Claude Sonnet 5 (Low)
Context 1M tokens
Top 5 cheapest providers (Adjusted $/task)
The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.
Within the active global provider, residency and confidentiality filters.
| # | Provider | Price channel | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Azurevia OpenRouter — Price via OpenRouter: OpenRouter's price for Azure's endpoint (https://openrouter.ai/anthropic/claude-sonnet-5/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Azure's endpoint (https://openrouter.ai/anthropic/claude-sonnet-5/providers), collected 2026-11-03. | $2.00 | $10.00 | |
| 2 | Googlevia OpenRouter — Price via OpenRouter: OpenRouter's price for Google's endpoint (https://openrouter.ai/anthropic/claude-sonnet-5/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Google's endpoint (https://openrouter.ai/anthropic/claude-sonnet-5/providers), collected 2026-11-03. | $2.00 | $10.00 | |
| 3 | Amazon Bedrockvia OpenRouter — Price via OpenRouter: OpenRouter's price for Amazon Bedrock's endpoint (https://openrouter.ai/anthropic/claude-sonnet-5/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Amazon Bedrock's endpoint (https://openrouter.ai/anthropic/claude-sonnet-5/providers), collected 2026-11-03. | $2.00 | $10.00 | |
| 4 | Google Vertex AIdirect — Direct price: Google Vertex AI's own price list (https://cloud.google.com/vertex-ai/generative-ai/pricing), collected 2026-11-03. | direct — Direct price: Google Vertex AI's own price list (https://cloud.google.com/vertex-ai/generative-ai/pricing), collected 2026-11-03. | $2.00 | $10.00 | |
| 5 | AWS Bedrockdirect — Direct price: AWS Bedrock's own price list (https://aws.amazon.com/bedrock/pricing/), collected 2026-11-03. | direct — Direct price: AWS Bedrock's own price list (https://aws.amazon.com/bedrock/pricing/), collected 2026-11-03. | $2.20 | $11.00 |
Composite
5 of 7 inputs · 4 from the model family6 radar axes: DesignArena's two boards share one57.0
AA Coding v4.x —Coding Agent v1.4 —AA Intelligence (est.) 12.3AA Agentic —Epoch ECI 157.0Software ECI 155.2DesignArena 1228/1249
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
19 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
6 of 19 values are Anthropic's own claims (†), not independent measurements; a matching independent result replaces a claim as soon as one exists.
- Epoch ECI · attached
- Software ECI · attached
- DesignArena Web Apps (agentic) · attached
- DesignArena Full-Stack · attached
Agentic
AA-Briefcase48927 Elo
AA-Briefcase published 2026-09-10 → · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.
GDPval-AA v2601,145 Elo
GDPval-AA v2 v2 → · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench v4.0 (AA)562.5%
Terminal-Bench v4.0 (AA) v4.0 → · Published board — Tests terminal-based work on the 66-task release using mini-SWE-agent v2.4.6.
Coding
SciCode (AA subproblems) v1.0.15450.1%
SciCode (AA subproblems) v1.0.1 → · Published board — Tests scientific Python programming with scientist-annotated background information.
CursorBench 4.0 (Cursor)developer's claim24.1%† self-reported by the developer
CursorBench 4.0 (Cursor) v4.0 → · Published board — Agent evaluation on ambiguous, multi-file tasks drawn from real Cursor sessions.
DeepSWE (Datacurve, via Epoch AI)630.5%
DeepSWE (Datacurve, via Epoch AI) published 2026-09-15 → · mini-SWE-agent — Pass rate of coding agents on original, long-horizon software engineering tasks, run by Datacurve with the mini-swe-agent harness.
FrontierCode 1.1 Main (Cognition)developer's claim28.7%† self-reported by the developer
FrontierCode 1.1 Main (Cognition) v1.1 → · Claude Code — Whether a maintainer would merge the agent's pull request, on tasks crafted by open-source maintainers and graded with tests, rubrics and verifiers.
FrontierCode 1.1 Extended (Cognition)developer's claim44.5%† self-reported by the developer
FrontierCode 1.1 Extended (Cognition) v1.1 → · Claude Code — Whether a maintainer would merge the agent's pull request, on the full 150-task FrontierCode set crafted by open-source maintainers and graded with tests, rubrics and verifiers.
Efficiency
CursorBench 4.0 cost per task (Cursor)developer's claim$1.39† self-reported by the developer
CursorBench 4.0 cost per task (Cursor) v4.0 → · Published board — Cursor's published USD cost per task for each CursorBench 4.0 model-effort configuration.
FrontierCode 1.1 Main cost per rollout (Cognition)developer's claim$2.39† self-reported by the developer
FrontierCode 1.1 Main cost per rollout (Cognition) v1.1 → · Claude Code — Cognition's published mean USD spend per rollout for each FrontierCode 1.1 Main model and reasoning effort.
FrontierCode 1.1 Extended cost per rollout (Cognition)developer's claim$2.03† self-reported by the developer
FrontierCode 1.1 Extended cost per rollout (Cognition) v1.1 → · Claude Code — Cognition's published mean USD spend per rollout for each FrontierCode 1.1 Extended model and reasoning effort.
