Pricingby GlyphSonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
Ways to buy 11
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API · cached $0.3 | $3 | $15 | $3 / $15List price | $0.3 | List price |
 AWS Bedrockglobal · cached $0.3 | $3 | $15 | $3 / $15Same as list | $0.3 | Same as list |
global · cached $0.3 | $3 | $15 | $3 / $15Same as list | $0.3 | Same as list |
| Claude Platform on AWS Default region · cached $0.3 | $3 | $15 | $3 / $15Same as list | $0.3 | Same as list |
From the platform pricing page | $3 | $15 | $3 / $15Same as list | n/a | Same as list |
global · cached $0.3 | $3 | $15 | $3 / $15Same as list | $0.3 | Same as list |
| AWS Bedrock eu-west-1 · cached $0.33 | $3.3 | $16.5 | $3.3 / $16.5+10% vs list | $0.33 | +10% vs list |
| AWS Bedrock us · cached $0.33 | $3.3 | $16.5 | $3.3 / $16.5+10% vs list | $0.33 | +10% vs list |
europe · cached $0.33 | $3.3 | $16.5 | $3.3 / $16.5+10% vs list | $0.33 | +10% vs list |
us-east5 · cached $0.33 | $3.3 | $16.5 | $3.3 / $16.5+10% vs list | $0.33 | +10% vs list |
From the platform pricing page | $3.6 | $18 | $3.6 / $18+20% vs list | n/a | +20% vs list |
USD per 1M tokens; batch $1.5 in, $7.5 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $600.00 direct.
Helicone$600.00+0%
Kong AI Gateway$600.00+0%
LiteLLM$600.00+0%
Neon AI Gateway$600.00+0%
Vercel AI Gateway$600.00+0%
Cloudflare AI Gateway$630.00+5%
Requesty$630.00+5%
Eden AI$633.00+5.5%
OpenRouter$633.00+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
Anthropic · 1M | $2 | $10 | $2 / $10 | $4 | 1M | Lab list price | · | Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. |
Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · | Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. |
Anthropic · 1M | $10 | $50 | $10 / $50 | $20 | 1M | Lab list price | · | Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual... |
OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · | GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. |
Google · 1MCheapest: $2 on Google Gemini API (flex) | $2 | $10 | $2 / $10 | $4 | 1M | $2 on Google Gemini API (flex) | · | Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. |
OpenAI · 1.05MCheapest: $4 on OpenAI (flex) | $4 | $20 | $4 / $20100% | $8 | 1.05M | $4 on OpenAI (flex) | 100% | GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. |
Qwen (Alibaba) · 1M | $2 | $6 | $2 / $6 | $3 | 1M | Lab list price | · | Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. |
About Claude Sonnet 4.6
Takes text, image, files in and returns text. First listed Feb 19, 2026. Up to 128K output tokens. Blended price $6 per 1M tokens at 3 input to 1 output. Overall score 1 on leadersboard.fru.dev (rank 44). Model id claude-sonnet-4-6.
Price history
List price since Feb 19, 2026, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Questions
How much does Claude Sonnet 4.6 cost?
$3 per million input tokens and $15 per million output tokens, with cached input at $0.3, or $1.5 and $7.5 through the Batch API.
What is the context window of Claude Sonnet 4.6?
1M tokens, with up to 128K tokens of output.
Where is Claude Sonnet 4.6 cheapest?
Of 11 routes tracked, AWS Bedrock is cheapest at $3 input and $15 output per million tokens.