Inference.net Models — Pricing & Benchmarks
2 models available
Last refreshed 2026-10-19. Next refresh: weekly.
Inference.net hosts 2 AI models in this catalog. The lowest listed input price is Schematron V2 Turbo at $0.03/1M input tokens. LLM Reference compares these models across all 112 providers.
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| Schematron V2 Turbo | $0.03 | $0.15 | 125K | |
| Schematron V2 Small | $0.05 | $0.23 | 125K |
Where else to run this
Schematron V2 Small on Inference.net
Provider setup and pricing
Schematron V2 Turbo on Inference.net
Provider setup and pricing
Schematron V2 Small on Vercel AI Gateway
Alternative host
Schematron V2 Turbo on Vercel AI Gateway
Alternative host
Fireworks AI model catalog
226 tracked models
NVIDIA NIM model catalog
143 tracked models
Pricing Overview
Cheapest$0.03/1M
Most expensive$0.05/1M