Claude Haiku 4.5

AnthropicKey claude-haiku-4-5Also reported as claude-haiku-4-5-20251001, anthropic/claude-haiku-4-5, router_client:claude/claude-haiku-4-5-20251001, cc/claude-haiku-4-5, claude-haiku-4.5, claude haiku 4-5, geraikita/gk/claude-haiku-4-5, anthropic/claude-4-5-haiku, router_client:unknown/claude-haiku-4-5-20251001, github-copilot/claude-haiku-4-5, gh/claude-haiku-4-5, kr/claude-haiku-4-5, anthropic/claude-haiku-4.5, enowxai/claude-haiku-4-5, copilot/claude-haiku-4-5, claude/claude-haiku-4-5, devin/claude-haiku-4-5, openrouter/anthropic/claude-haiku-4-5, gk/claude-haiku-4-5, cliproxyapi/claude-haiku-4-5

Rank
#25
by active users
Active users
102
Down 329 from 431 active users in the previous 30 days. vs previous 30 days
Adoption
11%
of 961 accounts
Tokens
6.6B
cache included
Est. cost
$2.7K
at public list prices
First seen
Jan 2, 2025
in any submission

Oct 14 – Nov 12, 2026 (UTC)961 accounts100% of tokens from an identified modelData through Nov 12, 2026, 06:48 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

2 active users on Nov 12, 2026

Daily active users for Claude Haiku 4.5, Oct 14, 2026 to Nov 12, 2026. Peak 37. Use the left and right arrow keys to read each day.40200
Show daily values
Daily active users and tokens for Claude Haiku 4.5
Date (UTC)Active usersTokens
Oct 14, 202637171.4M
Oct 15, 202629198.1M
Oct 16, 20262117.7M
Oct 17, 20262023.2M
Oct 18, 20261924.5M
Oct 19, 20262049.8M
Oct 20, 20261645.5M
Oct 21, 20262465.7M
Oct 22, 202623147.9M
Oct 23, 202625180.8M
Oct 24, 202613282.8M
Oct 25, 202611459.7M
Oct 26, 202619355.1M
Oct 27, 202614231.4M
Oct 28, 202618220.1M
Oct 29, 202613444.3M
Oct 30, 202614275.9M
Oct 31, 202612162.7M
Nov 1, 202613163.5M
Nov 2, 202616121.7M
Nov 3, 202617147.4M
Nov 4, 202617351.3M
Nov 5, 202617436.7M
Nov 6, 202617542.3M
Nov 7, 202613418M
Nov 8, 202615373M
Nov 9, 202613343.7M
Nov 10, 202612285.4M
Nov 11, 202610103.3M
Nov 12, 202621.5M

Token mix

How the 6.6B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input0.9%
  • Output0.9%
  • Cache read84%
  • Cache write15%
  • Reasoning<0.1%

Agents that carry Claude Haiku 4.5

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. Claude Code98% of this model's tokens85active users
  2. OpenCode0.9% of this model's tokens8active users
  3. Senpi (OmO Native)0.5% of this model's tokens7active users
  4. Aside0.1% of this model's tokens1active users
  5. Copilot<0.1% of this model's tokens2active users
  6. OpenClaw<0.1% of this model's tokens1active users
  7. Oh My Pi<0.1% of this model's tokens2active users
  8. Pi<0.1% of this model's tokens3active users
  9. Junie<0.1% of this model's tokens3active users
  10. DeepSeek Harness<0.1% of this model's tokens1active users
  11. cc-mirror/mozilla<0.1% of this model's tokens1active users
  12. cc-mirror/curl<0.1% of this model's tokens1active users

Benchmarks

The best result for Claude Haiku 4.5 in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.

All benchmarks
  • Epoch Capabilities IndexOverall · Epoch AI
    142.8
    Rank #103 of 158 matched modelsNo conditions reportedModel released Oct 15, 2025Source: epoch.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,330
    Rank #95 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    71.2%
    Rank #110 of 160 matched models32K budgetRun date Oct 22, 2025Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.5%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

