A side-by-side comparison of Claude Fable 5 and Claude Opus 4.8: input/output pricing, capabilities and available endpoints, served live from 370.AI. Both are reachable with the same API key.
| Item | Claude Fable 5 | Claude Opus 4.8 |
|---|---|---|
| Input (per 1M tokens) | $10 | $4.5 |
| Output (per 1M tokens) | $50 | $22.5 |
| Cache read (per 1M tokens) | $1 | $0.45 |
| Cache write 5m (per 1M tokens) | $12.5 | $5.625 |
| Item | Claude Fable 5 | Claude Opus 4.8 |
|---|---|---|
| Context window | 1,000,000 | 1,000,000 |
| Max output | 64,000 | 128,000 |
| Item | Claude Fable 5 | Claude Opus 4.8 |
|---|---|---|
| function_calling | Yes | Yes |
| prompt_caching | Yes | Yes |
| vision | Yes | Yes |
On input, Claude Opus 4.8 is cheaper ($10 vs $4.5 per 1M tokens). On output, Claude Opus 4.8 is cheaper ($50 vs $22.5 per 1M tokens). All prices are per million tokens in USD.
both support function_calling, prompt_caching, vision.
Yes. Both are available on 370.AI through one API key and the same OpenAI-compatible endpoint — switching means changing the model field from "claude-fable-5" to "claude-opus-4-8", nothing else.
Both are available on 370.AI under one API key — switching between them means changing the model field and nothing else, so you can use each where it fits rather than picking one.