This model was retired on 2027-02-10. The pricing below is the last-known rate, kept for migration reference.
Claude Sonnet 4.6Deprecated
VisionTool useReasoningPrompt cachingStructured output
Context
1M
Max output
128K
Serving providers
8
Cheapest input
$3.00 /1M
Prices are on-demand list rates. 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
44 t/s
tokens / second
Time to first token
1.93s
latency
Headline indices
Intelligence Index
48.4
of 100
Coding Index
63.0
of 100
Agentic Index
42.1
of 100
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 | 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 | 74% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| Mlcr Overall | 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 | 47% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 53% | reasoning: adaptive | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 71% | reasoning: adaptive | — | |||||||||||||||||
| τ-bench Banking | 34% | reasoning: adaptive | — | |||||||||||||||||
| τ²-bench | 80% | default | — | |||||||||||||||||
| ||||||||||||||||||||
Pricing by serving provider
last-known · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Databricks | $3.00 | $15.00 | 1 | ||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||
| Anthropic | $3.00 | $15.00 | 1 | ||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||
| Amazon Bedrock | $3.00 | $15.00 | 1 | ||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||
| Azure | $3.00 | $15.00 | 1 | ||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||
| Vertex AI | $3.00 | $15.00 | 1 | ||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||
| DeepInfra | $3.00 | $15.00 | 1 | ||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||
| Snowflake | $3.00 | $15.00 | 1 | ||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||
| OpenRouter | $3.00 | $15.00 | 1 | ||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$1,800
estimated / month
Model IDs
copy the exact identifier for your platformdatabricks/databricks-claude-sonnet-4-6claude-sonnet-4-6anthropic.claude-sonnet-4-6azure_ai/claude-sonnet-4-6vertex_ai/claude-sonnet-4-6deepinfra/anthropic/claude-sonnet-4-6snowflake/claude-sonnet-4-6anthropic/claude-sonnet-4.6
Frequently asked questions
Claude Sonnet 4.6 pricing, context and availabilityIs Claude Sonnet 4.6 still available?
Claude Sonnet 4.6 was retired on 2027-02-10. The pricing on this page is the last-known rate, kept for migration reference.
How much did Claude Sonnet 4.6 cost?
Claude Sonnet 4.6's last-known pricing, before it was retired on 2027-02-10, was $3.00 per 1M input tokens and $15.00 per 1M output tokens.
What was the context window of Claude Sonnet 4.6?
Claude Sonnet 4.6 had a 1M token context window and could return up to 128K output tokens.
What could Claude Sonnet 4.6 do?
Claude Sonnet 4.6 supported image input (vision), tool use, reasoning, prompt caching and structured output.
Other Anthropic models
compare pricing across the Anthropic lineup Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI