Pass IndexThe State of AISign in

Claude Sonnet 4.5

Claude Sonnet 4.5 is the newest model in the Sonnet series, offering improvements and updates over Sonnet 4.

text + image + file → text · made by Anthropic

$3→$15per Mtok in / out
Anthropic · 13 sellers

Sold by 35 ways

SellerLaneRate
AWS Bedrock cloudbatch$1.5per Mtok in$7.5per Mtok outaws.amazon.com · read 2026-08-24
AWS Bedrock 0 ways$1.5per Mtok in$7.5per Mtok out
AWS Bedrock cloudnot on the seller's list todaybatch cross-region$1.5per Mtok in$7.5per Mtok outaws.amazon.com · read 2026-08-24
Anthropic apibatch$1.5per Mtok in$7.5per Mtok outplatform.claude.com · read 2026-08-24
Google Vertex AI 0 ways$1.5per Mtok in$7.5per Mtok out$0.15per Mtok cached$1.88per Mtok cache write
Google Vertex AI cloudnot on the seller's list todaybatch$1.5per Mtok in$7.5per Mtok out$0.15per Mtok cached$1.88per Mtok cache writecloud.google.com · read 2026-08-24
AWS Bedrock cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeaws.amazon.com · read 2026-08-24
AWS Bedrock 0 ways$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache write
AWS Bedrock cloudnot on the seller's list todaycross-region$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeaws.amazon.com · read 2026-08-24
Anthropic apistandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeplatform.claude.com · read 2026-08-24
Databricks cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writemodels.dev · read 2026-09-16
DigitalOcean cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writemodels.dev · read 2026-09-16
Google Vertex AI cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writecloud.google.com · read 2026-08-24
Microsoft Azure AI cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writemodels.dev · read 2026-09-16
Snowflake Cortex cloudstandard$3per Mtok in$15per Mtok out$0.3per Mtok cachedraw.githubusercontent.com · read 2026-09-16
AWS Bedrock cloudlong-context$7.2per Mtok in$27per Mtok out$0.72per Mtok cachedraw.githubusercontent.com · read 2026-09-16
Nous Research 2 ways$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache write
Nous Research aggregatorbatch$1.5per Mtok in$7.5per Mtok out$0.15per Mtok cached$1.88per Mtok cache writeinference-api.nousresearch.com · read 2026-09-12
Nous Research aggregatorstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeinference-api.nousresearch.com · read 2026-09-12
OpenRouter 4 ways$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache write
OpenRouter aggregatorbatch$1.5per Mtok in$7.5per Mtok out$0.15per Mtok cached$1.88per Mtok cache writeopenrouter.ai · read 2026-08-24
OpenRouter aggregatorstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeopenrouter.ai · read 2026-08-24
OpenRouter aggregatoramazon-bedrock/eu-west-1$3.3per Mtok in$16.5per Mtok out$0.33per Mtok cached$4.12per Mtok cache writeopenrouter.ai · read 2026-08-25
OpenRouter aggregatorgoogle-vertex/us-east5$3.3per Mtok in$16.5per Mtok out$0.33per Mtok cached$4.12per Mtok cache writeopenrouter.ai · read 2026-08-25
Requesty 3 ways$2.97per Mtok in$14.85per Mtok out$0.27per Mtok cached
Requesty aggregatornot on the seller's list todaybedrock eu-central-1$2.97per Mtok in$14.85per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todaybedrock eu-north-1$2.97per Mtok in$14.85per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todaybedrock eu-west-1$2.97per Mtok in$14.85per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todaybedrock eu-west-3$2.97per Mtok in$14.85per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todaybedrock us-east-1$2.97per Mtok in$14.85per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todaybedrock us-east-2$2.97per Mtok in$14.85per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todaybedrock us-west-2$2.97per Mtok in$14.85per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todayvertex europe-west1$2.97per Mtok in$14.85per Mtok out$0.3per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todayvertex us-east5$2.97per Mtok in$14.85per Mtok out$0.3per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatoranthropic$3per Mtok in$15per Mtok out$0.3per Mtok cachedrouter.requesty.ai · read 2026-08-28
Requesty aggregatorbedrock$3.3per Mtok in$16.5per Mtok out$0.3per Mtok cachedrouter.requesty.ai · read 2026-08-31
Requesty aggregatorvertex$3.3per Mtok in$16.5per Mtok out$0.33per Mtok cachedrouter.requesty.ai · read 2026-09-15
ElectronHub aggregatorstandard$3per Mtok in$15per Mtok outapi.electronhub.ai · read 2026-09-16
GitHub Copilot 0 ways$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache write
GitHub Copilot aggregatornot on the seller's list todaystandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writemodels.dev · read 2026-09-04
Vercel AI Gateway aggregatorstandard$3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeai-gateway.vercel.sh · read 2026-08-25
Venice AI aggregatorstandard$3.75per Mtok in$18.75per Mtok out$0.38per Mtok cached$4.69per Mtok cache writemodels.dev · read 2026-09-16

