Claude Opus 4.6
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.
Beyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.
For users upgrading from earlier Opus versions, see our official migration guide here
- Organization
- Anthropic
- Family
- claude-opus
- Providers
- 40
- Context
- 1,000,000
- Output limit
- 128,000
- Knowledge
- 2025-05-31
- Release
- 2026-02-05
- Updated
- 2026-03-13
- Weights
- Closed
- Input
- text, image/jpeg, image/png, image/gif, image/webp, application/pdf
- Output
- text
- Capabilities
- —
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 |
|---|---|---|---|---|---|---|---|---|
| Abacus | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| AIHubMix | claude-opus-4-6-think | 1,000,000 | 128,000 | — / — | — | — | — | View |
| AIHubMix | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Amazon Bedrock | eu.anthropic.claude-opus-4-6-v1 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Amazon Bedrock | us.anthropic.claude-opus-4-6-v1 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Amazon Bedrock | au.anthropic.claude-opus-4-6-v1 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Amazon Bedrock | anthropic.claude-opus-4-6-v1 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Amazon Bedrock | global.anthropic.claude-opus-4-6-v1 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| AnyAPI | anthropic/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Auriko | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Cloudflare AI Gateway | anthropic/claude-opus-4.6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Cortecs | claude-opus4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Databricks | databricks-claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| DevPass (LLM Gateway) | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| DigitalOcean | anthropic-claude-opus-4.6 | 200,000 | 8,192 | — / — | — | — | — | View |
| Eden AI | anthropic/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| FreeModel | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| FrogBot | claude-opus-4-6 | 200,000 | 128,000 | — / — | — | — | — | View |
| GitLab Duo | duo-chat-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| GMI Cloud | anthropic/claude-opus-4.6 | 409,600 | 128,000 | — / — | — | — | — | View |
| Impossibl | anthropic/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Jiekou.AI | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Kilo Gateway | anthropic/claude-opus-4.6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| LLM Gateway | azure-anthropic/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| LLM Gateway | aws-bedrock/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| LLM Gateway | anthropic/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| LLM Gateway | vertex-anthropic/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Merge Gateway | anthropic/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| NanoGPT | anthropic/claude-opus-4.6:thinking:max | 1,000,000 | 128,000 | — / — | — | — | — | View |
| NanoGPT | anthropic/claude-opus-4.6:thinking:medium | 1,000,000 | 128,000 | — / — | — | — | — | View |
| NanoGPT | anthropic/claude-opus-4.6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| NanoGPT | anthropic/claude-opus-4.6:thinking:low | 1,000,000 | 128,000 | — / — | — | — | — | View |
| NanoGPT | anthropic/claude-opus-4.6:thinking | 1,000,000 | 128,000 | — / — | — | — | — | View |
| NEAR AI Cloud | anthropic/claude-opus-4-6 | 200,000 | 128,000 | — / — | — | — | — | View |
| Neon | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Ofox | anthropic/claude-opus-4.6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| OpenCode | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Amazon Bedrockvia OpenRouter | anthropic/claude-opus-4.6 unknown | 1,000,000 | 128,000 | $5.00 / $25.00 | Yes | Yes | Yes | View |
| Anthropicvia OpenRouter | anthropic/claude-opus-4.6 unknown | 1,000,000 | 128,000 | $5.00 / $25.00 | Yes | Yes | Yes | View |
| Azurevia OpenRouter | anthropic/claude-opus-4.6 unknown | 1,000,000 | 128,000 | $5.00 / $25.00 | Yes | Yes | Yes | View |
| Claude Platform on AWSvia OpenRouter | anthropic/claude-opus-4.6 unknown | 1,000,000 | 128,000 | $5.00 / $25.00 | Yes | Yes | Yes | View |
