Inference host prices
Open-weight models served by inference hosts, with each host's price per 1M tokens (input, output). One row per model, host and quantization.
Providers
| Providers | SKUs | Last verified | Source |
|---|---|---|---|
| baseten | 15 | 2026-10-23 17:00 UTC | www.baseten.co/pricing/ |
| cerebras | 2 | 2026-10-24 00:55 UTC | api.cerebras.ai/public/v1/models |
| groq | 6 | 2026-10-23 16:29 UTC | console.groq.com/docs/models |
| hf-router | 177 | 2026-10-24 00:55 UTC | router.huggingface.co/v1/models community cross-check |
| openrouter | 1143 | 2026-10-23 22:54 UTC | openrouter.ai/aion-labs/aion-2.0 community cross-check |
| sambanova | 6 | 2026-10-24 00:55 UTC | api.sambanova.ai/v1/models |
| together | 8 | 2026-10-24 01:11 UTC | www.together.ai/pricing |