Schematron V2 Turbo is 333.3× cheaper per million tokens (blended). Claude Fable 5 has the larger context window (1,000,000 vs 128,000 tokens, 7.8×). Schematron V2 Turbo is open-weights; the other is not.
Claude Fable 5 vs Schematron V2 Turbo
Live catalog fields. Best-in-row is highlighted.
Claude Fable 5
Anthropic · anthropic__claude-fable-5
Schematron V2 Turboopen
Inference Net · inference-net__schematron-v2-turbo
Identity
| Field | anthropic__claude-fable-5 | inference-net__schematron-v2-turbo |
|---|---|---|
| Provider | Anthropic | Inference Net |
| Slug | anthropic__claude-fable-5 | inference-net__schematron-v2-turbo |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | inference-net/schematron-v2-granite-4.0-h-micro |
Quality
| Field | anthropic__claude-fable-5 | inference-net__schematron-v2-turbo |
|---|---|---|
| Quality index (0–100) | 89.2 | — |
Cost
| Field | anthropic__claude-fable-5 | inference-net__schematron-v2-turbo |
|---|---|---|
| Input $ / 1M tokens | $10.00 | $0.03 |
| Cached input $ / 1M | $1.00 | $0.03 |
| Output $ / 1M tokens | $50.00 | $0.15 |
Context
| Field | anthropic__claude-fable-5 | inference-net__schematron-v2-turbo |
|---|---|---|
| Max context tokens | 1,000,000 | 128,000 |
| Max output tokens | 128,000 | 8,192 |
Modalities
| Field | anthropic__claude-fable-5 | inference-net__schematron-v2-turbo |
|---|---|---|
| Input | text, image, file | text |
| Output | text | text |