Anthropic · Chat
Claude Opus 5
Newer version: Claude Opus 5.5. We compared release dates and version names in our catalogue.
Claude Opus 5 is the most capable Opus-tier model from Anthropic, built for complex agentic coding and enterprise work. It delivers frontier reasoning and long-horizon autonomy, with a 1M token context window, up to 128K output tokens, adaptive thinking with selectable reasoning effort, multimodal input, native tool use, and prompt caching.
- llminfo IQ
- 143.9
- Maker's price
- $10.00 blended / 1M
- Max context
- 1M
- Listings
- 114
Evidence and sources
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Advantages
Trade-offs
Costs more than most peers
Maker's price: $10.00 blended / 1M, pricier than 8 of 9 priced peers.
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersCapabilities
Supported operations and provider-stated features
Listings
| 1M | $5.00cache read $0.50batch $2.50 | $25.00cache write 5m $6.25cache write 1h $10.00batch $12.50 | |
| 1M | $1.17cache read $0.1168 | $5.84cache write $1.46 | |
| 1M | $1.75 | $8.75 | |
| 1M | $1.923cache read $0.1923 | $9.615cache write $2.404 | |
| 1M | $2.50cache read $0.25 | $12.50cache write $3.125 | |
| 1M | $2.50cache read $0.25 | $12.50cache write 5m $3.125cache write 1h $5.00 | |
| 1M | $2.50cache read $0.25 | $12.50 | |
| 1M | $3.00cache read $0.30 | $15.00cache write $3.75 | |
| 1M | $3.25cache read $0.325 | $16.25cache write $4.06 | |
| 1M | $3.50cache read $0.35 | $17.50cache write $4.375 |
Showing 10 of 101: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by 302ai, Abacus, Aihubmix, Aimlapi, Amazon Web Services, Atlascloud, Boundless, Cloudflare AI Gateway, Cometapi, Commandcode, Cortecs AI, Crossmodel, Databricks, DeepInfra, Digitalocean, Eden AI, Eurouter, Evolink, Fastrouter, Frogbot, Github Copilot, Google, Hostinger Router, Hubris, Kenari, Kilo, Llmgateway, Llmgateway Providers, Lowrouter, Meganova, Merge Gateway, Microsoft Azure, NanoGPT, Near AI, Neon, Netmind, Ofox, Opper, Orcarouter, Perplexity, Perplexity Agent, Pioneer, Prime, Requesty, Snowflake, Snowflake Cortex, Standardcompute, Synthorai, Venice, Vivgrid, Wavespeed, Writer, Zenmux.
13 listings without a price are hidden.
Benchmarks
Named effort levels run from lowest to highest. Select a result to see its source details.
Agentic
| Benchmark | High | Max |
|---|---|---|
| Arena Agent | —Not measured | |
| Bash Recovery Steps | ||
| Bash Reliability | —Not measured | |
| Praise Complaint | —Not measured |
Show 3 more benchmarksHide 3 benchmarks
| Benchmark | High | Max |
|---|---|---|
| Steerability | —Not measured | |
| Task Outcome Explicit | —Not measured | |
| Tool Hallucination | —Not measured |
Show 11 more resultsHide 11 results
Show 1 more resultHide 1 result
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
- OpenRouter's automatic routing
- Amazon Bedrock
- Azure
- Claude Platform on AWS
- Anthropic
| Benchmark | Score |
|---|---|
| Tax Agent Bench | |
| Finance Agent (v2) | |
| Harvey's Legal Agent Benchmark v1 | |
| Terminal-Bench 2.1 |
Show 2 more benchmarksHide 2 benchmarks
| Benchmark | Score |
|---|---|
| Terminal-Bench 4.0 | |
| Terminal-Bench-Science |
Human preference
| Benchmark | High | Max |
|---|---|---|
| Arena ELO | ||
| Chinese | ||
| Creative Writing | ||
| Document | —Not measured |
Show 62 more benchmarksHide 62 benchmarks
Reasoning
Show 3 more resultsHide 3 results
Show 9 more resultsHide 9 results
Show 9 more resultsHide 9 results
Show 9 more resultsHide 9 results
Coding
| Benchmark | High | Max |
|---|---|---|
| Coding | ||
| Text Factuality - Coding | ||
| Webdev | ||
| Webdev - Image to Webdev | —Not measured |
Show 3 more benchmarksHide 3 benchmarks
