| Model | Base tokens | Prompt caching | |||
|---|---|---|---|---|---|
| Name | Input | Output | |||
Claude Fable 5.2For demanding reasoning and long-horizon agentic work | $8 / | $40 / MTok | $10 / MTok | $16 / MTok | / MTok |
Claude Opus 5.5For long-running agentic coding and knowledge work | $4 / MTok | $20 / MTok | $5 / MTok | $8 / MTok | / MTok |
Claude Sonnet 5.5The best combination of speed and intelligence | $2 / MTok | $10 / MTok | $2.50 / MTok | $4 / MTok | / MTok |
Claude Haiku 5.5For high-volume, latency-sensitive tasks such as classification, extraction, and routing | $0.10 / MTokfor prompts up to 100,000 tokens | $0.50 / MTok | $0.125 / MTok | $0.20 / MTok | $0.01 / MTok |
$0.50 / MTokfor prompts over 100,000 tokens | $2.50 / MTok | $0.625 / MTok | $1 / MTok | $0.05 / MTok | |
$8 / MTok | $40 / MTok | $10 / MTok | $16 / MTok | / MTok | |
$10 / MTok | $50 / MTok | $12.50 / MTok | $20 / MTok | / MTok | |
$10 / MTok | $50 / MTok | $12.50 / MTok | $20 / MTok | / MTok | |
$10 / MTok | $50 / MTok | $12.50 / MTok | $20 / MTok | $1 / MTok | |
$10 / MTok | $50 / MTok | $12.50 / MTok | $20 / MTok | $1 / MTok | |
$5 / MTok | $25 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | |
$5 / MTok | $25 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | |
$5 / MTok | $25 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | |
$5 / MTok | $25 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | |
$5 / MTok | $25 / MTok | $6.25 / MTok | $10 / MTok | $0.50 / MTok | |
Claude Opus 4.1 | $15 / MTok | $75 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok |
Claude Opus 4 | $15 / MTok | $75 / MTok | $18.75 / MTok | $30 / MTok | $1.50 / MTok |
/ MTok | / MTok | $2.50 / MTok | $4 / MTok | $0.20 / MTok | |
$3 / MTok | $15 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | |
$3 / MTok | $15 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok | |
Claude Sonnet 4 | $3 / MTok | $15 / MTok | $3.75 / MTok | $6 / MTok | $0.30 / MTok |
$1 / MTok | $5 / MTok | $1.25 / MTok | $2 / MTok | $0.10 / MTok |
For Claude 4.6 and later models, using inference_geo: "us" applies a 1.1x pricing multiplier. inference_geo: "global" (default) uses standard pricing. See Data residency for details.
For Claude 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads.
Fast mode provides significantly faster output for Claude Fable 5.2, Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8 at premium pricing.
| Model | Input | Output |
|---|---|---|
| Claude Fable 5.2 | $16 USD / MTok | $80 USD / MTok |
| Claude Mythos 5.2 | $16 USD / MTok | $80 USD / MTok |
| Claude Opus 5.5 | $8 USD / MTok | $40 USD / MTok |
| Claude Opus 5 / Claude Opus 4.8 | $10 USD / MTok | $50 USD / MTok |