All comparisons · Prices checked 2026-10-14
Claude Fable 5.1 (legacy) vs Claude Fable 5.2: API cost comparison
For a typical chatbot reply, Claude Fable 5.1 (legacy) costs $0.048 and Claude Fable 5.2 costs $0.039 per request: Claude Fable 5.2 is 20% cheaper. Claude Fable 5.2 is cheaper in every workload below.
API prices
| Claude Fable 5.1 (legacy) | Claude Fable 5.2 | |
|---|---|---|
| Maker | Anthropic | Anthropic |
| Input / 1M tokens | $10 | $8 |
| Output / 1M tokens | $50 | $40 |
| Output vs input price | +400% | +400% |
| Context window | 1M tokens | 1M tokens |
| Tokens for the same English text | ~138% of GPT's count (estimate) | ~138% of GPT's count (estimate) |
Capability
On the Epoch Capabilities Index, Claude Fable 5.1 (legacy) scores 167.1 and Claude Fable 5.2 173.5: Claude Fable 5.2 is 6.4 points higher, within the margin of error. See capability vs price for all models.
Capability scores: Epoch Capabilities Index by Epoch AI, used under CC BY 4.0.
Counting tokens for Claude? Use the Claude token counter: in our test Claude used 38% more tokens than GPT for the same English prompt (data).
Cost by workload
| Workload (per 1,000 requests) | Claude Fable 5.1 (legacy) | Claude Fable 5.2 | Cheaper |
|---|---|---|---|
| Chatbot reply short question plus some chat history · 1,500 in / 400 out | $48.30 | $38.64 | Claude Fable 5.2 20% cheaper |
| Document Q&A (RAG) retrieved passages plus a question · 8,000 in / 500 out | $145 | $116 | Claude Fable 5.2 20% cheaper |
| Coding agent step large working context, short edit · 25,000 in / 800 out | $400 | $320 | Claude Fable 5.2 20% cheaper |
| Summarize a long report long input, short summary · 20,000 in / 300 out | $297 | $237 | Claude Fable 5.2 20% cheaper |
| Write an article short brief, long draft · 800 in / 2,000 out | $149 | $119 | Claude Fable 5.2 20% cheaper |
Claude Fable 5.2 is cheaper on both input and output, so it costs less for every kind of request. It is 20% cheaper on input and 20% cheaper on output.
Monthly cost
| Monthly volume | Claude Fable 5.1 (legacy) | Claude Fable 5.2 |
|---|---|---|
| 10,000 chatbot replies / month | $483 | $386 |
| 100,000 chatbot replies / month | $4,830 | $3,864 |
| 1,000,000 chatbot replies / month | $48,300 | $38,640 |
Calculate your own
Enter your typical request size and volume.
Token counts are for English text measured with GPT's tokenizer; each model's own tokenizer difference is applied automatically.
Questions
Which is cheaper, Claude Fable 5.1 (legacy) or Claude Fable 5.2?
For a typical chatbot reply (1,500 input and 400 output tokens), Claude Fable 5.1 (legacy) costs $0.048 and Claude Fable 5.2 costs $0.039 per request, so Claude Fable 5.2 is 20% cheaper. Claude Fable 5.2 is cheaper in every workload below.
How much do Claude Fable 5.1 (legacy) and Claude Fable 5.2 cost per million tokens?
Claude Fable 5.1 (legacy) costs $10 per 1M input tokens and $50 per 1M output tokens. Claude Fable 5.2 costs $8 input and $40 output. Prices checked 2026-10-14.
Do both models count the same text as the same number of tokens?
No. Each model family has its own tokenizer, so the same text can be a different number of tokens. The costs on this page already include that difference (estimated from GPT's tokenizer).
Related comparisons
- GPT-6.2 Astra vs Claude Fable 5.2
- GPT-6 Astra (legacy) vs Claude Fable 5.2
- Gemini 4 Argon vs Claude Fable 5.2
- Claude Opus 5.5 vs Claude Fable 5.2
- GPT-6 Astra (legacy) vs Claude Fable 5.1 (legacy)
- Gemini 4 Argon vs Claude Fable 5.1 (legacy)
- Claude Opus 5.5 vs Claude Fable 5.1 (legacy)
Paste a real prompt to see its exact tokens and cost on Claude Fable 5.1 (legacy), Claude Fable 5.2 and 30+ other models.
Open the token counter →Standard API list prices, short-context tier, no caching or batch discounts. Prices change; check each provider's pricing page before large jobs.