Pricing / Hosted open-weight model inference
Cheapest price per million input tokens for Hosted open-weight model inference
Unit: usd_per_million_input_tokens only — nothing converted or blended. min sourced input SKU among candidates; not quality-adjusted. Updated 2026-10-27 (newest asOf / re-check on this page).
Pick is not a price winner. Cheapest sourced input $/1M among candidates is chutes at 0.039. The pick has no priceSortEligible input row.
| # | Provider | SKU | Input $/1M | Source | asOf / re-checked | First seen / last changed |
|---|---|---|---|---|---|---|
| 1 | Chutes | Qwen3.8-27B (Qwen/Qwen3.8-27B-TEE) | $0.039 | page | 2026-10-27 / 2026-10-27 | 2026-10-03 / 2026-10-19 |
| 2 | Groq | openai/gpt-oss-20b | $0.075 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 3 | DeepInfra | Llama-3.3-70B-Instruct-Turbo | $0.1 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 4 | FriendliAI | gemma-4-31B-it | $0.14 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 5 | Together AI | GLM-5.3-Flash | $0.15 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 6 | SambaNova | gpt-oss-120b | $0.22 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 7 | Cerebras | gpt-oss-120b | $0.35 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
| 8 | Moonshot (Kimi) | kimi-k2.6 | $0.95 | page | 2026-10-20 / 2026-10-27 | 2026-10-03 / no change recorded |
| 9 | OpenRouter | anthropic/claude-sonnet-5.5 | $2 | page | 2026-10-03 / 2026-10-27 | 2026-10-03 / no change recorded |
Price only: not quality-, latency- or limit-adjusted. The Depot Pick is editorial and is not chosen by price. Brief: /jtbds/open-model-inference · Agents: GET /api/quote?jtbd=open-model-inference