| Benchmark | High | Max |
|---|---|---|
| Webdev - Webdev | ||
| Webdev - Webdev Html | ||
| Webdev - Webdev React |
Multilingual
Show 34 more resultsHide 34 results
General
Science
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
- Azure
- Anthropic
- Amazon Bedrock
- Claude Platform on AWS
- OpenRouter's automatic routing
Math
Vision
Long context
Instruction following
Knowledge
Factuality
OCR
Safety
Speech
Other
Show 2 more resultsHide 2 results
Show 9 more resultsHide 9 results
Show 2 more resultsHide 2 results
Show 16 more resultsHide 16 results
Show 22 more resultsHide 22 results
Show 20 more resultsHide 20 results
Show 2 more resultsHide 2 results
Show 9 more resultsHide 9 results
Show 9 more resultsHide 9 results
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · CyberGym leaderboard (Wang, Shi, He, Cai, Zhang, Song; UC Berkeley), ICLR 2026. Results evaluated and submitted by the listed teams. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only. · Deep20Bench edition 1.1, Patrick Heusser. Results CC BY 4.0; native question scores and fraction-to-percent success rates. (licence) · Steel.dev Agent Leaderboards, MIT (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · ExploitGym leaderboard (Wang et al., UC Berkeley), arXiv:2605.11086. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only, and task data keeps its upstream licences. Literal exploit counts; hidden rows omitted. · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Outback Yak Research, NepNewsBench v2 research draft. Public numerical aggregates from a candidate preview that the publisher says is not evidence of publication; no release licence assigned and none asserted here. · Trishul Lab, PutnamBench public submitted results. Model identities and scaffold budgets preserved; result licence unstated. · Hugging Face official benchmark leaderboards; licence varies by benchmark · Sierra Research tau2-bench leaderboard submissions (github.com/sierra-research/tau2-bench), MIT (licence) · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.
Around the web
- Anthropic (Claude AI) IPO Is HERE! $78/Share!!! Are We Investing $10,000? (6 Things You MUST Know)Discussion
youtube.com
- Discussion
- Discussion
- Discussion
- Discussion
Also known as: claude-opus-5, aihubmix/claude-opus-5, anthropic-claude-opus-5, anthropic.claude-opus-5, anthropic.claude-opus-5-v1, anthropic/claude-opus-5, anthropic/claude-opus-5-batch, anthropic/claude-opus-5-fast, anthropic/claude-opus-5:batch, apac.anthropic.claude-opus-5, au.anthropic.claude-opus-5, aws-bedrock/claude-opus-5, azure_ai/claude-opus-5, bedrock/claude-opus-5, bedrock/claude-opus-5@eu-central-1, bedrock/claude-opus-5@eu-north-1, bedrock/claude-opus-5@eu-west-1, bedrock/claude-opus-5@eu-west-3, bedrock/us-gov-east-1/anthropic.claude-opus-5, bedrock/us-gov-west-1/anthropic.claude-opus-5, bedrock_mantle/us-gov-west-1/anthropic.claude-opus-5, claude opus 5, claude opus 5 fast, claude-opus-5-fast, claude-opus-5-high, claude-opus-5-max, claude-opus-5-thinking, claude-opus-5@default, claude-opus-5@eu, databricks/databricks-claude-opus-5, deepinfra/anthropic/claude-opus-5, eu.anthropic.claude-opus-5, eu.anthropic.claude-opus-5-v1, github_copilot/claude-opus-5, global.anthropic.claude-opus-5, global.anthropic.claude-opus-5-v1, jp.anthropic.claude-opus-5, perplexity/anthropic/claude-opus-5, regional.anthropic.claude-opus-5, snowflake/claude-opus-5, us-gov.anthropic.claude-opus-5, us.anthropic.claude-opus-5, us.anthropic.claude-opus-5-v1, vertex/claude-opus-5, vertex/claude-opus-5@eu, vertex/claude-opus-5@us, vertex_ai/claude-opus-5, vertex_ai/claude-opus-5@default
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works