Ornith-1.0-9B

Ornith AI released Ornith-1.0-9B, a 9-billion-parameter dense language model, on 2026-06-25, with a 262K context window and MIT license on HuggingFace. The model scores 43.1 on Terminal-Bench 2.1, 69.4 on SWE-bench Verified, and 82.5 on GPQA-Diamond, and is superseded by Ornith-1.5-9B.

Ornith-1.0-9B consumer ~9B Dense - the edge-deployable Ornith-1.0, released 2026-06-25 and superseded by Ornith-1.5-9B. 262K context, MIT-licensed on HuggingFace at ornith-ai/Ornith-1.0-9B GGUF quantizations . - Coding vendor self-reported : Terminal-Bench 2.1 43.1, SWE-bench Verified 69.4, SWE-bench Pro 42.9, NL2Repo 27.2. - Reasoning: HLE 16.8, GPQA-Diamond 82.5. - Agentic: MCP-Atlas 49.4, Toolathlon-Verified 33.4, ClawEval 63.1. Superseded by Ornith-1.5-9B TB-2.1 46.2, SWE-bench Verified 70.6 . Prefer 1.5 for new work. Runs on phones, laptops, and small GPUs via quantized builds. coding reasoning agentic - 9.0B - 262k - mit - 🇺🇸 USA - Jun 2026 Scores Coding 74 Reasoning 72 Tool calling 74 General 70 Or run it in the cloud No per-token API provider pricing tracked for Ornith-1.0-9B yet. For flagship list prices, see the calculator /calculator . PRICE HISTORY Inference cost over time Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API. Loading price history...