Measured 71 standings

PlaceBoardMetricScore
2ndof 109Berkeley Function-Calling Leaderboard (BFCL) V4Overall Acc (fc)73.24
3rdof 22Cybench — Epoch AIUnguided % Solved0.6
3rdof 81Forecastbench — Epoch AIOverall score61.9
4thof 11Gdpval — Epoch AIWin Rate (%)0.425
4thof 20Os world — Epoch AIScore62.9
5thof 25SWE-Bench Pro (Public Dataset)Resolve Rate43.6
6thof 25AgentBench Leaderboard (new)Success Rate (pass@1) AVG58.9
6thof 10Humanity's Last ExamAccuracy (%)13.7
6thof 108Math level 5 — Epoch AImean_score97.734
7thof 25AgentBench Leaderboard (new)Success Rate (pass@1) AVG (thinking)58.3
7thof 41Deepresearchbench — Epoch AIAverage score0.526
7thof 8τ²-bench Leaderboard (Overall: Retail · Airline · Telecom)Pass^176.4
10thof 18Algotune — Epoch AIScore1.52
10thof 13Rli — Epoch AIScore2.08
11thof 262MMLU-ProOverall (accuracy) (thinking)0.874
11thof 47SWE-bench Verified (default "Bash Only" view, agent = mini-SWE-agent)% Resolved71.4
11thof 47SWE-bench Verified (default "Bash Only" view, agent = mini-SWE-agent)% Resolved (high)71.4
14thof 50Metr time horizons — Epoch AIaverage_score0.674
15thof 180SWE-bench Verified (Bash Only toggle off — all agents)% Resolved74.8
16thof 38Gso — Epoch AIScore OPT@10.147
18thof 28τ³-Banking LeaderboardPass^125.3
20thof 38Vpct — Epoch AICorrect0.398
21stof 21Ebr bench — Epoch AImean_score2.381
23rdof 46Enigma eval — Epoch AIAccuracy5.997
24thof 34LMArena · SearchScore (Elo)1158
25thof 51Humanity's Last Exam (Epoch AI replication)Accuracy13.72
25thof 110OSWorld-Verified Results (All)Success Rate (Avg±Std)62.9
25thof 35Swe bench verified — Epoch AImean_score71.281
35thof 92Design Arena · asciiart (models)Elo1223
35thof 60Vending bench 2 — Epoch AIScore3838.74
37thof 64Proofbench — Epoch AIAccuracy19
38thof 123Lmca — Epoch AIScore38.76
41stof 72Frontiermath tier 4 — Epoch AImean_score4.167
43rdof 102Simplebench — Epoch AIScore (AVG@5)0.543
45thof 63Design Arena · mobileapps (agents)Elo1165
49thof 101FrontierMath (Tiers 1-3)mean_score15.225
51stof 161Dtbench — Epoch AIAccuracy83.2
53rdof 64Design Arena · fullstack (agents)Elo1059
55thof 62Design Arena · webapps (agents)Elo1075
58thof 402LMArena · TextScore (Elo) (high)1456
59thof 62Frontiermath tier 4 v2 — Epoch AImean_score2.439
59thof 80Simpleqa verified — Epoch AImean_score30.7
61stof 112Ale bench — Epoch AIPerformance796.15
71stof 106Frontiermath tiers 1 3 v2 — Epoch AImean_score23.86
71stof 127Mystery game puzzles — Epoch AImean_score17
72ndof 109Design Arena · svg (models)Elo1140
75thof 147Design Arena · 3d (models)Elo1186
76thof 156Design Arena · codecategories (models)Elo1198
76thof 170Weirdml — Epoch AIAccuracy47.71
77thof 105Vectara Hallucination LeaderboardHallucination Rate12
78thof 121Webdev arena — Epoch AIArena Score1391
79thof 128LMArena · WebDevScore (Elo) (high)1393
79thof 202Terminalbench — Epoch AIAccuracy mean0.465
80thof 143Artificial Analysis · Agentic IndexIndex17.5
80thof 162Design Arena · website (models)Elo1202
81stof 155Design Arena · gamedev (models)Elo1189
81stof 150Design Arena · uicomponent (models)Elo1188
85thof 184Artificial Analysis · Coding IndexIndex52.1
88thof 152Design Arena · dataviz (models)Elo1183
93rdof 168Scicode — Epoch AIScore44.676
111thof 177Critpt — Epoch AIAccuracy1.143
111thof 313GPQA Diamondmean_score82.323
113thof 290OTIS Mock AIME 2024-2025mean_score77.778
115thof 227Arc agi 2 — Epoch AIScore13.61
124thof 244Arc agi — Epoch AIScore63.67
130thof 222Chess puzzles — Epoch AImean_score12
135thof 216ARC-AGI-2 (Public Eval)Score (%)3.75
153rdof 232ARC-AGI-2 (Semi-Private)Score (%)3.75
163rdof 205ARC-AGI-1 (Public Eval)Score (%)35.38
183rdof 230ARC-AGI-1 (Semi-Private)Score (%)25.5
271stof 656Epoch capabilities index — Epoch AIECI Score146.84

