Anthropic · Chat
Claude Sonnet 5.5
Claude Sonnet 5.5 is Anthropic's advanced model for high-intelligence reasoning, coding, and autonomous tool workflows.
- llminfo IQ
- 143.9
- Maker's price
- $4.00 blended / 1M
- Max context
- 1M
- Listings
- 103
Evidence and sources
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Advantages
More provider options
Trade-offs
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 | $2.00cache read $0.10batch $1.00 | $10.00cache write 5m $2.50cache write 1h $4.00batch $5.00 | |
| 1M | $0.70 | $3.50 | |
| 1M | $0.7692cache read $0.0385 | $3.846cache write $0.9615 | |
| 1M | $0.7784cache read $0.0778 | $3.89cache write $0.9731 | |
| 1M | $0.80cache read $0.075 | $4.00cache write $1.60 | |
| 1M | $0.8543cache read $0.0854 | $4.2713 | |
| 1M | $1.00cache read $0.05 | $5.00cache write $1.25 | |
| 1M | $1.00cache read $0.05 | $5.00cache write 5m $1.25cache write 1h $2.00 | |
| 1M | $1.00cache read $0.05 | $5.00 | |
| 1M | $1.00cache read $0.05 | $5.00cache write $1.25 |
Showing 10 of 93: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by 302ai, Aihubmix, Aimlapi, Aixy, Amazon Web Services, Bumo, Cloudflare AI Gateway, Cometapi, Commandcode, Cortecs AI, Crossmodel, Databricks, Digitalocean, Dothoosh, Eden AI, Eurouter, Evolink, Fastrouter, Flowdot, Frogbot, Gisoo, Github Copilot, Google, Heroku, Hubris, Kenari, Kilo, Korouter, Llmgateway, Llmgateway Providers, Lowrouter, Meganova, Merge Gateway, Microsoft Azure, NanoGPT, Near AI, Neon, Neosantara, Netmind, Obscurify, Ofox, Outerlabs, Perplexity, Perplexity Agent, Prime, Ruapi, Snowflake, Sparrowcodes, Standardcompute, Synthorai, T Systems, Teamorouter, Venice, Vivgrid, Wavespeed, Writer, Zenmux.
10 listings without a price are hidden.
Included in plans
Benchmarks
Named effort levels run from lowest to highest. Select a result to see its source details.
Agentic
| Benchmark | High | Max |
|---|---|---|
| Arena Agent | ||
| Bash Recovery Steps | —Not measured | |
| Bash Reliability | ||
| Praise Complaint |
Show 3 more benchmarksHide 3 benchmarks
| Benchmark | High | Max |
|---|---|---|
| Steerability | ||
| Task Outcome Explicit | ||
| Tool Hallucination |
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
- OpenRouter's automatic routing
- Azure
- Amazon Bedrock
- Claude Platform on AWS
- Anthropic
| Benchmark | Score |
|---|---|
| Tax Agent Bench | |
| Finance Agent (v2) | |
| Finance Agent v2.1 | |
| Harvey's Legal Agent Benchmark v1 |
Show 3 more benchmarksHide 3 benchmarks
| Benchmark | Score |
|---|---|
| Terminal-Bench 2.1 | |
| Terminal-Bench 4.0 | |
| Terminal-Bench-Science |
Human preference
| Benchmark | xHigh |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| English |
Show 50 more benchmarksHide 50 benchmarks
Coding
| Benchmark | High | xHigh |
|---|---|---|
| Coding | —Not measured | |
| Text Factuality - Coding | —Not measured | |
| Webdev | ||
| Webdev - Image to Webdev | —Not measured |
Show 3 more benchmarksHide 3 benchmarks
| Benchmark | High | xHigh |
|---|---|---|
| Webdev - Webdev | ||
| Webdev - Webdev Html | ||
| Webdev - Webdev React |
Reasoning
Multilingual
Show 11 more resultsHide 11 results
General
Science
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
- Claude Platform on AWS
- Anthropic
- OpenRouter's automatic routing
- Amazon Bedrock
- Azure
Math
Vision
Instruction following
Factuality
Knowledge
OCR
Other
Show 2 more resultsHide 2 results
Show 14 more resultsHide 14 results
Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · 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. · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Benchmark Nusantara, ibahasa (M. Khoirul Huda), doi:10.5281/zenodo.21970463. Test results CC BY 4.0, attribution to ibahasa; aggregate results CSV only. (licence) · BullshitBench by Peter Gostev, MIT (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · 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) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · UzLiB, Tahrirchi (Abror Shopulatov). Public LEADERBOARD.md numbers; repository MIT covers software and documentation, no separate results licence stated and none asserted. · WeirdML v3 by Håvard Tveit Ihle (Norwegian Defence Research Establishment). API costs supported by Epoch AI, METR and NDRE.
Around the web
- Anthropic carelessly killed a Claude Code feature users built on, no warningDiscussion
26 points, 7 comments
news.ycombinator.com
- Anthropic upgrades Claude Code Projects to run parallel AI workersDiscussion
100 points, 97 comments
news.ycombinator.com
- Claude Mythos slashed software work to onboard AMD GPUs to around three daysDiscussion
55 points, 21 comments
news.ycombinator.com
- Mythos got Claude running on AMD chips in three days, a job that took monthsDiscussion
5 points, 5 comments
news.ycombinator.com
- Show HN: Langfuse AI Gateway, open source rust gateway to trace every LLM callDiscussion
9 points, 1 comment
news.ycombinator.com
Also known as: anthropic-claude-sonnet-5.5, anthropic.claude-sonnet-5-5, anthropic.claude-sonnet-5-5-v1, anthropic/claude-sonnet-5-5, anthropic/claude-sonnet-5.5, anthropic/claude-sonnet-5.5-batch, anthropic/claude-sonnet-5.5:batch, anthropic/claude-sonnet-5.5:thinking, apac.anthropic.claude-sonnet-5-5, au.anthropic.claude-sonnet-5-5, aws-bedrock/claude-sonnet-5-5, azure_ai/claude-sonnet-5-5, bedrock/us-gov-east-1/anthropic.claude-sonnet-5-5, bedrock/us-gov-west-1/anthropic.claude-sonnet-5-5, bedrock_mantle/anthropic.claude-sonnet-5-5, bedrock_mantle/us-gov-west-1/anthropic.claude-sonnet-5-5, ca.anthropic.claude-sonnet-5-5, claude sonnet 5.5, claude-sonnet-5-5, claude-sonnet-5-5-thinking, claude-sonnet-5-5@default, claude-sonnet-5-5@eu, claude-sonnet-5.5-high, claude-sonnet-5.5-max, claude-sonnet-5.5-xhigh, databricks/databricks-claude-sonnet-5-5, eu.anthropic.claude-sonnet-5-5, eu.anthropic.claude-sonnet-5-5-v1, github_copilot/claude-sonnet-5.5, global.anthropic.claude-sonnet-5-5, global.anthropic.claude-sonnet-5-5-v1, jp.anthropic.claude-sonnet-5-5, perplexity/anthropic/claude-sonnet-5-5, snowflake/claude-sonnet-5-5, us-gov.anthropic.claude-sonnet-5-5, us.anthropic.claude-sonnet-5-5, us.anthropic.claude-sonnet-5-5-v1, vertex-anthropic/claude-sonnet-5-5, vertex_ai/claude-sonnet-5-5, vertex_ai/claude-sonnet-5-5@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