Claude Opus 5.5
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.
The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.
- Organization
- Anthropic
- Family
- claude-opus
- Providers
- 35
- Context
- 1,000,000
- Output limit
- 128,000
- Knowledge
- 2026-06
- Release
- 2026-09-22
- Updated
- 2026-09-22
- Weights
- Closed
- Input
- text, image, pdf
- Output
- text
- Capabilities
- Tools, Reasoning
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| 302.AI | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| AIHubMix | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| AI/ML API | anthropic/claude-opus-5.5 | 1,000,000 | 128,000 | $5.20 / $26.00 | Yes | Yes | — | View |
| Aixy | anthropic/claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Amazon Bedrock | au.anthropic.claude-opus-5-5 | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | — | View |
| Amazon Bedrock | anthropic.claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| Amazon Bedrock | us.anthropic.claude-opus-5-5 | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | — | View |
| Amazon Bedrock | eu.anthropic.claude-opus-5-5 | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | — | View |
| Amazon Bedrock | global.anthropic.claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| Amazon Bedrock | jp.anthropic.claude-opus-5-5 | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | — | View |
| Anthropic | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Azure | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Azure Cognitive Services | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Boundless | claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| Cloudflare AI Gateway | anthropic/claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| CommandCode | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| Cortecs | claude-opus-5.5 | 1,000,000 | 128,000 | $4.399 / $21.998 | Yes | Yes | Yes | View |
| CrossModel | anthropic/claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| DevPass (LLM Gateway) | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| DigitalOcean | anthropic-claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| Eden AI | anthropic/claude-opus-latest | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Eden AI | anthropic/claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| GitHub Copilot | claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| GitLab Duo | duo-chat-opus-5-5 | 1,000,000 | 128,000 | $0.00 / $0.00 | Yes | Yes | — | View |
| Kilo Gateway | anthropic/claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| LLM Gateway | anthropic/claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| LLM Gateway | azure-anthropic/claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| LLM Gateway | aws-bedrock/claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | No | View |
| Merge Gateway | anthropic/claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| NanoGPT | anthropic/claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| NEAR AI Cloud | anthropic/claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| Neon | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | No | View |
| Ofox | anthropic/claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| OpenCode | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| Amazon Bedrockvia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | No | View |
| Amazon Bedrockvia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | No | View |
| Amazon Bedrockvia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | No | View |
| Anthropicvia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $8.00 / $40.00 | Yes | Yes | Yes | View |
| Anthropicvia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Azurevia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | Yes | View |
| Azurevia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Claude Platform on AWSvia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Googlevia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | Yes | View |
| Googlevia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Googlevia OpenRouter | anthropic/claude-opus-5.5 unknown | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | Yes | View |
| Prime Inference | anthropic/claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Requesty | claude-opus-5-5@eu | 1,000,000 | 128,000 | $4.40 / $22.00 | Yes | Yes | Yes | View |
| Requesty | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Venice AI | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Venice AI | claude-opus-5-5-fast | 1,000,000 | 128,000 | $8.00 / $40.00 | Yes | Yes | Yes | View |
| Vercel AI Gateway | anthropic/claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
| Vercel AI Gateway | anthropic/claude-opus-5.5-fast | 1,000,000 | 128,000 | $8.00 / $40.00 | Yes | Yes | — | View |
| Vertex | claude-opus-5-5@default | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Vertex (Anthropic) | claude-opus-5-5@default | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| Vivgrid | claude-opus-5-5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | Yes | View |
| ZenMux | anthropic/claude-opus-5.5 | 1,000,000 | 128,000 | $4.00 / $20.00 | Yes | Yes | — | View |
Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.
Pricing
Compare token rates and cache charges across available routes and hosting configurations.
Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.
anthropic/claude-opus-5.5Observed - Input
- $4.00
- Output
- $20.00
- Cache read
- $0.20
- Cache write
- $5.00
- Cache write · 1 hour
- $8.00
Additional fees and pricing conditions
- web search
- $0.01 / search
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Amazon Bedrockamazon-bedrock/us-east-1 | $4.40 | $22.00 | $0.22 | $5.50 |
| Amazon Bedrockamazon-bedrock/eu-west-1 | $4.40 | $22.00 | $0.22 | $5.50 |
| Amazon Bedrockamazon-bedrock | $4.00 | $20.00 | $0.20 | $5.00 |
| Anthropicanthropic/fast | $8.00 | $40.00 | $0.40 | $10.00 |
| Anthropicanthropic | $4.00 | $20.00 | $0.20 | $5.00 |
| Azureazure/us | $4.40 | $22.00 | $0.22 | $5.50 |
| Azureazure/global | $4.00 | $20.00 | $0.20 | $5.00 |
| Claude Platform on AWSclaude-on-aws | $4.00 | $20.00 | $0.20 | $5.00 |
| Googlegoogle-vertex/us | $4.40 | $22.00 | $0.22 | $5.50 |
| Googlegoogle-vertex/global | $4.00 | $20.00 | $0.20 | $5.00 |
| Googlegoogle-vertex/europe | $4.40 | $22.00 | $0.22 | $5.50 |
Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.
