Pricing / Trajectory SFT / DPO / GRPO distillation
Cheapest price per million train tokens for Trajectory SFT / DPO / GRPO distillation
Unit: usd_per_million_train_tokens only — nothing converted or blended. min sourced training-token SKU among candidates; not chat inference input; not quality-adjusted. Updated 2026-10-28 (newest asOf / re-check on this page).
Only 1 candidate has a matching Train $/1M; nothing was compared, so pickIsPriceWinner is null.
| # | Provider | SKU | Train $/1M | Source | asOf / re-checked | First seen / last changed |
|---|---|---|---|---|---|---|
| 1 | Fireworks AI | Managed training LoRA SFT up to 16B | $0.5 | page | 2026-10-28 / 2026-10-28 | 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/preference-dpo-sft-trace-distillation · Agents: GET /api/quote?jtbd=preference-dpo-sft-trace-distillation