Claude Sonnet 4.5

AnthropicKey claude-sonnet-4-5Also reported as claude-sonnet-4-5-20250929, claude-sonnet-4.5, claude sonnet 4-5, anthropic/claude-sonnet-4-5, kr/claude-sonnet-4-5, anthropic/claude-sonnet-4.5, antigravity/claude-sonnet-4-5, anthropic/claude-sonnet-4-5-20250929, anthropic/claude-4-5-sonnet, kiro/claude-sonnet-4-5, gh/claude-sonnet-4-5, enowxai/claude-sonnet-4-5, openrouter/anthropic/claude-sonnet-4-5, group/claude-sonnet-4-5, claude/claude-sonnet-4-5

Rank
#59
by active users
Active users
22
Down 14 from 36 active users in the previous 30 days. vs previous 30 days
Adoption
2.3%
of 967 accounts
Tokens
2.1B
cache included
Est. cost
$2K
at public list prices
First seen
Jan 1, 2025
in any submission

Oct 15 – Nov 13, 2026 (UTC)967 accounts100% of tokens from an identified modelData through Nov 13, 2026, 06:12 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

1 active users on Nov 13, 2026

Daily active users for Claude Sonnet 4.5, Oct 15, 2026 to Nov 13, 2026. Peak 8. Use the left and right arrow keys to read each day.840
Show daily values
Daily active users and tokens for Claude Sonnet 4.5
Date (UTC)Active usersTokens
Oct 15, 20268420.2M
Oct 16, 20267261.6M
Oct 17, 202622.2M
Oct 18, 20265127.6M
Oct 19, 20266182.3M
Oct 20, 2026351.4M
Oct 21, 20265104.4M
Oct 22, 2026777.5M
Oct 23, 20265142.7M
Oct 24, 202657.9M
Oct 25, 202652.2M
Oct 26, 20267107.1M
Oct 27, 2026588.4M
Oct 28, 2026352.8M
Oct 29, 2026245M
Oct 30, 2026226.9M
Oct 31, 2026176.1K
Nov 1, 202629.4M
Nov 2, 20262103.6M
Nov 3, 2026315.8M
Nov 4, 2026446.7M
Nov 5, 20262121M
Nov 6, 2026314.9M
Nov 7, 2026144.6K
Nov 8, 202632.2M
Nov 9, 20262355K
Nov 10, 2026141.4M
Nov 11, 2026219.3M
Nov 12, 202600
Nov 13, 2026183.3K

Token mix

How the 2.1B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input2.0%
  • Output1.4%
  • Cache read89%
  • Cache write7.3%
  • Reasoning<0.1%

Agents that carry Claude Sonnet 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 tokens13active users
  2. OpenClaw1.3% of this model's tokens1active users
  3. Hermes Agent0.6% of this model's tokens3active users
  4. Oh My Pi0.2% of this model's tokens2active users
  5. Pi<0.1% of this model's tokens1active users
  6. OpenCode<0.1% of this model's tokens1active users
  7. Codex CLI<0.1% of this model's tokens1active users
  8. Kiro<0.1% of this model's tokens1active users
  9. Gajae Code<0.1% of this model's tokens1active users
  10. Senpi (OmO Native)<0.1% of this model's tokens1active users

Benchmarks

The best result for Claude Sonnet 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
    147.6
    Rank #77 of 158 matched modelsNo conditions reportedModel released Sep 29, 2025Source: epoch.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,394
    Rank #82 of 110 matched modelsHighPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as Claude Sonnet 4.5 (20250929)
      1,385
      No conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    82.3%
    Rank #86 of 160 matched models59K budgetRun date Oct 28, 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 3 more results with other run conditionsHide the other results
    • Listed as claude-sonnet-4-5-20250929_32K
      81.7%
      32K budgetRun date Oct 21, 2025Source: epoch.ai (opens in a new tab)
    • Listed as claude-sonnet-4-5-20250929_16K
      78.8%
      16K budgetRun date Oct 28, 2025Source: epoch.ai (opens in a new tab)
    • Listed as claude-sonnet-4-5-20250929
      73.7%
      No conditions reportedRun date Sep 29, 2025Source: epoch.ai (opens in a new tab)
  • Humanity's Last ExamReasoning · Center for AI Safety and Scale AI, collected by Epoch AI
    13.7%
    Rank #24 of 40 matched modelsNo conditions reportedModel released Sep 29, 2025Source: lastexam.ai (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as claude-sonnet-4-5-20250929
      7.5%
      No conditions reportedModel released Sep 29, 2025Source: lastexam.ai (opens in a new tab)
  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    23.9%
    Rank #76 of 90 matched models32K budgetRun date Jun 11, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 95.1%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