Performance
Review reported latency and output-throughput percentiles from the latest observed rolling window.
Time to first token · milliseconds
All latency percentiles 11 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Amazon Bedrockamazon-bedrock/us-east-1 | 10,902 ms | 19,828.5 ms | 37,030.4 ms | 65,784.97 ms |
| Amazon Bedrockamazon-bedrock/eu-west-1 | 2,954.5 ms | 4,036.75 ms | 5,005.7 ms | 10,133.84 ms |
| Amazon Bedrockamazon-bedrock | 14,707 ms | 25,484.5 ms | 39,684.4 ms | 77,108.67 ms |
| Anthropicanthropic/fast | 2,059 ms | 2,995 ms | 3,748.6 ms | 16,534.34 ms |
| Anthropicanthropic | 3,321.5 ms | 4,579.5 ms | 6,300.7 ms | 17,029.19 ms |
| Azureazure/us | 1,783 ms | 2,519 ms | 3,109.8 ms | 4,610.28 ms |
| Azureazure/global | 2,094 ms | 2,825 ms | 3,364.8 ms | 4,812.6 ms |
| Claude Platform on AWSclaude-on-aws | 4,486.5 ms | 5,302 ms | 6,571.8 ms | 15,594.16 ms |
| Googlegoogle-vertex/us | 1,744.5 ms | 2,483.5 ms | 3,095.8 ms | 4,683.53 ms |
| Googlegoogle-vertex/global | 3,276 ms | 5,312.25 ms | 13,695.6 ms | 27,593.04 ms |
| Googlegoogle-vertex/europe | 1,852.5 ms | 2,567.25 ms | 3,184 ms | 4,352.75 ms |
Output throughput · tokens per second
All throughput percentiles 11 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Amazon Bedrockamazon-bedrock/us-east-1 | 18 t/s | 34 t/s | 51 t/s | 81.72 t/s |
| Amazon Bedrockamazon-bedrock/eu-west-1 | 58 t/s | 71 t/s | 82 t/s | 105.89 t/s |
| Amazon Bedrockamazon-bedrock | 27 t/s | 46 t/s | 64 t/s | 89 t/s |
| Anthropicanthropic/fast | 133 t/s | 219.5 t/s | 291 t/s | 355.48 t/s |
| Anthropicanthropic | 73 t/s | 92 t/s | 108 t/s | 139 t/s |
| Azureazure/us | 85 t/s | 99 t/s | 114 t/s | 138.48 t/s |
| Azureazure/global | 88 t/s | 101 t/s | 112 t/s | 138 t/s |
| Claude Platform on AWSclaude-on-aws | 71 t/s | 90 t/s | 103 t/s | 126 t/s |
| Googlegoogle-vertex/us | 91 t/s | 103 t/s | 115 t/s | 135.42 t/s |
| Googlegoogle-vertex/global | 84 t/s | 101 t/s | 113 t/s | 137 t/s |
| Googlegoogle-vertex/europe | 88 t/s | 100 t/s | 110 t/s | 130.74 t/s |
Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.
Uptime
Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.
Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.
Benchmarks
Review attributed evaluation results on each source's original scale.
anthropic/claude-opus-5.5Observed | Design Arena | Category | Elo | Win rate | Rank |
|---|---|---|---|---|
| agents | mobileapps | 1,328 | 64.3% | 2 |
| models | 3d | 1,483 | 72% | 1 |
| models | codecategories | 1,406 | 65.3% | 1 |
| models | dataviz | 1,403 | 64.7% | 1 |
| models | gamedev | 1,465 | 72.8% | 1 |
| models | svg | 1,331 | 50.3% | 1 |
| models | uicomponent | 1,396 | 65.4% | 1 |
| models | website | 1,339 | 57.6% | 3 |
Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| gpqa diamond | Anthropic: Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | OpenRouter | 90.446% | Details |
| Composite indices | Claude Opus 5.5 (Max, Default Fallback)anthropic/claude-opus-5.5-20260921 | Artificial Analysis | Intelligence 57.6 · Coding — · Agentic — | Details |
| models · uicomponent | Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | Design Arena | 1,380 Elo | Details |
| models · website | Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | Design Arena | 1,336 Elo | Details |
| models · svg | Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | Design Arena | 1,332 Elo | Details |
| models · gamedev | Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | Design Arena | 1,463 Elo | Details |
| tau bench verified airline | Anthropic: Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | OpenRouter | 75.5% | Details |
| models · codecategories | Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | Design Arena | 1,391 Elo | Details |
| models · 3d | Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | Design Arena | 1,478 Elo | Details |
| models · dataviz | Claude Opus 5.5anthropic/claude-opus-5.5-20260921 | Design Arena | 1,399 Elo | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 17, 2026.
