Claude Opus 4.7

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.

Beyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.

For users upgrading from earlier Opus versions, see our official migration guide here

anthropic/claude-opus-4-7
Organization
Anthropic
Providers
47
Context
1,000,000
Output limit
128,000
Knowledge
2026-01-31
Release
2026-04-16
Updated
—
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.

66 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
302.AI
claude-opus-4-7
1,000,000128,000— / ————
View
302.AI
claude-opus-4-7-thinking
1,000,000128,000— / ————
View
Abacus
claude-opus-4-7
1,000,000128,000— / ————
View
AIHubMix
claude-opus-4-7
1,000,000128,000— / ————
View
AIHubMix
claude-opus-4-7-think
1,000,000128,000— / ————
View
AI/ML API
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
Amazon Bedrock
jp.anthropic.claude-opus-4-7
1,000,000128,000— / ————
View
Amazon Bedrock
global.anthropic.claude-opus-4-7
1,000,000128,000— / ————
View
Amazon Bedrock
eu.anthropic.claude-opus-4-7
1,000,000128,000— / ————
View
Amazon Bedrock
us.anthropic.claude-opus-4-7
1,000,000128,000— / ————
View
Amazon Bedrock
au.anthropic.claude-opus-4-7
1,000,000128,000— / ————
View
Amazon Bedrock
anthropic.claude-opus-4-7
1,000,000128,000— / ————
View
AnyAPI
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
Auriko
claude-opus-4-7
1,000,000128,000— / ————
View
Azure
claude-opus-4-7
1,000,000128,000— / ————
View
Cloudflare AI Gateway
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
CommandCode
claude-opus-4-7
1,000,000128,000— / ————
View
Cortecs
claude-opus4-7
1,000,000128,000— / ————
View
CrossModel
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
Databricks
databricks-claude-opus-4-7
1,000,000128,000— / ————
View
DevPass (LLM Gateway)
claude-opus-4-7
1,000,000128,000— / ————
View
DigitalOcean
anthropic-claude-opus-4.7
200,0008,192— / ————
View
Eden AI
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
FreeModel
claude-opus-4-7
1,000,000128,000— / ————
View
FrogBot
claude-opus-4-7
200,000128,000— / ————
View
GitHub Copilot
claude-opus-4.7
200,00032,000— / ————
View
GitLab Duo
duo-chat-opus-4-7
1,000,000128,000— / ————
View
GMI Cloud
anthropic/claude-opus-4.7
409,600128,000— / ————
View
HPC-AI
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
Impossibl
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
Kenari
claude-opus-4-7
1,000,000128,000— / ————
View
Kilo Gateway
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
LLM Gateway
azure-anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
LLM Gateway
aws-bedrock/claude-opus-4-7
1,000,000128,000— / ————
View
LLM Gateway
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
LLM Gateway
vertex-anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
Merge Gateway
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
NanoGPT
anthropic/claude-opus-4.7:thinking
1,000,000128,000— / ————
View
NanoGPT
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
NEAR AI Cloud
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
Neon
claude-opus-4-7
1,000,000128,000— / ————
View
Ofox
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
OpenCode
claude-opus-4-7
1,000,000128,000— / ————
View
Amazon Bedrockvia OpenRouter
anthropic/claude-opus-4.7
unknown
1,000,000128,000$5.50 / $27.50YesYesNo
View
Amazon Bedrockvia OpenRouter
anthropic/claude-opus-4.7
unknown
1,000,000128,000$5.00 / $25.00YesYesNo
View
Anthropicvia OpenRouter
anthropic/claude-opus-4.7
unknown
1,000,000128,000$5.00 / $25.00YesYesYes
View
Azurevia OpenRouter
anthropic/claude-opus-4.7
unknown
1,000,000128,000$5.00 / $25.00YesYesYes
View
Claude Platform on AWSvia OpenRouter
anthropic/claude-opus-4.7
unknown
1,000,000128,000$5.00 / $25.00YesYesYes
View
Googlevia OpenRouter
anthropic/claude-opus-4.7
unknown
1,000,000128,000$5.00 / $25.00YesYesYes
View
Googlevia OpenRouter
anthropic/claude-opus-4.7
unknown
1,000,000128,000$5.50 / $27.50YesYesYes
View
Googlevia OpenRouter
anthropic/claude-opus-4.7
unknown
1,000,000128,000$5.50 / $27.50YesYesYes
View
Opper
claude-opus-4-7
1,000,00064,000— / ————
View
OrcaRouter
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
Perplexity Agent
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
Poe
anthropic/claude-opus-4.7
1,048,576128,000— / ————
View
Prime Inference
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
Requesty
claude-opus-4-7@eu
1,000,000128,000— / ————
View
Requesty
claude-opus-4-7
1,000,000128,000— / ————
View
SAP AI Core
anthropic--claude-4.7-opus
1,000,000128,000— / ————
View
Snowflake Cortex
claude-opus-4-7
1,000,000128,000— / ————
View
Tempr Gateway
anthropic/claude-opus-4-7
1,000,000128,000— / ————
View
Venice AI
claude-opus-4-7
1,000,000128,000— / ————
View
Vercel AI Gateway
anthropic/claude-opus-4.7
1,000,000128,000— / ————
View
Vertex
claude-opus-4-7@default
1,000,000128,000— / ————
View
Vertex (Anthropic)
claude-opus-4-7@default
1,000,000128,000— / ————
View
ZenMux
anthropic/claude-opus-4.7
1,000,000128,000— / ————
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.

