input / 1M
$3.00

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 proprietary 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 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Replicate API$3.00$15.00
Serverless
Snowflake Cortex--
ServerlessPartial

Capabilities

VisionMultimodalFunction CallingTool UseFine-tuning

Benchmark peer barsfor Coding

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
LiveCodeBench68.52026-04 (with thinking)Observed 2026-04-14Source
Aider Polyglot61.32026-04 (32k thinking tokens)Observed 2026-04-14Source
MMLU PRO83.7Observed 2026-04-14Source
SWE-bench Verified72.7Observed 2025-05-14Source

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Claude 4 Sonnet?

Claude 4 Sonnet has a context window of 200k tokens.

How much does Claude 4 Sonnet cost?

Claude 4 Sonnet is available at $3/1M input tokens through Replicate API.

When was Claude 4 Sonnet released?

Claude 4 Sonnet was released on 2025-05-14.

Which providers offer Claude 4 Sonnet?

Claude 4 Sonnet is available from 2 providers: Snowflake Cortex, Replicate API.

What benchmarks has Claude 4 Sonnet been tested on?

Claude 4 Sonnet has been evaluated on 4 benchmarks, including LiveCodeBench, Aider Polyglot, MMLU PRO, SWE-bench Verified.