| Googlevia OpenRouter | anthropic/claude-opus-4.6 unknown | 1,000,000 | 128,000 | $5.00 / $25.00 | Yes | Yes | Yes | View |
| Googlevia OpenRouter | anthropic/claude-opus-4.6 unknown | 1,000,000 | 128,000 | $5.50 / $27.50 | Yes | Yes | Yes | View |
| Opper | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| OrcaRouter | anthropic/claude-opus-4.6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Perplexity Agent | anthropic/claude-opus-4-6 | 200,000 | 128,000 | — / — | — | — | — | View |
| Poe | anthropic/claude-opus-4.6 | 983,040 | 128,000 | — / — | — | — | — | View |
| Prime Inference | anthropic/claude-opus-4.6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Requesty | claude-opus-4-6@eu | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Requesty | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| SAP AI Core | anthropic--claude-4.6-opus | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Snowflake Cortex | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Tempr Gateway | anthropic/claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Venice AI | claude-opus-4-6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Vercel AI Gateway | anthropic/claude-opus-4.6 | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Vertex | claude-opus-4-6@default | 1,000,000 | 128,000 | — / — | — | — | — | View |
| Vertex (Anthropic) | claude-opus-4-6@default | 1,000,000 | 128,000 | — / — | — | — | — | View |
| ZenMux | anthropic/claude-opus-4.6 | 1,000,000 | 128,000 | — / — | — | — | — | 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-4.6Observed - Input
- $5.00
- Output
- $25.00
- Cache read
- $0.50
- Cache write
- $6.25
- Cache write · 1 hour
- $10.00
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 | $5.00 | $25.00 | $0.50 | $6.25 |
| Anthropicanthropic | $5.00 | $25.00 | $0.50 | $6.25 |
| Azureazure/global | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Platform on AWSclaude-on-aws | $5.00 | $25.00 | $0.50 | $6.25 |
| Googlegoogle-vertex/global | $5.00 | $25.00 | $0.50 | $6.25 |
| Googlegoogle-vertex/europe | $5.50 | $27.50 | $0.55 | $6.875 |
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 6 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Amazon Bedrockamazon-bedrock | 1,598 ms | 2,132 ms | 2,862.4 ms | 6,289.48 ms |
| Anthropicanthropic | 1,691 ms | 2,201.5 ms | 3,156 ms | 8,121.5 ms |
| Azureazure/global | 1,989.5 ms | 2,145.75 ms | 2,426.9 ms | 7,055.05 ms |
| Claude Platform on AWSclaude-on-aws | 1,517 ms | 1,778 ms | 2,373 ms | 16,852.5 ms |
| Googlegoogle-vertex/global | 1,781.5 ms | 2,188.25 ms | 8,237.1 ms | 10,929.48 ms |
| Googlegoogle-vertex/europe | 1,456 ms | 1,460 ms | 1,495.2 ms | 1,506.72 ms |
Output throughput · tokens per second
All throughput percentiles 6 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Amazon Bedrockamazon-bedrock | 39 t/s | 56 t/s | 66 t/s | 90 t/s |
| Anthropicanthropic | 36 t/s | 42.5 t/s | 60 t/s | 80 t/s |
| Azureazure/global | 60 t/s | 74 t/s | 79 t/s | 91.2 t/s |
| Claude Platform on AWSclaude-on-aws | 46 t/s | 57 t/s | 72 t/s | 93.88 t/s |
| Googlegoogle-vertex/global | 41 t/s | 48 t/s | 61 t/s | 96.43 t/s |
| Googlegoogle-vertex/europe | 73 t/s | 80 t/s | 84.2 t/s | 84.92 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-4.6Observed | Design Arena | Category | Elo | Win rate | Rank |
|---|---|---|---|---|
| agents | agenticgamedev | 1,213 | 50% | 8 |
| agents | androidnative | 1,215 | 63.8% | 12 |
| agents | fullstack | 1,220 | 59.9% | 13 |
| agents | mobileapps | 1,204 | 59.2% | 15 |
| agents | webapps | 1,199 | 57% | 18 |
| models | 3d | 1,280 | 62.5% | 18 |
| models | asciiart | 1,261 | 61.9% | 13 |
| models | codecategories | 1,293 | 61.2% | 14 |
| models | dataviz | 1,283 | 58.7% | 17 |
| models | gamedev | 1,285 | 61% | 20 |
| models | svg | 1,227 | 60.9% | 17 |
| models | uicomponent | 1,288 | 59.8% | 21 |
| models | website | 1,294 | 61.2% | 15 |
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 |
|---|---|---|---|---|
| models · dataviz | Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | Design Arena | 1,277 Elo | Details |
| gpqa diamond | Anthropic: Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | OpenRouter | 86.578% | Details |