About

Claude Sonnet 4.5 — a text model from Anthropic, sold by 13 companies from $3 in and $15 out per million tokens, placed 2nd of 109 on Berkeley Function-Calling Leaderboard (BFCL) V4.

It takes text, images and files and returns text, with a context window of 1,000,000 tokens. It was published in September 2025, trained on material up to July 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Thirteen companies sell it. The cheapest is $3 in and $15 out per million tokens at AWS Bedrock. Beside the standard rate there are batch, separately routed and regional lanes. It has been measured on 69 boards, and stands best at 2nd of 109 on Berkeley Function-Calling Leaderboard (BFCL) V4.

Every current figure

Maker
Anthropic
Register
model
Takes
text + image + file
Returns
text
Context
1,000,000 tokens
Longest answer
200,000 tokens
Published
September 2025
Knowledge to
July 2025
Licence
not read
Sellers
13
Price
$3 in and $15 out per million tokens — AWS Bedrock
Boards
69
Best place
2nd of 109 — Berkeley Function-Calling Leaderboard (BFCL) V4

Known as 26 names

Claude Sonnet 4.5 (2025-09-29)Claude Sonnet 4.5 Thinking (2025-09-29)Claude-Sonnet-4-5-20250929 (FC)Claude Sonnet 4.5 (59k thinking)Claude 4.5 Sonnetclaude-sonnet-4-5-searchClaude-4.5-Sonnet(Thinking)claude-sonnet-4-5-20250929claude-4-5-SonnetClaude 4.5 Sonnet highanthropic.claude-sonnet-4-5-20250929-v1:0anthropic/claude-sonnet-4.5anthropic/claude-sonnet-4.5:batchanthropic/claude-sonnet-4-5bedrock/claude-sonnet-4-5bedrock/claude-sonnet-4-5@eu-central-1bedrock/claude-sonnet-4-5@eu-north-1bedrock/claude-sonnet-4-5@eu-west-1bedrock/claude-sonnet-4-5@eu-west-3bedrock/claude-sonnet-4-5@us-east-1bedrock/claude-sonnet-4-5@us-east-2bedrock/claude-sonnet-4-5@us-west-2vertex/claude-sonnet-4-5vertex/claude-sonnet-4-5@europe-west1vertex/claude-sonnet-4-5@us-east5Anthropic: Claude Sonnet 4.5 (batch)