Ornith 1.5 35B live on RunInfra: 262K context, ~$0.02/1M effective input with cache
alejandroll10 · x · 2026-08-22
RunInfra announced Ornith 1.5 35B (ornith-ai/Ornith-1.5-35B-A3B) is live on its model API platform.
Pricing (pay per token): $0.10/1M input, $0.01/1M cached input, $0.40/1M output. With a claimed 90% cache hit rate, effective input runs $0.02/1M; 1M in + 1M out with a warm cache costs about $0.42.
Measured performance: 216 output tok/s (model only), fleet median 195 tok/s over the last 24h, 167ms time to first token. Context window is 262,144 tokens with matching max output. Supports tool calling, JSON mode, and streaming; FP8 precision across weights, activations, and KV cache; accepts text and image input via OpenAI-compatible chat completions. Prompts are never stored or used for training.
More from Models
- Muse Spark Open runs locally on a Mac M3 Ultra via llama.cpp: frontier model on desktop — pcuenq · 2026-10-16
- OpenAI ships GPT-Live-1.1: new voices in six languages, fewer confirmations — OpenAI · 2026-10-16
- Muse Spark model appears on LMArena, testable in Battle and Agent modes — arena · 2026-10-16
- Running a multi-model UI design arena: Paseo orchestrates four design drafts per model — vista8 · 2026-10-16
- Ilya Sutskever questions Meta license clause taxing MaaS providers above $20M revenue — ilyasu · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16