Claude Haiku 5.5
Claude Haiku 5.5 brings adaptive reasoning to Anthropic’s low-cost Haiku family for everyday tasks, tool use, and scaled sub-agent deployments.
text + image + file → text · made by Anthropic
$0.1→$0.5per Mtok in / out
Anthropic · 14 sellers
Sold by 39 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | batch | $0.05per Mtok in$0.25per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| DigitalOcean cloud | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writemodels.dev · read 2026-10-31 |
| Google Vertex AI cloud | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writemodels.dev · read 2026-10-31 |
| Databricks cloud | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.13per Mtok cache writeraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | standard | $0.11per Mtok in$0.55per Mtok out$0.011per Mtok cached$0.14per Mtok cache writemodels.dev · read 2026-10-31 |
| Nous Research 2 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache write | |
| Nous Research aggregator | batch | $0.05per Mtok in$0.25per Mtok out$0.005per Mtok cached$0.062per Mtok cache writeinference-api.nousresearch.com · read 2026-10-09 |
| Nous Research aggregator | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writeinference-api.nousresearch.com · read 2026-10-09 |
| OpenRouter 12 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache write | |
| OpenRouter aggregator | batch | $0.05per Mtok in$0.25per Mtok out$0.005per Mtok cached$0.062per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | amazon-bedrock | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | anthropic | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | azure/global | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | claude-on-aws | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | google-vertex/global | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | amazon-bedrock/eu-west-1 | $0.11per Mtok in$0.55per Mtok out$0.011per Mtok cached$0.14per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | amazon-bedrock/us-east-1 | $0.11per Mtok in$0.55per Mtok out$0.011per Mtok cached$0.14per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | azure/us | $0.11per Mtok in$0.55per Mtok out$0.011per Mtok cached$0.14per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | google-vertex/europe | $0.11per Mtok in$0.55per Mtok out$0.011per Mtok cached$0.14per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| OpenRouter aggregator | google-vertex/us | $0.11per Mtok in$0.55per Mtok out$0.011per Mtok cached$0.14per Mtok cache writeopenrouter.ai · read 2026-10-09 |
| Anthropic aggregator | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cacheddocs.claude.com · read 2026-10-31 |
| ElectronHub aggregator | standard | $0.1per Mtok in$0.5per Mtok outapi.electronhub.ai · read 2026-10-31 |
| GitHub Copilot aggregator | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writemodels.dev · read 2026-10-31 |
| Microsoft Azure AI aggregator | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writemodels.dev · read 2026-10-31 |
| Requesty 2 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| Requesty aggregator | anthropic | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedrouter.requesty.ai · read 2026-10-09 |
| Requesty aggregator | bedrock | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedrouter.requesty.ai · read 2026-10-09 |
| Venice AI aggregator | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writemodels.dev · read 2026-10-31 |
| Vercel AI Gateway aggregator | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached$0.12per Mtok cache writeai-gateway.vercel.sh · read 2026-10-09 |
| azure-cognitive-services 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| azure-cognitive-services aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| edenai 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| edenai aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| google-vertex 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| google-vertex aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| google-vertex-anthropic aggregator | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| kilo 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| kilo aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| llmgateway 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| llmgateway aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| llmgateway-providers 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| llmgateway-providers aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| merge-gateway 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| merge-gateway aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| nano-gpt 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| nano-gpt aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| opencode 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| opencode aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| opencode-go 0 ways | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cached | |
