Anthropic › Claude Sonnet 4.6 › Pricing
Claude Sonnet 4.6 pricing
API list price by Anthropic · same on Amazon Bedrock, Azure, Claude Platform on AWS · checked Oct 23, 2026
$3 / $15per 1M tokens in / out
$0.30cache read · −90%
$1.50 / $7.50batch · −50%
#59on OpenRouter by tokens · 281.2B / week
Price sheetper 1M tokens
| Input | $3 | list |
| Output | $15 | |
| Cache read | $0.30 | −90% vs input |
| Cache write · 5 min | $3.75 | +25% vs input |
| Cache write · 1 h | $6 | +100% vs input |
| Batch input | $1.50 | −50% |
| Batch output | $7.50 | −50% |
| Context · max output | 1M · 128K | tokens |
Where to buy6 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Amazon Bedrock | $3 | $15 | 1M |
| Anthropiclab | $3 | $15 | 1M |
| Azure | $3 | $15 | 1M |
| Claude Platform on AWS | $3 | $15 | 1M |
| DeepInfra | $3 | $15 | — |
| $3 | $15 | 1M |
In Anthropic's line-upper 1M in / out
| Claude Haiku 5.5 | $0.10 / $0.50 | −97% |
| Claude Sonnet 5.5 | $2 / $10 | −33% |
| Claude Sonnet 4.6 | $3 / $15 | this model |
| Claude Opus 5.5 | $4 / $20 | +33% |
| Claude Fable 5.1 | $10 / $50 | 3.3× |
| Claude Mythos 5 | $10 / $50 | 3.3× |
| Claude Mythos 5.1 | $10 / $50 | 3.3× |
Cheaper for the same workvs Sonnet 4.6
| Claude Sonnet 5.5 max | -33% | score ×2.3 | $5.46 |
| Gemini 4 Argon high | -33% | score ×2.1 | $1.99 |
| GPT-6.1 Sol max | -33% | score ×2.1 | $0.72 |
| Muse Spark 1.3 max | -67% | score +95% | $1.60 |
| GPT-6 Sol max | -33% | score +93% | $1.04 |
Pricing questions
How much does Claude Sonnet 4.6 cost?›
$3 per 1M input tokens and $15 per 1M output tokens on Anthropic's API and Amazon Bedrock, Azure, Claude Platform on AWS. Cached input is $0.30. Batch requests cost $1.50 / $7.50.
Is Claude Sonnet 4.6 free to use?›
There is no free API tier.
How much does prompt caching save?›
Cache reads cost $0.30 per 1M, 90% below the input price. Writing to the cache costs $3.75 per 1M (5m TTL).
What is a cheaper alternative to Claude Sonnet 4.6?›
Claude Sonnet 5.5 at max effort costs -33% per task with a score ×2.3 on Humanity's Last Exam.