Large coding-reasoning model for agentic software tasks and RL search
Ornith 1.0 35B by deepreinforce is currently listed from a single provider. Its reference price is $0 per 1M tokens. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 262,000 tokens, with an output limit of 100,000 tokens. It supports reasoning and tool use. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| InferX Ornith-1.0-35B-FP8 | Gateway | Free | — | — | 262,000 | 100,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 / 1 providers expose no reasoning control (reasoning_options: []).
This model is $0 across all listed channels (InferX).
Price history accumulates from each data sync; currently only 1 sample(s) (2026-10-11). Each future sync adds a point, and once accumulated a line is drawn here.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 75.6 | percent resolved | Source ↗ |
| SWE-Bench Pro | — | 50.4 | percent resolved | Source ↗ |
| SWE-Bench Multilingual | — | 69.3 | percent resolved | Source ↗ |
| Terminal-Bench 2.1 | variant: Terminus-2 | 64.2 | percent | Source ↗ |
| Terminal-Bench 2.1 | variant: Claude Code | 62.8 | percent | Source ↗ |
| NL2Repo | — | 34.6 | percent | Source ↗ |
| Claw-eval | — | 69.8 | percent | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.