| opencode-go aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.5per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-10-08 |
| amazon-bedrock 0 ways | $0.11per Mtok in$0.55per Mtok out$0.011per Mtok cached | |
| amazon-bedrock aggregatornot on the seller's list today | standard | $0.11per Mtok in$0.55per Mtok out$0.011per Mtok cachedmodels.dev · read 2026-10-08 |
Measured 39 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 5thof 30 | Mirrorcode — Epoch AI | mean_score (max) | 78.889 |
| 8thof 21 | Frontierswe — Epoch AI | Score (max) | 43.769 |
| 10thof 28 | Ebr bench — Epoch AI | mean_score (max) | 43.81 |
| 10thof 84 | Proofbench — Epoch AI | Accuracy (max) | 89 |
| 13thof 35 | Furniture assembly — Epoch AI | mean_score (max) | 47.5 |
| 13thof 56 | Humanity's Last Exam (Epoch AI replication) | Accuracy | 30.12 |
| 13thof 25 | Weirdml v3 — Epoch AI | Score (xhigh) | 11.695 |
| 15thof 35 | Blueprint bench 2 — Epoch AI | Score | 32.972 |
| 15thof 82 | Cursorbench — Epoch AI | Score (max) | 48.4 |
| 15thof 46 | Frontiercode — Epoch AI | Main score (max) | 0.464 |
| 16thof 154 | Chess puzzles — Epoch AI | mean_score (max) | 55 |
| 17thof 150 | Design Arena · 3d (models) | Elo | 1340 |
| 20thof 162 | Design Arena · gamedev (models) | Elo | 1321 |
| 21stof 60 | Apex agents — Epoch AI | Pass@1 score (max) | 0.561 |
| 21stof 122 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score (max) | 75.088 |
| 21stof 306 | OTIS Mock AIME 2024-2025 | mean_score (xhigh) | 98.889 |
| 23rdof 132 | Ale bench — Epoch AI | Performance (high) | 1587 |
| 25thof 154 | Design Arena · dataviz (models) | Elo | 1289 |
| 29thof 78 | Frontiermath tier 4 v2 — Epoch AI | mean_score (max) | 46.341 |
| 31stof 86 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index (max) | 36 |
| 35thof 142 | Mystery game puzzles — Epoch AI | mean_score (max) | 30 |
| 36thof 163 | Design Arena · codecategories (models) | Elo | 1280 |
| 38thof 157 | Design Arena · uicomponent (models) | Elo | 1278 |
| 43rdof 114 | Design Arena · svg (models) | Elo | 1205 |
| 45thof 235 | Dtbench — Epoch AI | Accuracy (max) | 94.99 |
| 48thof 71 | Vending bench 2 — Epoch AI | Score | 3602.463 |
| 54thof 169 | Design Arena · website (models) | Elo | 1261 |
| 54thof 326 | GPQA Diamond | mean_score (max) | 89.646 |
| 58thof 260 | Critpt — Epoch AI | Accuracy (xhigh) | 22.571 |
| 60thof 235 | Scicode — Epoch AI | Score (max) | 54.977 |
| 62ndof 197 | Lmca — Epoch AI | Score (max) | 51.06 |
| 75thof 93 | Simpleqa verified — Epoch AI | mean_score (max) | 23.8 |
| 76thof 112 | ARC-AGI-3 (Semi-Private) | Score (%) (max) | 0.45 |
| 77thof 282 | ARC-AGI-2 (Public Eval) | Score (%) (xhigh) | 64.44 |
| 85thof 298 | ARC-AGI-2 (Semi-Private) | Score (%) (xhigh) | 61.25 |
| 88thof 298 | ARC-AGI-1 (Semi-Private) | Score (%) (max) | 89 |
| 92ndof 290 | Arc agi 2 — Epoch AI | Score (xhigh) | 61.25 |
| 96thof 309 | Arc agi — Epoch AI | Score (max) | 89 |
| 107thof 273 | ARC-AGI-1 (Public Eval) | Score (%) (max) | 90.12 |
About
Claude Haiku 5.5 — a text model from Anthropic, sold by 14 companies from $0.1 in and $0.5 out per million tokens, placed 21st of 306 on OTIS Mock AIME 2024-2025.
It takes text, images and files and returns text, with a context window of 1,000,000 tokens. It was published in October 2026, trained on material up to June 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and agents. Fourteen companies sell it. The cheapest is $0.1 in and $0.5 out per million tokens at Anthropic. Beside the standard rate there are batch, separately routed and regional lanes. It has been measured on 39 boards, and stands best at 21st of 306 on OTIS Mock AIME 2024-2025.
Every current figure
- Maker
- Anthropic
- Register
- model
- Takes
- text + image + file
- Returns
- text
- Context
- 1,000,000 tokens
- Longest answer
- 128,000 tokens
- Published
- October 2026
- Knowledge to
- June 2026
- Licence
- not read
- Sellers
- 14
- Price
- $0.1 in and $0.5 out per million tokens — Anthropic
- Boards
- 39
- Best place
- 21st of 306 — OTIS Mock AIME 2024-2025
Known as 3 names
anthropic/claude-haiku-5.5anthropic/claude-haiku-5-5bedrock/claude-haiku-5-5