Get started

Claude Haiku 5.5

Timed at 145 tok/s, scored 36.5 on the Intelligence Index, and on 9 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Haiku 5.5USD per 1M tokens · as OpenRouter routes it
anthropic/claude-haiku-5.5Anthropic · base listing · Claude tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.10per 1M tokens
Output$0.50per 1M tokens
Cached input$0.01per 1M tokens
Context1M1,000,000 tokens
The other meters · every further rate the list publishes for this id, in the unit it states3 meters
Cache write$0.125per 1M tokens
Cache write, 1 hour$0.20per 1M tokens
Web search$0.01per search
Over the base window · the rate the list gives once a prompt is longer than a thresholdin / out per 1M tokens
Prompts over 100K tokens$0.50 / $2.50cached $0.05
What Vitna read · the provider's own pricing page, kept as a dated recordin / out per 1M tokens
Anthropicthe maker$0.10 / $0.50confirmed 22 Nov 2026

The maker's own list price, read from platform.claude.com. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.

What the list says · the fields OpenRouter publishes for this id10 fields
AuthorAnthropic
Listed
Canonical idanthropic/claude-haiku-5.5-20261007
Context1,000,000 tokens
Max output128,000 tokens
Modalitiestext, image, file → text
TokenizerClaude
Reasoningoptional · effort max, xhigh, high, medium, low, none, medium by default
Moderationmoderated by OpenRouter
Other listingbatch variant

Measured speed

1,286,911 requests · 10 endpoints · 30-minute window
Throughput145 tok/sMedian output rate, weighted across the 10 endpoints serving it by the requests each answered.the speed board
First token1.57sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread110 to 163The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

10 priced · 10 timed · cheapest first
  1. Amazon Bedrockamazon-bedrock · listed$0.10$0.50$0.01not declared128k152 tok/s543.31s43,817 req100%
  2. Amazon Bedrockamazon-bedrock · listed$0.10$0.50$0.01not declared128k145 tok/s712.31s284 req100%
  3. Amazon Bedrockamazon-bedrock · listed$0.10$0.50$0.01not declared128k110 tok/s512.19s1,927 req100%
  4. Anthropicanthropic · listed$0.10$0.50$0.01not declared128k137 tok/s1001.71s820,837 req100%
  5. Azureazure/global · listed$0.10$0.50$0.01not declared128k145 tok/s871.35s170 req100%
  6. Azureazure/global · listed$0.10$0.50$0.01not declared128k163 tok/s871.17s48,034 req100%
  7. Claude Platform on AWSclaude-on-aws · listed$0.10$0.50$0.01not declared128k160 tok/s871.06s270,539 req100%
  8. Googlegoogle-vertex/global · listed$0.10$0.50$0.01not declared128k153 tok/s821.26s84,991 req100%
  9. Googlegoogle-vertex/global · listed$0.10$0.50$0.01not declared128k134 tok/s961.34s2,459 req100%
  10. Googlegoogle-vertex/global · listed$0.10$0.50$0.01not declared128k157 tok/s89.1683ms13,853 req100%

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 3 of the 10 timed routes are slower than it, and the middle route runs at 149 tok/s. The widest median-to-p90 gap is Amazon Bedrock's, 2.81x.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 4 of the 10 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Amazon Bedrock (amazon-bedrock) at 84.30% on 8 Nov 2026, Amazon Bedrock (amazon-bedrock/us-east-1) at 88.96% on 6 Nov 2026, Anthropic at 97.01% on 13 Nov 2026, and Azure (azure/global) at 98.54% on 13 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

11 parameters · 5 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. reasoning_effortevery seller
  5. response_formatevery seller
  6. stopevery seller
  7. tool_choiceevery seller
  8. toolsevery seller
  9. verbosityevery seller
  10. structured_outputs3 of 5not Amazon Bedrock and Claude Platform on AWS
  11. max_completion_tokens1 of 5only Azure

9 of these 11 are accepted by every one of the 5 sellers that publish a list; the other 2 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $0.20 per million tokens, 3 in to 1 out: cheaper than 266 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board

Each mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.

Intelligence Index36.5Position 16 of 58, above 72% of the models scored.the intelligence leaderboard
Coding Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard
  1. pdf · Agents1260 Elowin rate 63.0% · source rank 8the board, 36 ranked
  2. 3D scenes · Models1319 Elowin rate 55.1% · source rank 17the board, 113 ranked
  3. ASCII art · Models1204 Elowin rate 49.6% · source rank 24the board, 67 ranked
  4. Code · Models1276 Elowin rate 49.9% · source rank 26the board, 120 ranked
  5. Data visualisation · Models1277 Elowin rate 50.4% · source rank 20the board, 110 ranked
  6. Game development · Models1313 Elowin rate 51.2% · source rank 15the board, 120 ranked
  7. SVG · Models1196 Elowin rate 43.9% · source rank 31the board, 83 ranked
  8. UI components · Models1267 Elowin rate 50.0% · source rank 33the board, 116 ranked
  9. Websites · Models1252 Elowin rate 48.1% · source rank 42the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index160.3158.2 to 162.7
Position20 of 258above 93% of the models placed
Results behind it20benchmark results
As Epoch names itClaude Haiku 5.5released 7 Oct 2026

Position 20 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Claude Haiku 5.5 under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.