LLM Reference

Claude 3.7 Sonnet

Released
2024-03-04
Last refreshed
2026-07-20
Status
Researched 92d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool useHighlight

Claude 3.7 Sonnet is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 200k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2024-03-04
Context
200k
Architecture
Decoder Only
Knowledge cutoff
2024-11
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by
AnthropicAnthropic

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 6 routes · AWS Bedrock

Providers(6)
Snowflake CortexGCP Vertex AIReplicate APIOpenRouterAWS BedrockAnthropic
View 6 provider routes
Links
Website

About

Claude 3.7 Sonnet is Anthropic's advanced model with extended thinking capabilities, offering state-of-the-art reasoning for complex tasks.

Claude 3.7 Sonnet is a proprietary model in the Claude 3.7 family. The structured metadata tracks a 200k-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Snowflake Cortex, GCP Vertex AI, Replicate API, and 3 more, with the cheapest tracked route listed at $3 input and $15 output per 1M tokens. Headline tracked benchmarks include HumanEval 93.0, SWE-bench Verified 70.3, and LiveCodeBench 68.9.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

4 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ D

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 6

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
AWS Bedrock$3.00$15.00
Serverless
GCP Vertex AI$3.00$15.00
Serverless
OpenRouter$3.00$15.00
Serverless
Replicate API$3.00$15.00
Serverless

Available via routers & gateways(15)

LiteLLM

Gateway

Open-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.

Free OSSAnthropicGCP Vertex AI

OpenRouter

Hybrid

Unified 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.

PassthroughAnthropicGCP Vertex AI

Portkey

Gateway

Production 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.

SubscriptionAnthropicGCP Vertex AI

AIRouter

Router

Commercial 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.

Passthrough + feeAnthropicGCP Vertex AI

Amazon Bedrock Intelligent Prompt Routing

Router

AWS 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.

PassthroughAWS Bedrock

Helicone

Gateway

Observability-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.

SubscriptionAnthropicGCP Vertex AI

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Benchmark peer barsfor Coding

SWE-bench VerifiedRank 62 of 80
Claude Fable 5
96.0
Claude Mythos Preview
93.9
Claude Opus 4.8
88.6
Claude Opus 4.7
87.6
Claude 3.7 Sonnetcurrent
70.3
HumanEvalRank 8 of 97
Claude Sonnet 4.6
98.0
o3
96.7
Claude Opus 4.6
95.0
Grok-3
94.5
Claude 3.7 Sonnetcurrent
93.0
LiveCodeBenchRank 43 of 55
DeepSeek V4 Pro
93.5
Gemini 3.1 Pro Preview
91.7
DeepSeek V4 Flash
91.6
Qwen3.7-Max
91.6
Claude 3.7 Sonnetcurrent
68.9

Benchmark scores(6)

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
HumanEval93.02025-02Observed 2026-04-09—Source
SWE-bench Verified70.32025-02Observed 2026-04-09—Source
LiveCodeBench68.92025-02Observed 2026-04-09—Source
Aider Polyglot64.92026-04 (32k thinking tokens)Observed 2026-04-14—Source
Massive Multi-discipline Multimodal Understanding75.0—Observed 2026-04-15—Source
MMLU PRO80.3—Observed 2026-04-14—Source

Migration checks

No linked migration route is available for this model yet.

API versions

claude-3-7-sonnet-20250219

Compare Claude 3.7 Sonnet with other models

Show all 49 popular comparisonssorted by 7-day search impressions
Claude 3.7 Sonnet vs Grok-3133Claude 3.7 Sonnet vs Qwen3.6-27B126Claude 3.7 Sonnet vs GPT-5.589Claude 3.7 Sonnet vs GLM-5.180Claude 3.7 Sonnet vs o379Claude 3.7 Sonnet vs GPT-5.477Claude 3.7 Sonnet vs Gemini 2.5 Flash59Claude 3.7 Sonnet vs GPT-4o Search Preview46Claude 3.7 Sonnet vs GLM-542Claude 3.7 Sonnet vs Claude 3.5 Haiku39Claude 3.7 Sonnet vs Qwen3.5-27B37Claude 3.7 Sonnet vs Kimi K2.536Claude 3.7 Sonnet vs o3 Deep Research35Claude 3.7 Sonnet vs DeepSeek V334Claude 3.7 Sonnet vs Xiaomi MiMo-V2.5-Pro34Claude 3.7 Sonnet vs o3 Mini32Claude 3.7 Sonnet vs Mistral Large 231Claude 3.7 Sonnet vs Qwen3.5-35B-A3B27Claude 3.7 Sonnet vs Qwen3.5-397B-A17B27Claude 3.7 Sonnet vs Llama 3 8B Instruct25Claude 3.7 Sonnet vs Trinity-Large-Thinking24Claude 3.7 Sonnet vs Llama 2 13B Chat21Claude 3.7 Sonnet vs Qwen3.5-122B-A10B21Claude 3.7 Sonnet vs Llama 3 70B Instruct19Claude 3.7 Sonnet vs DeepSeek V3.118Claude 3.7 Sonnet vs Llama 2 70B Chat18Claude 3.7 Sonnet vs Kimi K2 Instruct16Claude 3.7 Sonnet vs Gemma 7B Instruct15Claude 3.7 Sonnet vs GPT-5.5 Instant15Claude 3.7 Sonnet vs Llama 3.1 70B Instruct12Claude 3.7 Sonnet vs Mistral Nemotron12Claude 3.7 Sonnet vs Code Davinci 00111Claude 3.7 Sonnet vs GPT-4o-mini Search Preview10Claude 3.7 Sonnet vs Grok 3 Mini9Claude 3.7 Sonnet vs Mistral Large 3 675B Instruct8Claude 3.7 Sonnet vs Qwen2.5-72B-Instruct7Claude 3.7 Sonnet vs GPT-5.27Claude 3.7 Sonnet vs DeepSeek R1 05286Claude 3.7 Sonnet vs Llama 3.2 1B Instruct6Claude 3.7 Sonnet vs o1-pro5Claude 3.7 Sonnet vs Mixtral 8x7B5Claude 3.7 Sonnet vs Claude 3.5 Sonnet v25Claude 3.7 Sonnet vs Phi-4 Mini Flash Reasoning4Claude 3.7 Sonnet vs Qwen3-9B4Claude 3.7 Sonnet vs Together AI - Llama 3 8B Lite4Claude 3.7 Sonnet vs GPT-5.3-Codex4Claude 3.7 Sonnet vs Phi-3 Mini 4k3Claude 3.7 Sonnet vs Qwen3-235B-A22B1Claude 3.7 Sonnet vs Gemini 2.5 Flash Live API1

Frequently asked questions

What is the context window of Claude 3.7 Sonnet?

Claude 3.7 Sonnet has a context window of 200k tokens.

How much does Claude 3.7 Sonnet cost?

Claude 3.7 Sonnet is available at $3/1M input tokens through GCP Vertex AI.

When was Claude 3.7 Sonnet released?

Claude 3.7 Sonnet was released on 2024-03-04.

Which providers offer Claude 3.7 Sonnet?

Claude 3.7 Sonnet is available from 6 providers: Snowflake Cortex, GCP Vertex AI, Replicate API, OpenRouter, AWS Bedrock, Anthropic.

What benchmarks has Claude 3.7 Sonnet been tested on?

Claude 3.7 Sonnet has been evaluated on 6 benchmarks, including HumanEval, SWE-bench Verified, LiveCodeBench, Aider Polyglot, Massive Multi-discipline Multimodal Understanding.