USD per million tokens
Input from$5.00Per 1M input tokens
Output from$25.00Per 1M output tokens
Available offers66Across 47 providers

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.

Endpoint price comparisonLatest observed snapshot · 8 lowest-priced configurations
InputOutput
Amazon Bedrockamazon-bedrock/global
$5.00$25.00
Anthropicanthropic
$5.00$25.00
Azureazure/global
$5.00$25.00
Claude Platform on AWSclaude-on-aws
$5.00$25.00
Googlegoogle-vertex/global
$5.00$25.00
Amazon Bedrockamazon-bedrock/eu-west-1
$5.50$27.50
Googlegoogle-vertex/us
$5.50$27.50
Googlegoogle-vertex/europe
$5.50$27.50
anthropic/claude-opus-4.7Observed
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
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Amazon Bedrockamazon-bedrock/eu-west-1$5.50$27.50$0.55$6.875
Amazon Bedrockamazon-bedrock/global$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/us$5.50$27.50$0.55$6.875
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.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/eu-west-1
2,987–4,154.74 ms
Amazon Bedrockamazon-bedrock/global
1,181–4,295.08 ms
Anthropicanthropic
769–6,701.12 ms
Azureazure/global
1,289–6,397 ms
Claude Platform on AWSclaude-on-aws
1,757–12,279.2 ms
Googlegoogle-vertex/global
1,944.5–6,737.85 ms
All latency percentiles 7 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/eu-west-12,987 ms3,389.5 ms3,788.5 ms4,154.74 ms
Amazon Bedrockamazon-bedrock/global1,181 ms1,881 ms2,731.4 ms4,295.08 ms
Anthropicanthropic769 ms2,029 ms3,344.4 ms6,701.12 ms
Azureazure/global1,289 ms2,568 ms3,794 ms6,397 ms
Claude Platform on AWSclaude-on-aws1,757 ms4,013.25 ms5,129 ms12,279.2 ms
Googlegoogle-vertex/global1,944.5 ms6,281.25 ms6,459 ms6,737.85 ms
Googlegoogle-vertex/us514 ms1,630.75 ms2,465.3 ms3,612.78 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints
P50P75P90P99
Amazon Bedrockamazon-bedrock/eu-west-1
104–128.52 t/s
Amazon Bedrockamazon-bedrock/global
61–132 t/s
Anthropicanthropic
63–110.05 t/s
Azureazure/global
53–101.18 t/s
Claude Platform on AWSclaude-on-aws
47–101 t/s
Googlegoogle-vertex/global
77–131 t/s
All throughput percentiles 7 endpoints
EndpointP50P75P90P99
Amazon Bedrockamazon-bedrock/eu-west-1104 t/s112 t/s118.4 t/s128.52 t/s
Amazon Bedrockamazon-bedrock/global61 t/s68 t/s94 t/s132 t/s
Anthropicanthropic63 t/s77.25 t/s94 t/s110.05 t/s
Azureazure/global53 t/s73 t/s85 t/s101.18 t/s
Claude Platform on AWSclaude-on-aws47 t/s59 t/s77 t/s101 t/s
Googlegoogle-vertex/global77 t/s93 t/s111 t/s131 t/s
Googlegoogle-vertex/us90 t/s109.5 t/s129 t/s147 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.