Apps & session costs
Compare observed median session costs for applications using this model, grouped by conversation length.
| Application | Model route | Turns | Median cost / session | Details |
|---|---|---|---|---|
| Claude Code | anthropic/claude-opus-5.5-20260921 | 1 turn | $0.134167 | Details |
| Claude Code | anthropic/claude-opus-5.5-20260921 | 10–49 turns | $1.383299 | Details |
| Hermes Agent | anthropic/claude-opus-5.5-20260921 | 1 turn | $0.020732 | Details |
| Hermes Agent | anthropic/claude-opus-5.5-20260921 | 2–9 turns | $0.201541 | Details |
| Hermes Agent | anthropic/claude-opus-5.5-20260921 | 50+ turns | $8.689499 | Details |
| Claude Code | anthropic/claude-opus-5.5-20260921 | 2–9 turns | $0.304359 | Details |
| Hermes Agent | anthropic/claude-opus-5.5-20260921 | 10–49 turns | $1.321082 | Details |
| Claude Code | anthropic/claude-opus-5.5-20260921 | 50+ turns | $8.943665 | Details |
| Codex | anthropic/claude-opus-5.5-20260921 | 1 turn | $0.056924 | Details |
| Kilo Code | anthropic/claude-opus-5.5-20260921 | 50+ turns | $7.945149 | Details |
| Kilo Code | anthropic/claude-opus-5.5-20260921 | 10–49 turns | $1.612654 | Details |
| Codex | anthropic/claude-opus-5.5-20260921 | 2–9 turns | $0.558664 | Details |
| Kilo Code | anthropic/claude-opus-5.5-20260921 | 2–9 turns | $0.385898 | Details |
Source: OpenRouter, as of Oct 12, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.
Activity
Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.
194,213,435,310 tokens
224,960,655,519 tokens
242,184,315,698 tokens
187,657,725,049 tokens
204,661,336,620 tokens
321,735,526,822 tokens
312,346,533,110 tokens
439,601,687,630 tokens
358,562,668,902 tokens
344,560,596,736 tokens
332,532,867,669 tokens
353,658,217,039 tokens
457,654,386,250 tokens
640,063,496,672 tokens
883,020,526,231 tokens
818,315,141,426 tokens
830,267,538,712 tokens
699,435,464,442 tokens
689,978,363,698 tokens
788,542,034,297 tokens
931,821,267,503 tokens
887,438,539,653 tokens
1,020,025,645,998 tokens
933,379,863,866 tokens
Daily observations · 24 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| Oct 16, 2026 | 933,379,863,866 | 1 |
| Oct 15, 2026 | 1,020,025,645,998 | 1 |
| Oct 14, 2026 | 887,438,539,653 | 1 |
| Oct 13, 2026 | 931,821,267,503 | 1 |
| Oct 12, 2026 | 788,542,034,297 | 1 |
| Oct 11, 2026 | 689,978,363,698 | 1 |
| Oct 10, 2026 | 699,435,464,442 | 1 |
| Oct 9, 2026 | 830,267,538,712 | 1 |
| Oct 8, 2026 | 818,315,141,426 | 1 |
| Oct 7, 2026 | 883,020,526,231 | 1 |
| Oct 6, 2026 | 640,063,496,672 | 1 |
| Oct 5, 2026 | 457,654,386,250 | 1 |
| Oct 4, 2026 | 353,658,217,039 | 1 |
| Oct 3, 2026 | 332,532,867,669 | 1 |
| Oct 2, 2026 | 344,560,596,736 | 1 |
| Oct 1, 2026 | 358,562,668,902 | 1 |
| Sep 30, 2026 | 439,601,687,630 | 1 |
| Sep 29, 2026 | 312,346,533,110 | 1 |
| Sep 28, 2026 | 321,735,526,822 | 1 |
| Sep 27, 2026 | 204,661,336,620 | 1 |
| Sep 26, 2026 | 187,657,725,049 | 1 |
| Sep 25, 2026 | 242,184,315,698 | 1 |
| Sep 24, 2026 | 224,960,655,519 | 1 |
| Sep 23, 2026 | 194,213,435,310 | 1 |
Source: OpenRouter (openrouter.ai/rankings), as of Oct 17, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.
Technical details & API
Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.
anthropic/claude-opus-5.5Observed - Context
- 1,000,000
- Maximum output
- 128,000
- Tokenizer
- Claude
- Input
- text, image, file
- Output
- text
- Moderation
- Yes
- Added to OpenRouter
- 2026-09-22
https://openrouter.ai/api/v1anthropic/claude-opus-5.5anthropic/claude-opus-5.5-20260921Reasoning
- Required
- Yes
- Enabled by default
- Not reported
- Default effort
- high
- Supported efforts
- max, xhigh, high, medium, low
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does Claude Opus 5.5 cost?
Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer Claude Opus 5.5?
There are 56 cataloged offers across 35 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 1,000,000 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.
Catalog history · 1 recorded revision
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
4317c0a98435