Anthropic model product
Claude Sonnet 4.5
5 is the best coding model in the world.
Updated Aug 12, 2026. Default version: Claude Sonnet 4.5
LLMBoard score56.0Claude Sonnet 4.5
Coverage80%8 benchmark families
Context window200KTokens
Official input price$3Anthropic API
Claude Sonnet 4.5 Specifications
Technical details for the model's default version.
- Version
- Claude Sonnet 4.5
- Released
- Sep 29, 2025
- Knowledge cutoff
- Jan 31, 2025
- Parameters
- N/A
- Context window
- 200K
- Max output
- 64K
- Inputs
- audio, image, pdf, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Claude Sonnet 4.5 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Claude Sonnet 4.5 Benchmark Results
Benchmark scores for Claude Sonnet 4.5.
| SWE-bench Verified (Agentic Coding) | 77.2% | 01 | 2 | 100.0% | C | |
| TAU-bench Airline | 70.0% | 01 | 23 | 100.0% | C | |
| TAU-bench Retail | 86.2% | 01 | 25 | 100.0% | C | |
| Terminal-Bench | 50.0% | 01 | 25 | 100.0% | C | |
| MMMUval | 77.8% | 03 | 4 | 33.3% | C | |
| OSWorld | 61.4% | 08 | 20 | 63.2% | C | |
| MMMLU | 89.1% | 13 | 49 | 75.0% | C | |
| AIME 2025 | 87.0% | 56 | 114 | 51.3% | C | |
| GPQA | 83.4% | 66 | 234 | 72.1% | C |
Claude Sonnet 4.5 Arena Results
Preference and agent-evaluation results for the default version.
| search factuality | overall | 20 | 1161.3 | 105,575 | N/A | |
| search style control | overall | 21 | 1175.8 | 105,762 | N/A | |
| document | overall | 22 | 1446.2 | 28,634 | N/A | |
| search | overall | 22 | 1158.5 | 105,762 | N/A | |
| document style control | overall | 27 | 1446.4 | 28,634 | N/A | |
| text style control | overall | 54 | 1455.8 | 82,532 | N/A | |
| text style control | overall | 56 | 1454.8 | 80,931 | N/A | |
| text factuality | overall | 57 | 1448.0 | 75,741 | N/A | |
| text factuality | overall | 61 | 1445.7 | 73,202 | N/A | |
| text | overall | 63 | 1437.8 | 80,931 | N/A | |
| webdev | overall | 63 | 1392.2 | 12,804 | N/A | |
| webdev | overall | 68 | 1385.1 | 15,179 | N/A | |
| text | overall | 73 | 1433.3 | 82,532 | N/A |
Claude Sonnet 4.5 Runtime Performance
Provider-specific output speed and catalog latency for Claude Sonnet 4.5. Runtime does not affect the capability score.
| Anthropic | 46.518 tok/s | 2.746 s | 200K | 64K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Claude Sonnet 4.5 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $3 input, $15 output per 1M
- Official provider
- Anthropic
- Lowest third-party
- From $0.43 input, $2.14 output per 1M via QiHang
- Tracked offerings
- 38
| QiHang | claude-sonnet-4-5-20250929 | global | $0.43 | $2.14 | 200K | |
| Poe | anthropic/claude-sonnet-4.5 | global | $2.6 | $13 | 983K | |
| Jiekou.AI | claude-sonnet-4-5-20250929 | global | $2.7 | $13.5 | 200K | |
| Cortecs | claude-4-5-sonnet | global | $2.99 | $14.95 | 200K | |
| Impossibl | anthropic/claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| NanoGPT | claude-sonnet-4-5-20250929 | global | $3 | $15 | 1M | |
| NEAR AI Cloud | anthropic/claude-sonnet-4-5 | global | $3 | $15.5 | 200K | |
| LLM Gateway | claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| LLM Gateway | claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| OpenCode Zen | claude-sonnet-4-5 | global | $3 | $15 | 1M | |
| GitHub Copilot | claude-sonnet-4.5 | global | $3 | $15 | 200K | |
| 302.AI | claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| 302.AI | claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| Helicone | claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| Neon | claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| Pioneer | claude-sonnet-4-5 | global | $3 | $15 | 1M | |
| ZenMux | anthropic/claude-sonnet-4.5 | global | $3 | $15 | 1M | |
| Abacus | claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| Azure Cognitive Services | claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| Azure | claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| Vertex (Anthropic) | claude-sonnet-4-5@20250929 | global | $3 | $15 | 200K | |
| OrcaRouter | anthropic/claude-sonnet-4.5 | global | $3 | $15 | 200K | |
| Vertex | claude-sonnet-4-5@20250929 | global | $3 | $15 | 200K | |
| Amazon Bedrock | anthropic.claude-sonnet-4-5-20250929-v1:0 | global | $3 | $15 | 200K | |
| Requesty | claude-sonnet-4-5 | global | $3 | $15 | 1M | |
| Kilo Gateway | anthropic/claude-sonnet-4.5 | global | $3 | $15 | 1M | |
| Merge Gateway | anthropic/claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| Vercel AI Gateway | anthropic/claude-sonnet-4.5 | global | $3 | $15 | 1M | |
| OpenRouter | anthropic/claude-sonnet-4.5 | global | $3 | $15 | 1M | |
| Anthropic | claude-sonnet-4-5 | global | $3 | $15 | 1M | |
| Anthropic | claude-sonnet-4-5-20250929 | global | $3 | $15 | 1M | |
| Cloudflare AI Gateway | anthropic/claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| Perplexity Agent | anthropic/claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| Databricks | databricks-claude-sonnet-4 | global | $3 | $15 | 200K | |
| Databricks | databricks-claude-sonnet-4-5 | global | $3 | $15 | 200K | |
| Venice AI | claude-sonnet-4-5 | global | $3.75 | $18.75 | 198K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Claude Sonnet 4.5 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Claude Sonnet 4.5 | 56.0 | N/A | 200K | 64K | No | Proprietary |
What is Claude Sonnet 4.5?
Key information about Claude Sonnet 4.5 and its available data.
5 is the best coding model in the world. It's the strongest model for building complex agents. It’s the best model at using computers. And it shows substantial gains in reasoning and math. Highest intelligence across most tasks with exceptional agent and coding capabilities.
Data as of 2026-08-11.
Claude Sonnet 4.5 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Claude Sonnet 4.5
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AN
Claude Opus 4.1
Anthropic
AN
Claude Opus 4
Anthropic
AN
Claude Haiku 4.5
Anthropic
AN
Claude Opus 4.5
Anthropic
AN
Claude Sonnet 4
Anthropic
AN
Claude Sonnet 4.6
Anthropic
FAQ
Common questions about Claude Sonnet 4.5.
When was Claude Sonnet 4.5 released?
Claude Sonnet 4.5's default version was released on Sep 29, 2025.
How much does Claude Sonnet 4.5 cost?
Claude Sonnet 4.5's official API price is $3 per million input tokens and $15 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $0.43 input and $2.14 output via QiHang.
Who created Claude Sonnet 4.5?
Claude Sonnet 4.5 was created by Anthropic.
What is the context window for Claude Sonnet 4.5?
The default version has a 200K token context window.
Is Claude Sonnet 4.5 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Claude Sonnet 4.5?
38 provider offerings are linked to the default version.
What models should I compare Claude Sonnet 4.5 with?
Nearby ranked alternatives include GLM 5V Turbo, Gemini 3.5 Flash Lite, Grok 4.