Get started

Claude Haiku 4.5 (batch)

Timed at 88.4 tok/s, scored 7.4 on the Intelligence Index, and on 8 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Haiku 4.5 (batch)USD per 1M tokens · as OpenRouter routes it
anthropic/claude-haiku-4.5:batchAnthropic · batch variant · Claude tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.50per 1M tokens
Output$2.50per 1M tokens
Cached input$0.05per 1M tokens
Context200k200,000 tokens
The other meters · every further rate the list publishes for this id, in the unit it states3 meters
Cache write$0.625per 1M tokens
Cache write, 1 hour$1.00per 1M tokens
Web search$0.01per search
What the list says · the fields OpenRouter publishes for this id11 fields
AuthorAnthropic
Listed
Canonical idanthropic/claude-4.5-haiku-20251001
Context200,000 tokens
Max output64,000 tokens
Modalitiestext, image, file → text
TokenizerClaude
Reasoningoptional
Moderationmoderated by OpenRouter
Variantbatch
Other listingbase listing

Measured speed

60,318 requests · 8 endpoints · 30-minute window
Throughput88.4 tok/sMedian output rate, weighted across the 8 endpoints serving it by the requests each answered.the speed board
First token609msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread44 to 147The 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

8 priced · 8 timed · cheapest first
  1. Amazon Bedrockamazon-bedrock/global$1.00$5.00$0.10not declared64k128 tok/s85633ms6 req100%
  2. Amazon Bedrockamazon-bedrock/global$1.00$5.00$0.10not declared64k93 tok/s51686ms44,302 req100%
  3. Amazon Bedrockamazon-bedrock/global$1.00$5.00$0.10not declared64k147 tok/s94518ms66 req100%
  4. Anthropicanthropic$1.00$5.00$0.10not declared64k76 tok/s52353ms14,018 req100%
  5. Azureazure/global$1.00$5.00$0.10not declared64k71 tok/s48.2505ms390 req100%
  6. Googlegoogle-vertex/global$1.00$5.00$0.10not declared64k44 tok/s39.72.83s148 req100%
  7. Googlegoogle-vertex/global$1.00$5.00$0.10not declared64k74 tok/s60.6540ms1,374 req100%
  8. Googlegoogle-vertex/global$1.00$5.00$0.10not declared64k96 tok/s62296ms14 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: 4 of the 8 timed routes are slower than it, and the middle route runs at 84.5 tok/s. The widest median-to-p90 gap is Amazon Bedrock's, 1.82x.

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 . 3 of the 8 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Azure at 96.68% on 13 Nov 2026, Amazon Bedrock (amazon-bedrock/us) at 97.22% on 15 Nov 2026, and Anthropic at 97.22% 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

12 parameters · 4 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. structured_outputsevery seller
  5. temperatureevery seller
  6. tool_choiceevery seller
  7. toolsevery seller
  8. top_kevery seller
  9. top_pevery seller
  10. response_format3 of 4not Google
  11. stop3 of 4not Azure
  12. max_completion_tokens1 of 4not Amazon Bedrock, Anthropic, and Google

9 of these 12 are accepted by every one of the 4 sellers that publish a list; the other 3 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 $1.00 per million tokens, 3 in to 1 out: cheaper than 147 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 Index7.4Position 48 of 58, above 17% of the models scored.the intelligence leaderboard
Coding Index43.9Position 69 of 118, above 42% of the models scored.the coding leaderboard
Agentic Index8.0Position 60 of 94, above 36% of the models scored.the agentic leaderboard
  1. 3D scenes · Models1052 Elowin rate 41.1% · source rank 112the board, 113 ranked
  2. ASCII art · Models1123 Elowin rate 49.3% · source rank 55the board, 67 ranked
  3. Code · Models1103 Elowin rate 44.9% · source rank 106the board, 120 ranked
  4. Data visualisation · Models1121 Elowin rate 45.7% · source rank 96the board, 110 ranked
  5. Game development · Models1086 Elowin rate 44.7% · source rank 103the board, 120 ranked
  6. SVG · Models1014 Elowin rate 39.1% · source rank 90the board, 83 ranked
  7. UI components · Models1088 Elowin rate 42.6% · source rank 104the board, 116 ranked
  8. Websites · Models1113 Elowin rate 45.1% · source rank 108the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index142.7141.0 to 144.4
Position111 of 258above 57% of the models placed
Results behind it16benchmark results
As Epoch names itClaude Haiku 4.5released 15 Oct 2025

Position 111 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 4.5 (batch) 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.