| models · uicomponent | Claude Opus 4.6 (Thinking)anthropic/claude-4.6-opus-20260205 | Design Arena | 1,271 Elo | Details |
| models · codecategories | Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | Design Arena | 1,278 Elo | Details |
| models · website | Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | Design Arena | 1,283 Elo | Details |
| models · 3d | Claude Opus 4.6 (Thinking)anthropic/claude-4.6-opus-20260205 | Design Arena | 1,251 Elo | Details |
| models · uicomponent | Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | Design Arena | 1,274 Elo | Details |
| models · codecategories | Claude Opus 4.6 (Thinking)anthropic/claude-4.6-opus-20260205 | Design Arena | 1,275 Elo | Details |
| models · svg | Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | Design Arena | 1,204 Elo | Details |
| models · svg | Claude Opus 4.6 (Thinking)anthropic/claude-4.6-opus-20260205 | Design Arena | 1,217 Elo | Details |
| models · dataviz | Claude Opus 4.6 (Thinking)anthropic/claude-4.6-opus-20260205 | Design Arena | 1,267 Elo | Details |
| models · 3d | Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | Design Arena | 1,254 Elo | Details |
| tau bench verified airline | Anthropic: Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | OpenRouter | 74.133% | Details |
| models · asciiart | Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | Design Arena | 1,248 Elo | Details |
| models · website | Claude Opus 4.6 (Thinking)anthropic/claude-4.6-opus-20260205 | Design Arena | 1,278 Elo | Details |
| models · gamedev | Claude Opus 4.6 (Thinking)anthropic/claude-4.6-opus-20260205 | Design Arena | 1,267 Elo | Details |
| models · asciiart | Claude Opus 4.6 (Thinking)anthropic/claude-4.6-opus-20260205 | Design Arena | 1,250 Elo | Details |
| models · gamedev | Claude Opus 4.6anthropic/claude-4.6-opus-20260205 | Design Arena | 1,261 Elo | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Nov 14, 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 |
|---|---|---|---|---|
| Hermes Agent | anthropic/claude-4.6-opus-20260205 | 50+ turns | $4.96928 | Details |
| Claude Code | anthropic/claude-4.6-opus-20260205 | 2–9 turns | $0.284352 | Details |
| Claude Code | anthropic/claude-4.6-opus-20260205 | 10–49 turns | $1.331705 | Details |
| Claude Code | anthropic/claude-4.6-opus-20260205 | 50+ turns | $12.288338 | Details |
| Hermes Agent | anthropic/claude-4.6-opus-20260205 | 1 turn | $0.002541 | Details |
| Hermes Agent | anthropic/claude-4.6-opus-20260205 | 10–49 turns | $0.784901 | Details |
| Claude Code | anthropic/claude-4.6-opus-20260205 | 1 turn | $0.040443 | Details |
| Hermes Agent | anthropic/claude-4.6-opus-20260205 | 2–9 turns | $0.120526 | Details |
Source: OpenRouter, as of Nov 9, 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.
27,628,781,713 tokens
32,662,978,309 tokens
29,715,111,222 tokens
23,706,947,362 tokens
Daily observations · 4 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| Aug 26, 2026 | 23,706,947,362 | 1 |
| Aug 24, 2026 | 29,715,111,222 | 1 |
| Aug 18, 2026 | 32,662,978,309 | 1 |
| Aug 17, 2026 | 27,628,781,713 | 1 |
Source: OpenRouter (openrouter.ai/rankings), as of Nov 14, 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-4.6Observed - Context
- 1,000,000
- Maximum output
- 128,000
- Tokenizer
- Claude
- Input
- text, image, file
- Output
- text
- Moderation
- Yes
- Added to OpenRouter
- 2026-02-04
https://openrouter.ai/api/v1anthropic/claude-opus-4.6anthropic/claude-4.6-opus-20260205Reasoning
- Required
- No
- Enabled by default
- No
- Default effort
- high
- Supported efforts
- max, high, medium, low
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_pverbosity
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does Claude Opus 4.6 cost?
Listed rates start at $5.00 per million input tokens and $25.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer Claude Opus 4.6?
There are 58 cataloged offers across 40 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: Not reported. Structured output: Not reported. Support can vary by endpoint.
Catalog history · 3 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
4eca0509a8e3 - ·
6ccf6800f233 - ·
d22a5f7ce3c1