Fireworks AI Fine-tuning vs Tinker

Fireworks AI Fine-tuning

SFT, DPO, ORPO and RFT as managed jobs, plus a serverless Training API that is generally available. Tuned LoRAs only deploy to on-demand GPUs at $8 an hour and up, never to serverless.

Tinker

Full control of the training loop with the GPUs abstracted away, plus recipes for SFT, DPO, RL and distillation. LoRA only; no full-parameter training.

Fireworks AI Fine-tuning

1. Add a payment method before the first job; without one the account has 0 training GPUs and 10 requests a minute
2. Check firectl model get -a fireworks <MODEL-ID> for Tunable: true before uploading a dataset
3. Pass your own supervisedFineTuningJobId on create, so after a timeout you can GET the job by that name instead of guessing whether it started
4. Deploy the LoRA to an on-demand deployment with a BF16 shape if several adapters will share it, and delete the deployment when evaluation ends
5. Download with firectl model download and keep the exact base model; the adapter alone won't run

Tinker

1. Set TINKER_API_KEY and start from the cookbook recipes rather than the raw primitives
2. Read the 'Avoid Client-Side Timeouts and Retries' guide before wrapping sampling calls in your own retries; the SDK already retries sampling with stable request IDs
3. Save intermediate checkpoints with a TTL between 1 hour and 10 years; storage bills at $0.10 a GB-month until they expire
4. Read models.json for current prices before a run; sampling tokens cost more than training tokens on the open models
5. Check the model deprecations page before pinning a base model; 18 were retired on 2026-06-12