## Service directory (1-1 of 1)

| id | Provider | Product | Free tier | Lowest paid price | Checked |
|---|---|---|---|---|---|
| together-ai | Together AI | Together AI serverless models | — | From $0.15 per 1M input tokens (e.g. GLM-5.3-Flash, $0.50 output) | 2026-10-23 [pricing page](https://www.together.ai/pricing) |

**Provider caveats**
- Together AI: Dedicated endpoints and GPU clusters are priced separately.

Categories: llm (1), ai_infra (1).

**Caveats (show these word for word)**
- Directory prices summarise each provider's pricing page on the date shown (checked_at), read automatically and pending human review. Check the page before relying on a price.

Confidence: medium.

Use estimate_cost or plan_stack for providers priced by the cost engine.