Claude Sonnet 4.6
Claude Sonnet 4.6 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 1m context window
- Buyers comparing 4 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- Family
- Claude 4.6
- Released
- 2026-02-17
- Context
- 1m
- Max output
- 64,000
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-08
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 6 routes · Anthropic · cache read $0.300
About
Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence. Proprietary decoder-only model with 1M-token context, 64K max output, multimodal vision, extended thinking, and function calling. Available via Anthropic API, AWS Bedrock, GCP Vertex AI, and OpenRouter at $3/1M input and $15/1M output tokens.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ D3 relevant benchmarks in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Q/$ D3 relevant benchmarks in the decision map.
Provider price ladder
Compare all 6Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Batch in / out | Cache | Route |
|---|---|---|---|---|---|
| Anthropic | $3.00 | $15.00 | $1.50 / $7.50 | read $0.300 / 5m $3.75 / 1h $6.00 | Serverless |
| AWS Bedrock | $3.00 | $15.00 | - | - | Serverless |
| GCP Vertex AI | $3.00 | $15.00 | - | - | Serverless |
| Microsoft Foundry | $3.00 | $15.00 | - | read $0.300 / 5m $3.75 / 1h $6.00 | Serverless |
Available via routers & gateways(16)
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.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(19)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| SWE-bench Verified | 79.6 | SWE-bench VerifiedObserved 2026-02-17 | — | Source |
| Terminal-Bench 2.0 | 59.1 | Terminal-Bench 2.0Observed 2026-02-17 | — | Source |
| SWE-bench Multilingual | 75.9 | SWE-bench MultilingualObserved 2026-05-21 | — | Source |
| Google-Proof Q&A | 89.9 | diamondObserved 2026-04-28 | — | Source |
| MMLU PRO | 87.3 | —Observed 2026-04-19 | — | Source |
| τ-bench | 87.5 | τ-benchObserved 2026-04-24 | — | Source |
| MultiChallenge | 57.1 | MultiChallengeObserved 2026-04-26 | — | Source |
| Chatbot Arena | 1459.0 | —Observed 2026-04-28 | — | Source |
| MMMU Pro | 75.6 | official Anthropic system card, adaptive thinking, max effort, with image cropping toolObserved 2026-02-17 | — | Source |
| SWE-rebench | 60.7 | pass@1 (best of 5 runs)Observed 2026-05-28 | — | Source |
| AIME 2025 | 94.0 | AIME 2025 (accuracy)Observed 2026-06-07 | — | Source |
| ARC-AGI-2 | 58.3 | llm-stats shows 0 (accuracy%)Observed 2026-06-07 | — | Source |
| Humanity's Last Exam | 33.2 | HLE without tools (accuracy)Observed 2026-06-07 | — | Source |
| HumanEval | 98.0 | HumanEval (pass@1)Observed 2026-06-07 | — | Source |
| LiveCodeBench | 80.0 | LiveCodeBench score (accuracy)Observed 2026-06-07 | — | Source |
| MCP-Atlas | 61.3 | llm-stats shows 0 (accuracy%)Observed 2026-06-07 | — | Source |
| Massive Multitask Language Understanding | 89.3 | MMLU (accuracy)Observed 2026-06-07 | — | Source |
| Massive Multi-discipline Multimodal Understanding | 83.6 | MMMU (accuracy)Observed 2026-06-07 | — | Source |
| CursorBench | 49.0 | CursorBench 3.1Observed 2026-06-30 | Configuration: Sonnet 4.6 Max Harness: CursorBench 3.1 Evaluator: Cursor Confidence: confirmed Notes: Highest CursorBench 3.1 score across Cursor's published effort configurations for this base model. | Source |
Migration checks
Rankings & picks(10)
Compare Claude Sonnet 4.6 with other models
Comparison and alternatives
Browse all comparisons →Show all 80 popular comparisonssorted by 7-day search impressions
Cheapest of 6 routes · Anthropic · cache read $0.300