Claude Sonnet 5 vs Claude Sonnet 5.5
Claude Sonnet 5 (2026) and Claude Sonnet 5.5 (2026) are frontier-tier reasoning models from Anthropic. Both ship a 1M-token context window. On CursorBench, Claude Sonnet 5.5 leads by 31.4 pts. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Pick Claude Sonnet 5.5 for coding; token pricing is tied, so keep Claude Sonnet 5 only for already-validated prompts or route constraints.
Decision scorecard
Local evidence first| Signal | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| Best for | reasoning-heavy apps, multimodal apps, and tool-calling agents | reasoning-heavy apps, multimodal apps, and tool-calling agents |
| Decision fit | Coding, RAG, and Agents | Coding, RAG, and Agents |
| Context window | 1M | 1M |
| Cheapest output | $10/1M tokens | $10/1M tokens |
| Provider routes | 6 tracked | 5 tracked |
| Shared benchmarks | 11 shared | CursorBench leader |
Decision tradeoffs
- Claude Sonnet 5 holds a shared-benchmark lead on CursorBench, ahead by 6 points.
- Claude Sonnet 5 has broader tracked provider coverage for fallback and route flexibility.
- Claude Sonnet 5 uniquely exposes Code execution in local model data.
- Local decision data tags Claude Sonnet 5 for Coding, RAG, and Agents.
- Claude Sonnet 5.5 holds a shared-benchmark lead on CursorBench, ahead by 31.4 points.
- Claude Sonnet 5.5 has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Local decision data tags Claude Sonnet 5.5 for Coding, RAG, and Agents.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Claude Sonnet 5
$4,100
Cheapest tracked route/tier: Anthropic
Claude Sonnet 5.5
$4,100
Cheapest tracked route/tier: Anthropic
Estimated monthly gap: $0.00. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on Anthropic, AWS Bedrock, and GCP Vertex AI; start route-level A/B tests there.
- Cheapest tracked output pricing is tied, so migration risk shifts to quality, latency, and provider packaging.
- Check replacement coverage for Code execution before moving production traffic.
- Provider overlap exists on Anthropic, AWS Bedrock, and GCP Vertex AI; start route-level A/B tests there.
- Cheapest tracked output pricing is tied, so migration risk shifts to quality, latency, and provider packaging.
- Claude Sonnet 5 adds Code execution in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2026-06-30 | 2026-09-28 |
| Context window | 1M | 1M |
| Parameters | — | — |
| Architecture | Decoder Only | Decoder Only |
| License | Proprietary | Proprietary |
| Openness | Proprietary | Proprietary |
| Weights | Not released | Not released |
| Code | Unknown | Unknown |
| Commercial use | Commercial use: conditional | Commercial use: conditional |
| Knowledge cutoff | 2026-01 | 2026-06 |
Pricing and availability
| Pricing attribute | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| Input price | $2/1M tokens | $2/1M tokens |
| Output price | $10/1M tokens | $10/1M tokens |
| Providers |
Capabilities
| Capability | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | Yes | Yes |
| Reasoning | Yes | Yes |
| JSON / Tool use | Yes | Yes |
| Structured outputs | Yes | Yes |
| Code execution | Yes | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| CursorBench | 24.1 | 55.5 |
| CursorBench | 28.0 | 55.5 |
| CursorBench | 30.8 | 55.5 |
| CursorBench | 32.0 | 55.5 |
| CursorBench | 34.1 | 55.5 |
| CursorBench | 47.7 | 55.5 |
| CursorBench | 61.5 | 55.5 |
| CursorBench | 61.2 | 55.5 |
| CursorBench | 58.7 | 55.5 |
| CursorBench | 52.4 | 55.5 |
| CursorBench | 56.9 | 55.5 |
Deep dive
On shared benchmark coverage, CursorBench has Claude Sonnet 5 at 24.1 and Claude Sonnet 5.5 at 55.5, with Claude Sonnet 5.5 ahead by 31.4 points; CursorBench has Claude Sonnet 5 at 28 and Claude Sonnet 5.5 at 55.5, with Claude Sonnet 5.5 ahead by 27.5 points; CursorBench has Claude Sonnet 5 at 30.8 and Claude Sonnet 5.5 at 55.5, with Claude Sonnet 5.5 ahead by 24.7 points. The largest visible gap is 31.4 points on CursorBench, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.
The capability footprint differs most on code execution: Claude Sonnet 5. Both models share vision, multimodal input, reasoning mode, and JSON / Tool use, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.
For cost, Claude Sonnet 5 lists $2/1M input and $10/1M output tokens on the cheapest tracked provider, while Claude Sonnet 5.5 lists $2/1M input and $10/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend is tied on the cheapest tracked routes. Availability is 6 providers versus 5, so concentration risk also matters.
Choose Claude Sonnet 5 when coding workflow support and broader provider choice are central to the workload. Choose Claude Sonnet 5.5 when long-context analysis and larger context windows are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which has a larger context window, Claude Sonnet 5 or Claude Sonnet 5.5?
Claude Sonnet 5.5 supports 1M tokens, while Claude Sonnet 5 supports 1M tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Which is cheaper, Claude Sonnet 5 or Claude Sonnet 5.5?
Neither is cheaper on tracked token pricing. Both list $2/1M input and $10/1M output tokens on the cheapest tracked route. Provider discounts, batch pricing, or route-specific tiers can still change the final bill.
Is Claude Sonnet 5 or Claude Sonnet 5.5 open source?
Claude Sonnet 5 is listed under Proprietary. Claude Sonnet 5.5 is listed under Proprietary. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for vision, Claude Sonnet 5 or Claude Sonnet 5.5?
Both Claude Sonnet 5 and Claude Sonnet 5.5 expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.
Which is better for multimodal input, Claude Sonnet 5 or Claude Sonnet 5.5?
Both Claude Sonnet 5 and Claude Sonnet 5.5 expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.
Where can I run Claude Sonnet 5 and Claude Sonnet 5.5?
Claude Sonnet 5 is available on Anthropic, AWS Bedrock, GCP Vertex AI, OpenRouter, and Microsoft Foundry. Claude Sonnet 5.5 is available on Anthropic, AWS Bedrock, GCP Vertex AI, Microsoft Foundry, and OpenRouter. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-10-16. Data sourced from public model cards and provider documentation.