Successful requests by window
Availability by endpointCurrent overlapping windows · 8 endpoints
Endpoint5 minutes30 minutes24 hours
Amazon Bedrockamazon-bedrock/eu-west-1
Amazon Bedrockamazon-bedrock/global
Anthropicanthropic
Azureazure/global
Claude Platform on AWSclaude-on-aws
Googlegoogle-vertex/global
Googlegoogle-vertex/us
Googlegoogle-vertex/europe

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.

External evaluations
anthropic/claude-opus-4.7Observed
Benchmark profileArtificial Analysis · shared source scale from 0 to 80
Coding73.6
Agentic38.6
Intelligence40.7

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
tau bench verified airlineAnthropic: Claude Opus 4.7
76.606%
gpqa diamondAnthropic: Claude Opus 4.7
89.507%
EvaluationConfigurationSourceResultsDetails
tau bench verified airlineAnthropic: Claude Opus 4.7anthropic/claude-4.7-opus-20260416OpenRouter76.606%
Details
gpqa diamondAnthropic: Claude Opus 4.7anthropic/claude-4.7-opus-20260416OpenRouter89.507%
Details
Composite indicesClaude Opus 4.7 (Max)anthropic/claude-4.7-opus-20260416Artificial AnalysisIntelligence 40.7 · Coding 73.6 · Agentic 38.6
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Oct 18, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Claude Codeanthropic/claude-4.7-opus-202604162–9 turns
$0.47649
Details
Claude Codeanthropic/claude-4.7-opus-2026041610–49 turns
$1.417518
Details

Source: OpenRouter, as of Oct 20, 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.

Last 90 complete UTC days
Daily token usage1,426,704,106,260 reported tokens · 26 days with observations
Jul 26, 2026Oct 23, 2026
Daily observations · 26 days
Date (UTC)Reported tokensReported routes
Sep 11, 202655,327,728,3731
Aug 26, 202644,942,507,6431
Aug 21, 202648,434,935,1421
Aug 20, 202693,692,867,0201
Aug 19, 202633,458,481,4271
Aug 18, 2026110,781,771,5171
Aug 17, 2026102,323,346,0861
Aug 16, 202625,070,616,3721
Aug 15, 2026125,909,470,9031
Aug 14, 2026141,107,627,6541
Aug 13, 202647,715,197,4961
Aug 12, 202637,532,460,2021
Aug 11, 202643,931,720,5921
Aug 10, 202637,609,959,3671
Aug 9, 202630,848,765,2791
Aug 8, 202648,449,954,1801
Aug 7, 202664,660,735,9611
Aug 6, 202648,721,863,5821
Aug 5, 202656,336,622,0361
Aug 4, 202627,782,966,3591
Aug 3, 202622,006,700,0521
Jul 31, 202628,130,577,9031
Jul 30, 202658,345,486,2141
Jul 29, 202629,111,643,9951
Jul 28, 202639,221,292,3111
Jul 27, 202625,248,808,5941

Source: OpenRouter (openrouter.ai/rankings), as of Oct 24, 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.

Current route specifications
anthropic/claude-opus-4.7Observed
Context
1,000,000
Maximum output
128,000
Tokenizer
Claude
Input
text, image, file
Output
text
Moderation
Yes
Added to OpenRouter
2026-04-16
Base URLhttps://openrouter.ai/api/v1
Model IDanthropic/claude-opus-4.7
Version IDanthropic/claude-4.7-opus-20260416

Reasoning

Required
No
Enabled by default
No
Default effort
high
Supported efforts
max, xhigh, high, medium, low

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • stop
  • structured_outputs
  • tool_choice
  • tools
  • verbosity

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Claude Opus 4.7 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 4.7?

There are 66 cataloged offers across 47 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.

  • · 7d77eb432446
  • · f35a9ee70d89
  • · 3a869d9b7964