Inference.net
- Models
- 2
- Hosted by a direct provider
- 0
Provider counts exclude gateways.
| Model | Compare | Type | Released | Context | Providers | Input $/1M | Output $/1M |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 (Inference.net) | Chat | 2026-10-17 | 262K | 0 +1 | via LLM Gateway $0.30 | via LLM Gateway $1.00 | |
| Llama 3.2 11B Instruct (Inference.net) | Chat | 2024-09-25 | 128K | 0 +1 | via LLM Gateway $0.07 | via LLM Gateway $0.33 |
Providers: direct count, then “+n” gateways. Prices are the range across comparable direct providers (gateways, subscription plans, deprecated endpoints and anything that is not a paid per-token price excluded); models only on gateways show the cheapest gateway list price. Non-token models show their native unit.