Knowledge
Humanity's Last Exam (AA text-only)7221.9%
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index72-8.23
AA-Omniscience Index published 2026-09-10 → · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Long-context
GDP.pdf (AA)429.4%
GDP.pdf (AA) published 2026-09-10 → · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.16167.3%
AA-LCR v1.1 v1.1 → · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Safety/Alignment
BullshitBench V1 (clear pushback)9265.5%
BullshitBench V1 (clear pushback) published 2026-09-10 → · Published board — Whether a model rejects the broken premise of 55 deliberately nonsensical prompts (V1 question set) instead of answering them confidently.
BullshitBench V2 (clear pushback)9980.0%
BullshitBench V2 (clear pushback) published 2026-09-10 → · Published board — Whether a model rejects the broken premise of 100 deliberately nonsensical prompts (V2 question set) instead of answering them confidently.
Science
CritPt (AA)764.6%
CritPt (AA) published 2026-09-10 → · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
Tool-use
AutomationBench-AA v1.0.64319.9%
AutomationBench-AA v1.0.6 → · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
Unusual results
2 threshold-crossing signals flagged · 13 eligible benchmark families
How flags are calculated
Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.
- unusually weak DeepSWE (Datacurve, via Epoch AI) published 2026-09-15
Why
Observed: 0.30512 fractionPeer mean 0.56136 · peer sd 0.161 · n 63 · families 21Directed z -1.592 · baseline z 0.387 · gap -1.978 · profile n 120.30512 fractionmeasuredobserved 2026-09-15epoch.ai ↗Evidence
Axis: DeepSWE (Datacurve, via Epoch AI) · published 2026-09-15 · mini-SWE-agentExact value:0.3051224944320713fractionEvaluation harness: mini-SWE-agentObserved: 2026-09-15T09:05:24Z · publication date: not recordedObservation id:public:eb3bf56a46512ff02158c73f - unusually strong BullshitBench V2 (clear pushback) published 2026-09-10
Why
Observed: 0.8 fractionPeer mean 0.3888 · peer sd 0.23889 · n 75 · families 60Directed z 1.721 · baseline z 0.111 · gap 1.611 · profile n 120.8 fractionmeasuredobserved 2026-09-15raw.githubusercontent.com ↗Evidence
Axis: BullshitBench V2 (clear pushback) · published 2026-09-10 · Published boardExact value:0.8fractionObserved: 2026-09-15T01:07:23.764154+00:00 · publication date: not recordedObservation id:public:8d7dac6e6ac868bc672d0a91
Missing coverage · 300 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.
Variants / reasoning settings
Artificial Analysis snapshot 2026-11-03 · Intelligence Index v5.0 (est. = estimated from v4, not measured) · Coding Index v4.x frozen 2026-10-27 · Data: Artificial Analysis · Data: Epoch AI (CC BY)
| Variant | AA Coding | AA Intelligence |
|---|---|---|
| Claude Sonnet 5 (Max) | 71.5 | 28.0est. |
| Claude Sonnet 5 (Non-reasoning, High) | 66.4 | 11.9est. |
| Claude Sonnet 5 (High) | — | 20.1est. |
| Claude Sonnet 5 (Low) | — | 12.3est. |
| Claude Sonnet 5 (Medium) | — | 17.6est. |
| Claude Sonnet 5 (Xhigh) | — | 24.0est. |
SUBSCRIPTION PLAN
GitHub Copilot
Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.
Token offers by platform · 11 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
11 offers within the active global filters, 3 more outside them; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.
OpenRouter (8)
Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/anthropic/claude-sonnet-5/providers, collected 2026-11-03.
| Azure | globalazure/global | $2.00 raw in $/1M | $10.00 raw out $/1M | |
| globalgoogle-vertex/global | $2.00 raw in $/1M | $10.00 raw out $/1M | ||
| Amazon Bedrock | globalamazon-bedrock/global | $2.00 raw in $/1M | $10.00 raw out $/1M | |
| Amazon Bedrock | euamazon-bedrock/eu-west-1EU | $2.20 raw in $/1M | $11.00 raw out $/1M | |
| Azure | globalazure/us | $2.20 raw in $/1M | $11.00 raw out $/1M | |
| globalgoogle-vertex/us | $2.20 raw in $/1M | $11.00 raw out $/1M | ||
| eugoogle-vertex/europeEU | $2.20 raw in $/1M | $11.00 raw out $/1M | ||
| Amazon Bedrock | globalamazon-bedrock/us-east-1 | $2.20 raw in $/1M | $11.00 raw out $/1M |
Google Vertex AI (2)
Direct prices from Google Vertex AI's own price list. Source: cloud.google.com/vertex-ai/generative-ai/pricing, collected 2026-11-03.
| Google Vertex AI | global | $2.00 raw in $/1M | $10.00 raw out $/1M | |
| Google Vertex AI | euEU | $2.20 raw in $/1M | $11.00 raw out $/1M |
AWS Bedrock (1)
Direct prices from AWS Bedrock's own price list. Source: aws.amazon.com/bedrock/pricing/, collected 2026-11-03.
| AWS Bedrock | eu-central-1 (EU cross-region inference profile)EU | $2.20 raw in $/1M | $11.00 raw out $/1M |