API pricing per million tokens
- Input
- $5
- per 1M, list
- Output
- $25
- per 1M tokens
- Cached input
- $0.5
- batch $2.5 / $12.5
- Context
- 1M
- 128K max output
Where to buy it (6)
AWS Bedrockdefault region$5 / $25cached $0.5
Azure AI Foundryglobal$5 / $25cached $0.5
Google Vertex AIglobal$5 / $25cached $0.5
Anthropic (list)the lab's own API$5 / $25cached $0.5
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%
Databricks Mosaic AI$1,000+0%
Hugging Face Inference$1,000+0%
Cloudflare AI Gateway$1,050+5%
Requesty$1,050+5%
Eden AI$1,055+5.5%
OpenRouter$1,055+5.5%
Snowflake Cortex AI$1,200+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
GPT-6 AstraOpenAI · 1.05M$10 / $50in / out per 1M$10$50$11.05MSep 4, 2026
Gemini 3.1 Pro PreviewGoogle Gemini API · 1M$2 / $12in / out per 1M$2$12$0.21MFeb 19, 2026
About Claude Opus 4.6
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.
Takes text, image, files in and returns text. First listed Feb 15, 2026. Blended price $10 per 1M tokens at 3 input to 1 output. Overall score 23 on leadersboard.fru.dev (rank 6).
Questions
How much does Claude Opus 4.6 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 4.6?
1M tokens, with up to 128K tokens of output.
Where is Claude Opus 4.6 cheapest?
Of 6 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.