Ways to buy 11
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 Anthropic APIThe lab's own API · cached $0.5 | $5 | $25 | $5 / $25List price | $0.5 | List price |
 AWS BedrockDefault region · cached $0.5 | $5 | $25 | $5 / $25Same as list | $0.5 | Same as list |
 Azure AI Foundryglobal · cached $0.5 | $5 | $25 | $5 / $25Same as list | $0.5 | Same as list |
| Claude Platform on AWS Default region · cached $0.5 | $5 | $25 | $5 / $25Same as list | $0.5 | Same as list |
 Google Vertex AIglobal · cached $0.5 | $5 | $25 | $5 / $25Same as list | $0.5 | Same as list |
| AWS Bedrock eu-west-1 · cached $0.55 | $5.5 | $27.5 | $5.5 / $27.5+10% vs list | $0.55 | +10% vs list |
| AWS Bedrock us · cached $0.55 | $5.5 | $27.5 | $5.5 / $27.5+10% vs list | $0.55 | +10% vs list |
| Azure AI Foundry us · cached $0.55 | $5.5 | $27.5 | $5.5 / $27.5+10% vs list | $0.55 | +10% vs list |
| Google Vertex AI europe · cached $0.55 | $5.5 | $27.5 | $5.5 / $27.5+10% vs list | $0.55 | +10% vs list |
| Google Vertex AI us · cached $0.55 | $5.5 | $27.5 | $5.5 / $27.5+10% vs list | $0.55 | +10% vs list |
| Anthropic fast · cached $1 | $10 | $50 | $10 / $50+100% vs list | $1 | +100% vs list |
USD per 1M tokens; batch $2.5 in, $12.5 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $1,000 direct.
Helicone$1,000+0%
Kong AI Gateway$1,000+0%
LiteLLM$1,000+0%
Vercel AI Gateway$1,000+0%
Cloudflare AI Gateway$1,050+5%
Requesty$1,050+5%
Eden AI$1,055+5.5%
OpenRouter$1,055+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| Claude Opus 5.5 Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · |
| Claude Fable 5.1 Anthropic · 1M | $10 | $50 | $10 / $50 | $20 | 1M | Lab list price | · |
| Claude Opus 5 Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · |
| Claude Sonnet 5 Anthropic · 1M | $2 | $10 | $2 / $10 | $4 | 1M | Lab list price | · |
 GPT-6 AstraOpenAI · 1.05MCheapest: $10 on OpenAI (flex) | $10 | $50 | $10 / $50 | $20 | 1.05M | $10 on OpenAI (flex) | · |
| GPT-5.5 OpenAI · 1.05MCheapest: $5.63 on OpenAI (flex) | $5 | $30 | $5 / $30 | $11.3 | 1.05M | $5.63 on OpenAI (flex) | · |
 Gemini 3.1 Pro PreviewGoogle · 1MCheapest: $2.25 on Google Vertex AI (global-flex) | $2 | $12 | $2 / $12 | $4.5 | 1M | $2.25 on Google Vertex AI (global-flex) | · |
| GPT-5.6 Terra OpenAI · 1.05MCheapest: $2.25 on OpenAI (flex) | $2 | $12 | $2 / $12 | $4.5 | 1.05M | $2.25 on OpenAI (flex) | · |
About Claude Opus 4.8
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.
Takes text, image, files in and returns text. First listed May 29, 2026. Up to 128K output tokens. Blended price $10 per 1M tokens at 3 input to 1 output. Overall score 3 on leadersboard.fru.dev (rank 34). Model id claude-opus-4-8.
Price history
List price since May 29, 2026, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Questions
How much does Claude Opus 4.8 cost?
$5 per million input tokens and $25 per million output tokens, with cached input at $0.5, or $2.5 and $12.5 through the Batch API.
What is the context window of Claude Opus 4.8?
1M tokens, with up to 128K tokens of output.
Where is Claude Opus 4.8 cheapest?
Of 11 routes tracked, AWS Bedrock is cheapest at $5 input and $25 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.