Scheduled for retirement on Feb 10, 2027. Still available at the prices below until then.
Context
1M
Max output
128K
Serving providers
9
Cheapest input
$3.00 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: ARC Prize and Artificial AnalysisSpeed & latency
Output speed
46 t/s
tokens / second
Time to first token
1.02s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aa Analyst Agent | 0.2 | reasoning: adaptive | — | |||||||||||||||||
| APEX Agents | 28% | reasoning: adaptive | — | |||||||||||||||||
| ARC-AGI-2 | 60% | high | $2.70 | |||||||||||||||||
| ||||||||||||||||||||
| Automation Bench | 0.2 | reasoning: adaptive | — | |||||||||||||||||
| CritPt | 3% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1374.3 | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 87% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| Harvey Lab | 0.9 | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 34% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 57% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| IT-Bench SRE | 40% | reasoning: adaptive | — | |||||||||||||||||
| Long-Context Reasoning | 80% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.2 | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| MMMU-Pro | 73% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | 12.2 | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.4 | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.5 | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCode | 50% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| Terminal Bench40 | 0.0 | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 53% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 71% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 34% | reasoning: adaptive | — | |||||||||||||||||
| τ²-bench | 80% | default | — | |||||||||||||||||
| ||||||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DatabricksCheapest | $3.00 | $15.00 | 1 | |||||||||||||||||||||
Standarddatabricks/databricks-claude-sonnet-4-6
| ||||||||||||||||||||||||
| Anthropic | $3.00 | $15.00 | 1 | |||||||||||||||||||||
Standardclaude-sonnet-4-6
| ||||||||||||||||||||||||
| Azure | $3.00 | $15.00 | 1 | |||||||||||||||||||||
Standardazure_ai/claude-sonnet-4-6
| ||||||||||||||||||||||||
| Amazon Bedrock | $3.00 | $15.00 | 1 | |||||||||||||||||||||
Standardanthropic.claude-sonnet-4-6
| ||||||||||||||||||||||||
| DeepInfra | $3.00 | $15.00 | 1 | |||||||||||||||||||||
Standarddeepinfra/anthropic/claude-sonnet-4-6
| ||||||||||||||||||||||||
| OpenRouter | $3.00 | $15.00 | 1 | |||||||||||||||||||||
Standardanthropic/claude-sonnet-4.6
| ||||||||||||||||||||||||
| Snowflake | $3.00 | $15.00 | 1 | |||||||||||||||||||||
Standardsnowflake/claude-sonnet-4-6
| ||||||||||||||||||||||||
| VercelVercel reseller quote | $3.00 | $15.00 | 1 | |||||||||||||||||||||
Standardanthropic/claude-sonnet-4.6
| ||||||||||||||||||||||||
| Anthropic is dearest at $3.00 / $15.00 | ||||||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$1,800
estimated / month
Model IDs
copy the exact identifier for your platformanthropic/claude-sonnet-4.6:batchdatabricks/databricks-claude-sonnet-4-6azure_ai/claude-sonnet-4-6anthropic.claude-sonnet-4-6snowflake/claude-sonnet-4-6anthropic/claude-sonnet-4.6deepinfra/anthropic/claude-sonnet-4-6anthropic/claude-sonnet-4.6claude-sonnet-4-6vertex_ai/claude-sonnet-4-6
Frequently asked questions
Claude Sonnet 4.6 pricing, context and availabilityIs Claude Sonnet 4.6 still available?
Yes. Claude Sonnet 4.6 is scheduled for retirement on 2027-02-10.
How much does Claude Sonnet 4.6 cost?
Claude Sonnet 4.6 costs $3.00 per 1M input tokens from Databricks, and $15.00 per 1M output tokens from Anthropic. Across 9 serving providers, input prices range from $3.00 to $3.00 per 1M tokens.
What is the context window of Claude Sonnet 4.6?
Claude Sonnet 4.6 accepts up to 1M tokens of context and can return up to 128K output tokens.
Which providers serve Claude Sonnet 4.6?
Claude Sonnet 4.6 is available from 9 serving providers, each with its own pricing and model ID. Databricks is currently the cheapest.
What can Claude Sonnet 4.6 do?
Claude Sonnet 4.6 supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other Anthropic models
compare pricing across the Anthropic lineup Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI