Claude Sonnet 4.5 20250929
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking. Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.
- Input / output price
- $3.00 / $15.00 per 1M
- Context
- 200K tokens
- Released
- Sep 29, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
3 routes from 2 providers, cheapest first, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
AnthropicRetiring anthropic/claude-sonnet-4.5-20250929 | $3.00/M | $15.00/M |
Bedrock bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0 | $3.00/M | $15.00/M |
Bedrock bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0 | $3.30/M | $16.50/M |
Is a provider down? Claude status, AWS Bedrock status
Pricing
Averaged across 3 routes from 2 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $3.10 per 1M
- Average output
- $15.50 per 1M
- Average cache read
- $0.31 per 1M
- Average cache write
- $3.88 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better45tokens/sacross providers
Time to first token
Lower is better1.2sacross providers
Response latency
Lower is better6.1sacross providers
Benchmarks
The Respan Index plus 37 published scores from 11 sources, each linked to where it was published.
31.3/ 100
Respan Index#86 of 176
- 86Claude Sonnet 4.531.3
- 85Inkling31.9
- 87MiniMax M331.2
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench VerifiedAnthropic | 77.2% | Anthropic | Feb 17, 2026 |
| SWE-bench VerifiedEpoch AI | 71.3% | Epoch AI | Oct 5, 2026 |
| Terminal-Bench 2.0Anthropic | 51% | Anthropic | Feb 17, 2026 |
| WeirdMLHåvard Tveit Ihle | 47.7% | Håvard Tveit Ihle | Oct 5, 2026 |
| GSO Opt@1GSO | 12.7% | GSO | Oct 10, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Tau2-bench TelecomAnthropic | 98% | Anthropic | Feb 17, 2026 |
| Tau2-bench RetailAnthropic | 86.2% | Anthropic | Feb 17, 2026 |
| tau2-bench TelecomSierra | 84.9% | Sierra | Feb 26, 2026 |
| tau2-bench RetailSierra | 72.4% | Sierra | Feb 26, 2026 |
| tau2-bench AirlineSierra | 72% | Sierra | Feb 26, 2026 |
| OSWorld-VerifiedXLANG | 62.9% | XLANG | Oct 31, 2025 |
| OSWorld-VerifiedAnthropic | 61.4% | Anthropic | Feb 17, 2026 |
| MCP AtlasAnthropic | 43.8% | Anthropic | Feb 17, 2026 |
| tau2-bench Banking KnowledgeSierra | 25.3% | Sierra | Feb 26, 2026 |
| Vending-Bench 2Andon Labs | 3838.74 · #44 of 68 | Andon Labs | Oct 5, 2026 |
| GDPval-AAAnthropic | 1276 Elo | Anthropic | Feb 17, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondAnthropic | 83.4% | Anthropic | Feb 17, 2026 |
| GPQA DiamondEpoch AI | 82.3% | Epoch AI | Oct 5, 2026 |
| SimpleBenchSimpleBench | 54.3% | SimpleBench | Oct 5, 2026 |
| Humanity's Last Exam (with tools)Anthropic | 33.6% | Anthropic | Feb 17, 2026 |
| Humanity's Last Exam (no tools)Anthropic | 17.7% | Anthropic | Feb 17, 2026 |
| Mystery Game PuzzlesEpoch AI | 17% | Epoch AI | Oct 5, 2026 |
| ARC-AGI-2 (Verified)Anthropic | 13.6% | Anthropic | Feb 17, 2026 |
| Chess PuzzlesEpoch AI | 10% | Epoch AI | Oct 28, 2026 |
| EBR-benchEpoch AI | 2.4% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH Level 5Epoch AI | 97.7% | Epoch AI | Oct 5, 2026 |
| AIME 2025MathArena | 84.2% | MathArena | Sep 17, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 77.8% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 23.9% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 2.4% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMMLUAnthropic | 89.5% | Anthropic | Feb 17, 2026 |
| SimpleQA VerifiedEpoch AI | 30.7% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMMU-Pro (with tools)Anthropic | 68.9% | Anthropic | Feb 17, 2026 |
| MMMU-Pro (no tools)Anthropic | 63.4% | Anthropic | Feb 17, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1456 Elo · #58 of 191 | LMArena | Nov 19, 2026 |
| LMArena WebDevLMArena | 1394 Elo · #93 of 124 | LMArena | Nov 20, 2026 |
How Claude compares: Claude vs Gemini, Claude vs Grok, Claude vs GPT
Compare Claude Sonnet 4.5 20250929: Claude Sonnet 4.5 vs Claude Sonnet 4, Claude Sonnet 4.5 vs Claude Sonnet 4.6, Claude Sonnet 4.5 vs GLM-5, Claude Sonnet 4.5 vs Claude Fable 5.2, Claude Sonnet 4.5 vs Claude Opus 5.5, Claude Sonnet 4.5 vs Claude Sonnet 5.5
Apps
Use Claude Sonnet 4.5 20250929 in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Claude Sonnet 4.5 20250929 FAQ
Short answers, built from the data on this page.
Claude Sonnet 4.5 20250929 is a model from Anthropic, released on Sep 29, 2025. Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking. Sonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.
On the Respan gateway, Claude Sonnet 4.5 20250929 costs from $3.00 per 1M input tokens and $15.00 per 1M output tokens on Anthropic and Bedrock, after gateway discounts. Averaged across its 3 routes from 2 providers, it costs $3.10 per 1M input tokens and $15.50 per 1M output tokens.
Claude Sonnet 4.5 20250929 is available through 3 routes from 2 providers: Anthropic and Bedrock.
Claude Sonnet 4.5 20250929 accepts up to 200K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "anthropic/claude-sonnet-4.5-20250929". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Claude Sonnet 4.5 20250929 scores 31.3 out of 100 on the Respan Index v1.1, ranking #86 of 176 models. By category: Coding 13.1, Agents 41.7, Reasoning 27.5, Knowledge & language 31.2, and Human preference 50.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Claude Sonnet 4.5 20250929 has 37 published benchmark scores, including SWE-bench Verified 77.2%, Tau2-bench Telecom 98%, and GPQA Diamond 83.4%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.