Claude Sonnet 4.6

AnthropicKey claude-sonnet-4-6Also reported as router_client:claude/claude-sonnet-4-6, kr/claude-sonnet-4-6, anthropic/claude-sonnet-4-6, cc/claude-sonnet-4-6, dario/claude-sonnet-4-6, claude-sonnet-4.6, kiro/claude-sonnet-4-6, claude/claude-sonnet-4-6, google-antigravity/claude-sonnet-4-6, combo/todo-orchestrator/claude-sonnet-4-6, anthropic/claude-4-6-sonnet, gh/claude-sonnet-4-6, frg/claude-sonnet-4-6, combo/writing/claude-sonnet-4-6, combo/plan-gap-analyzer/claude-sonnet-4-6, ag/claude-sonnet-4-6, agy/claude-sonnet-4-6, no-think/claude/claude-sonnet-4-6, combo/unspecified-low/claude-sonnet-4-6, omni/claude/claude-sonnet-4-6

Rank
#34
by active users
Active users
55
Down 45 from 100 active users in the previous 30 days. vs previous 30 days
Adoption
5.7%
of 961 accounts
Tokens
5.3B
cache included
Est. cost
$3K
at public list prices
First seen
Nov 18, 2025
in any submission

Oct 14 – Nov 12, 2026 (UTC)961 accounts100% of tokens from an identified modelData through Nov 12, 2026, 06:58 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

0 active users on Nov 12, 2026

Daily active users for Claude Sonnet 4.6, Oct 14, 2026 to Nov 12, 2026. Peak 12. Use the left and right arrow keys to read each day.1580
Show daily values
Daily active users and tokens for Claude Sonnet 4.6
Date (UTC)Active usersTokens
Oct 14, 20261246.1M
Oct 15, 20261249.2M
Oct 16, 20261247.2M
Oct 17, 20261187.6M
Oct 18, 20261246.8M
Oct 19, 20261034.2M
Oct 20, 2026953.7M
Oct 21, 2026718.4M
Oct 22, 2026885.2M
Oct 23, 20266164.7M
Oct 24, 20267520.8M
Oct 25, 20267152.6M
Oct 26, 2026856M
Oct 27, 2026410.4M
Oct 28, 20265725M
Oct 29, 20265493.1M
Oct 30, 20265699M
Oct 31, 202651.3B
Nov 1, 20261614K
Nov 2, 20265129.6M
Nov 3, 20264169.5M
Nov 4, 2026411M
Nov 5, 2026541M
Nov 6, 2026518.7M
Nov 7, 2026217.9M
Nov 8, 2026149.1M
Nov 9, 2026329M
Nov 10, 20263112.7M
Nov 11, 2026397.2M
Nov 12, 202600

Token mix

How the 5.3B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input2.7%
  • Output0.7%
  • Cache read94%
  • Cache write2.4%
  • Reasoning<0.1%

Agents that carry Claude Sonnet 4.6

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

  1. Claude Code60% of this model's tokens28active users
  2. Oh My Pi31% of this model's tokens5active users
  3. OpenClaw3.1% of this model's tokens1active users
  4. Pi3.0% of this model's tokens3active users
  5. Goose1.1% of this model's tokens1active users
  6. Antigravity1.0% of this model's tokens3active users
  7. Antigravity IDE Extension0.7% of this model's tokens6active users
  8. OpenCode0.3% of this model's tokens3active users
  9. Reasonix0.1% of this model's tokens1active users
  10. DeepSeek Harness0.1% of this model's tokens2active users
  11. Antigravity CLI<0.1% of this model's tokens5active users
  12. 9Router<0.1% of this model's tokens1active users
  13. Hermes Agent<0.1% of this model's tokens1active users

Benchmarks

The best result for Claude Sonnet 4.6 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
    152.9
    Rank #55 of 158 matched modelsNo conditions reportedModel released Feb 17, 2026Source: epoch.ai (opens in a new tab)
  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    29.9%
    Rank #25 of 26 matched modelsHigh · mini-swe-agentModel released Feb 17, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,523
    Rank #46 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    87.4%
    Rank #64 of 160 matched models32K budgetRun date Feb 20, 2026Source: 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-4-6_high
      83.3%
      HighRun date Jul 13, 2026Source: epoch.ai (opens in a new tab)
    • Listed as claude-sonnet-4-6_medium
      83.3%
      MediumRun date Jul 13, 2026Source: epoch.ai (opens in a new tab)
    • Listed as claude-sonnet-4-6_max
      78.8%
      MaxRun date Aug 6, 2026Source: epoch.ai (opens in a new tab)
  • SimpleQA VerifiedKnowledge · Epoch AI
    35.5%
    Rank #57 of 86 matched modelsHighRun 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-sonnet-4-6_max
      32.8%
      MaxRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)
  • SWE-bench VerifiedHistory · Epoch AI
    75.2%
    Rank #14 of 32 matched modelsNo conditions reportedRun date Feb 21, 2026Source: epoch.ai (opens in a new tab)

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

Not evaluated: Humanity's Last Exam, FrontierMath Tiers 1–3 (v2), Terminal-Bench 4.1, CursorBench, 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
$0.56
Est. per 1M tokens
94% 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 94% of Claude Sonnet 4.6 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-4-6
    $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
  • Amazon Bedrockanthropic.claude-sonnet-4-6
    $3.30 input per 1M tokens$16.50 output per 1M tokens$0.33 cache read per 1M tokens$4.13 cache write per 1M tokens1M tokens of context
  • Vertexclaude-sonnet-4-6@default
    $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
  • Vertex (Anthropic)claude-sonnet-4-6@default
    $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
Show 3 more providersShow fewer providers
  • Azureclaude-sonnet-4-6
    $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
  • OpenRouteranthropic/claude-sonnet-4.6
    $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-4.6
    $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
1M tokens
Max output
128K tokens
Input
Text, Image, PDF
Output
Text
Knowledge cutoff
Aug 31, 2025
Release date
Feb 17, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Claude Sonnet 4.6 most in this period, by tokens. Hidden accounts are never listed.

  1. 1曹亚文@bobcyw2.2Btokens$1Kest. cost6active days$1K est. cost · 6 active days
  2. 2Milad Safdari@Eulex0x1.6Btokens$770est. cost13active days$770 est. cost · 13 active days
  3. 3Koala@koalaauto624Mtokens$331est. cost6active days$331 est. cost · 6 active days
  4. 4YeonGyu-Kim@code-yeongyu163Mtokens$196est. cost5active days$196 est. cost · 5 active days
  5. 5LJM@lee98www148.9Mtokens$57est. cost5active days$57 est. cost · 5 active days
  6. 6JB Jeon@PepperJeon99.6Mtokens$55est. cost7active days$55 est. cost · 7 active days
  7. 7Kaan Aricioglu@kaanarici92.1Mtokens$56est. cost12active days$56 est. cost · 12 active days
  8. 8Jelloeater@Jelloeater73.4Mtokens$229est. cost14active days$229 est. cost · 14 active days
  9. 9Daniel@daniel-diao69Mtokens$34est. cost3active days$34 est. cost · 3 active days
  10. 10mikedoesgithub@mikedoesgithub34.4Mtokens$25est. cost2active days$25 est. cost · 2 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% adoption558active 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