10 open-source models across 6 families, served through one OpenAI-compatible API.
High-throughput agentic work with 1M context
Tool-heavy coding at 3B-active cost
Dense agentic coding with thinking control
Gemma 4 quality at 4B-active speed
Multimodal long-context work with thinking control
Top-ranked multilingual embeddings for search
o4-mini-class reasoning for tool-driven coding
Marathon coding agents with visual context
Low-latency reasoning on a tiny budget
Long-horizon engineering with planning depth
Use $25 free credits to compare models with your prompts, token sizes, latency targets, and cost assumptions before moving traffic.