Schematron V2 Small is 9.9× cheaper per million tokens (blended). Qwen3.8 27B has the larger context window (262,144 vs 128,000 tokens, 2.0×).
Schematron V2 Small vs Qwen3.8 27B
Live catalog fields. Best-in-row is highlighted.
Schematron V2 Smallopen
Inference Net · inference-net__schematron-v2-small
Qwen3.8 27Bopen
Qwen · qwen__qwen3.8-27b
Identity
| Field | inference-net__schematron-v2-small | qwen__qwen3.8-27b |
|---|---|---|
| Provider | Inference Net | Qwen |
| Slug | inference-net__schematron-v2-small | qwen__qwen3.8-27b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | inference-net/schematron-v2-llama-3.2-3b | Qwen/Qwen3.8-27B |
Quality
| Field | inference-net__schematron-v2-small | qwen__qwen3.8-27b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | inference-net__schematron-v2-small | qwen__qwen3.8-27b |
|---|---|---|
| Input $ / 1M tokens | $0.05 | $0.21 |
| Cached input $ / 1M | $0.05 | $0.15 |
| Output $ / 1M tokens | $0.23 | $2.55 |
Context
| Field | inference-net__schematron-v2-small | qwen__qwen3.8-27b |
|---|---|---|
| Max context tokens | 128,000 | 262,144 |
| Max output tokens | 4,096 | 131,072 |
Modalities
| Field | inference-net__schematron-v2-small | qwen__qwen3.8-27b |
|---|---|---|
| Input | text | text, image, video |
| Output | text | text |