    Show 1 more result with other run conditionsHide the other results
    • Listed as claude-haiku-4-5-20251001
      60.5%
      No conditions reportedRun date Oct 16, 2025Source: epoch.ai (opens in a new tab)
  • SimpleQA VerifiedKnowledge · Epoch AI
    13.2%
    Rank #80 of 86 matched modelsNo conditions reportedRun date Aug 10, 2026Source: epoch.ai (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as claude-haiku-4-5-20251001_32K
      12.6%
      32K budgetRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, FrontierMath Tiers 1–3 (v2), Terminal-Bench 4.1, CursorBench, DeepSWE, FrontierSWE, Agent Arena. A missing result is not a score of zero.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. Anthropic is the lab's own API and the reference price for the estimates below.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0.32
Est. per 1M tokens
84% cache reads
At the community mix
$0.15
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$2
Per 1M tokens at list prices
No cache

Cache reads were 84% of Claude Haiku 4.5 tokens in the last 30 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • Anthropic list prices per 1M tokens: input $1, output $5, cache read $0.10, cache write $1.25.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 30 days.
  • The community mix is the tokens of every identified model in the last 30 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.

List prices by provider

  • AnthropicReferenceclaude-haiku-4-5
    $1 input per 1M tokens$5 output per 1M tokens$0.10 cache read per 1M tokens$1.25 cache write per 1M tokens200K tokens of context
  • Amazon Bedrockanthropic.claude-haiku-4-5-20251001-v1:0
    $1 input per 1M tokens$5 output per 1M tokens$0.10 cache read per 1M tokens$1.25 cache write per 1M tokens200K tokens of context
  • Vertexclaude-haiku-4-5@20251001
    $1 input per 1M tokens$5 output per 1M tokens$0.10 cache read per 1M tokens$1.25 cache write per 1M tokens200K tokens of context
  • Vertex (Anthropic)claude-haiku-4-5@20251001
    $1 input per 1M tokens$5 output per 1M tokens$0.10 cache read per 1M tokens$1.25 cache write per 1M tokens200K tokens of context
Show 2 more providersShow fewer providers
  • OpenRouteranthropic/claude-haiku-4.5
    $1 input per 1M tokens$5 output per 1M tokens$0.10 cache read per 1M tokens$1.25 cache write per 1M tokens200K tokens of context
  • Vercel AI Gatewayanthropic/claude-haiku-4.5
    $1 input per 1M tokens$5 output per 1M tokens$0.10 cache read per 1M tokens$1.25 cache write per 1M tokens200K tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
200K tokens
Max output
64K tokens
Input
Text, Image, PDF
Output
Text
Knowledge cutoff
Feb 28, 2025
Release date
Oct 15, 2025
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Claude Haiku 4.5 most in this period, by tokens. Hidden accounts are never listed.

  1. 1registered2nd@registered2nd4.1Btokens$1.7Kest. cost29active days$1.7K est. cost · 29 active days
  2. 2Komal Vardhan Lolugu@KomalSrinivasan1Btokens$330est. cost21active days$330 est. cost · 21 active days
  3. 3Bulo@BuloZB346.4Mtokens$104est. cost8active days$104 est. cost · 8 active days
  4. 4leko@lekoOwO193Mtokens$40est. cost13active days$40 est. cost · 13 active days
  5. 5kil-penguin@kilhyeonjun110Mtokens$19est. cost8active days$19 est. cost · 8 active days
  6. 6seoyoung@b1ueseoyoung86.9Mtokens$33est. cost6active days$33 est. cost · 6 active days
  7. 7cmj1203@cmj120383.9Mtokens$52est. cost3active days$52 est. cost · 3 active days
  8. 8ManzJoozy@JTZ1883.6Mtokens$17est. cost9active days$17 est. cost · 9 active days
  9. 9Jonathannkayy@Jonathannkayy64.9Mtokens$29est. cost23active days$29 est. cost · 23 active days
  10. 10hanukoon@cokia59.4Mtokens$60est. cost16active days$60 est. cost · 16 active days

More from Anthropic

Other Anthropic models in the same period, by active users.

  1. Claude Opus 5.574% adoption713active users
  2. Claude Sonnet 5.558% adoption557active users
  3. Claude Haiku 5.550% adoption479active users
  4. Claude Fable 5.138% adoption362active users
  5. Claude Opus 4.823% adoption222active users
  6. Claude Fable 5.220% adoption192active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • Epoch AIEpoch Capabilities Index, Epoch's own runs and the external results it collects.CC BY 4.0 · Retrieved Nov 12, 2026 · Data through Nov 9, 2026Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.
  • LMArenaWebDev Arena and Agent Arena leaderboards.CC BY 4.0 · Retrieved Oct 21, 2026 · Data through Oct 19, 2026LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), Hugging Face.
  • models.devSpecs and list prices per provider.MIT · Retrieved Nov 12, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count