Loading…
Your privacy choices
Necessary storage keeps the site working. Analytics and advertising stay off unless you allow them. Cookie notice
Documentation for Tinker, a training API for fine-tuning open-weight language models: SDK reference, cookbook guides, recipes, and tutorials.
This data may be out of date
Last checked 10 Nov 2026, 09:01 UTC. A newer update is expected. Records released or published after this time are not shown.
Every model version this company develops, newest first; each links to its own model card.
Thinking Machines does not develop any model tracked here.
Offers this company serves as a provider, whoever developed the model. Each price uses the currency and billing unit shown with it.
1–5 of 5
| Model | Input, USD / 1M | Cached input, USD / 1M | Output, USD / 1M | Updated |
|---|---|---|---|---|
| Nemotron 3.5 Lightning 30B A3B (nvidia nemotron 3.5 lightning) | 0.18 | 0.04 | 0.50 | |
| Nemotron 3.5 Super VL (nemotron 3.5 super vl 120b a12b) | 0.57 | 0.11 | 1.44 | |
| Qwen3.5-35B-A3B-Base | 0.54 | 0.11 | 1.34 | |
| Qwen3.5 397B A17B | 1.65 | 0.33 | 7.50 | |
| Qwen3.5-9B-Base | 0.30 | 0.06 | 0.81 |