  • SimpleQA VerifiedKnowledge · Epoch AI
    30.7%
    Rank #67 of 86 matched models59K budgetRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as claude-sonnet-4-5-20250929
      23.7%
      No conditions reportedRun date Aug 10, 2026Source: epoch.ai (opens in a new tab)
  • SWE-bench VerifiedHistory · Epoch AI
    71.3%
    Rank #23 of 32 matched modelsNo conditions reportedRun date Feb 5, 2026Source: epoch.ai (opens in a new tab)

    History only. Newer agentic coding benchmarks are on the main board.

Not evaluated: 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
$0.81
Est. per 1M tokens
89% cache reads
At the community mix
$0.46
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$6
Per 1M tokens at list prices
No cache

Cache reads were 89% of Claude Sonnet 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 $3, output $15, cache read $0.30, cache write $3.75.
  • 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-sonnet-4-5
    $3 input per 1M tokens$15 output per 1M tokens$0.30 cache read per 1M tokens$3.75 cache write per 1M tokens200K tokens of context
  • Amazon Bedrockanthropic.claude-sonnet-4-5-20250929-v1:0
    $3 input per 1M tokens$15 output per 1M tokens$0.30 cache read per 1M tokens$3.75 cache write per 1M tokens200K tokens of context
  • Vertexclaude-sonnet-4-5@20250929
    $3 input per 1M tokens$15 output per 1M tokens$0.30 cache read per 1M tokens$3.75 cache write per 1M tokens200K tokens of context
  • Vertex (Anthropic)claude-sonnet-4-5@20250929
    $3 input per 1M tokens$15 output per 1M tokens$0.30 cache read per 1M tokens$3.75 cache write per 1M tokens200K tokens of context
Show 2 more providersShow fewer providers
  • OpenRouteranthropic/claude-sonnet-4.5
    $3 input per 1M tokens$15 output per 1M tokens$0.30 cache read per 1M tokens$3.75 cache write per 1M tokens1M tokens of context
  • Vercel AI Gatewayanthropic/claude-sonnet-4.5
    $3 input per 1M tokens$15 output per 1M tokens$0.30 cache read per 1M tokens$3.75 cache write per 1M tokens1M 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
Jul 31, 2025
Release date
Sep 29, 2025
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

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

  1. 1Amit Rajput@amit_fwo439.8Mtokens$391est. cost14active days$391 est. cost · 14 active days
  2. 2Ing Tian@IngTian370.7Mtokens$200est. cost9active days$200 est. cost · 9 active days
  3. 3Amit Rajput@AmitRajput-Dev329.3Mtokens$276est. cost11active days$276 est. cost · 11 active days
  4. 4fwo_admin@fwo_admin329Mtokens$276est. cost11active days$276 est. cost · 11 active days
  5. 5autocat@donghyeon-dev303.1Mtokens$322est. cost21active days$322 est. cost · 21 active days
  6. 6Shun Kakinoki@shunkakinoki243.1Mtokens$307est. cost2active days$307 est. cost · 2 active days
  7. 7heyrm@rizlmaulanaa39.2Mtokens$119est. cost2active days$119 est. cost · 2 active days
  8. 8Randy Chang@raw3410.3Mtokens$76est. cost15active days$76 est. cost · 15 active days
  9. 9Bulo@BuloZB4.9Mtokens$7est. cost3active days$7 est. cost · 3 active days
  10. 10SangBum Kim@Puri122.1Mtokens$3est. cost1active days$3 est. cost · 1 active days

More from Anthropic

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

  1. Claude Opus 5.574% adoption720active users
  2. Claude Sonnet 5.558% adoption565active users
  3. Claude Haiku 5.551% adoption490active users
  4. Claude Fable 5.138% adoption367active users
  5. Claude Fable 5.226% adoption255active users
  6. Claude Opus 4.823% adoption222active 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