Pyyan / Compare / Gemini Decision 1 vs Claude Fable 5.1
Gemini Decision 1 vs Claude Fable 5.1
2 of 5Language Models · verified 12 Nov 2026
Gemini Decision 1Googlecurrent Claude Fable 5.1Anthropiccurrent | Specification | Gemini Decision 1 | Claude Fable 5.1 |
|---|
| Summary | Scores up to 1,000 closed questions in one pass, at $0.10 per million input tokens and $0 for output. | Same price as Fable 5, and cache reads cost a quarter of what they did. |
|---|
| Context | 256K | 1M |
|---|
| Input ($/Mtok) | $0.1 | $10 |
|---|
| Output ($/Mtok) | $0 | $50 |
|---|
| Licence | Proprietary | Proprietary |
|---|
| Max output | 0 (no output tokens) | 128K |
|---|
| Parameters | Not published | Not published |
|---|
| Released | 11 Nov 2026 | 1 Sep 2026 |
|---|
| Model ID | gemini-decision-1 | claude-fable-5-1 |
|---|
| Category | Language Models | Language Models |
|---|
| Official | Google ↗ | — |
|---|
Highlighted rows are where these differ.
Gemini Decision 1
- One multimodal input, text, images, audio, video or PDFs, up to 256K tokens, and up to 1,000 independent questions
- Returns probabilities and a confidence score, with zero output tokens billed, in 150 to 250 milliseconds end to end, by Google's figures
- Three question types: noul for yes or no, choice for 2 to 255 options, and score for an ordered rubric
- Priced at $0.10 per million input tokens. The shared input is billed once per request, and Google quotes no output charge
Best for fast yes or no, multiple choice and rubric scores inside an agent.
Full spec sheet →
Claude Fable 5.1
- Matches or beats Fable 5 at low and medium effort, and pulls clear at high effort
- Cache reads cut to 25% of the old price, so re-reading a long context got much cheaper
- Identical model to Mythos 5.1 underneath; the difference is the safeguards
Best for coding and long-running work.
Full spec sheet →