LLM inference API for consumer apps, from $0.07 per 1M input tokens
Inworld Inference is Inworld AI's OpenAI-compatible LLM inference API, launched to all developers on 14 October 2026. It serves open models consumer apps run on, such as Gemma 4, GLM 5.3 Flash, MiMo 2.6 Pro, DeepSeek V4.1 Flash and the Clef decision model, on Inworld's own fleet across the US, Europe, India and Asia Pacific, with cache-aware routing, serving tiers and dedicated deployments for custom weights. Pricing for open models starts at $0.07 per million input tokens and $0.34 per million output tokens for Gemma 4 26B.
For people
For agents