Appearance
Claude
Claude Max Pool — 0.24x of official Anthropic pricing. Supports claude-fable-5, claude-opus-4.6/4.7/4.8, claude-sonnet-5, claude-sonnet-4.6, and claude-haiku-4.5. Quality and behavior are identical to official Claude Max.
Claude via Kiro — 0.048x of official Anthropic pricing during testing. Partial capacity. Supports all models above except claude-fable-5. Kiro routes may have some system prompt contamination that can affect model quality.
Official Anthropic pricing for reference. Per 1M tokens, USD.
| Model | Cache Read | 5m Cache Write | 1h Cache Write | Input | Output |
|---|---|---|---|---|---|
| claude-fable-5 | $1.00 | $12.50 | $20.00 | $10.00 | $50.00 |
| claude-opus-4.6 / 4.7 / 4.8 | $0.50 | $6.25 | $10.00 | $5.00 | $25.00 |
| claude-sonnet-5 | $0.20 | $2.50 | $4.00 | $2.00 | $10.00 |
| claude-sonnet-4.6 | $0.30 | $3.75 | $6.00 | $3.00 | $15.00 |
| claude-haiku-4.5 | $0.10 | $1.25 | $2.00 | $1.00 | $5.00 |
Fable 5 leaves Claude Pro/Max subscriptions on July 12.
Sonnet 5 intro pricing ends Aug 31, then $3 input / $15 output. CE will adjust accordingly.
Sonnet 5 consumes much more tokens per task. Consider Opus 4.8 for better cost efficiency.
Opus 4.6 and Sonnet 4.6 are better suited for writing and conversation tasks.