claude-fable-5 API — compare providers
The same model (claude-fable-5) is served by 3 providers at the same blended price — $60.0/1M whichever endpoint you pick. On quality, claude-fable-5 scores 1507 on the LMArena (Chatbot Arena) — identical whichever provider serves it, so decide on latency, terms and region.
Quality and intelligence scores are attached to the model itself — identical whichever provider serves it. Verified 2026-09-04.
| Rank | Provider | Input /1M | Output /1M | Blended /1M | Value (Elo/$) |
|---|---|---|---|---|---|
| 1 | Anthropic | $10 | $50 | $60 | 25 |
| 2 | Amazon Bedrock | $10 | $50 | $60 | 25 |
| 3 | $10 | $50 | $60 | 25 |
Value = model Elo ÷ blended price per 1M tokens. All providers charge the same here, so value per dollar is identical — pick on latency, terms and region.
Prices are per 1M tokens (USD). "Blended" = input + output, for coarse ranking. Same underlying model, 3 serving providers, identically priced across all of them. Context window: 200,000 tokens (64,000 max output) — see how it ranks in biggest context windows. See how this compares across the catalogue in same model, different price, or find the best quality per dollar in the value ranking.
Cost per 1,000 requests by workload
What each provider actually bills for a representative job, not just the sticker price.
| Provider | Chatbot 1000 in / 500 out | RAG / long context 8000 in / 500 out | Batch summarize 4000 in / 1000 out |
|---|---|---|---|
| Anthropic | $35.00 | $105.00 | $90.00 |
| Amazon Bedrock | $35.00 | $105.00 | $90.00 |
| $35.00 | $105.00 | $90.00 |
Estimate your own workload
Input tokens/request: Output tokens/request: Requests:
| Provider | Estimated cost (USD) |
|---|