InferenceNet
Inference providerUS Westprices checked Oct 23, 06:00 UTC
InferenceNet serves 8 models at a verified price. On the 8 it shares with other hosts, it is the cheapest on 1 and charges a median 103% above the cheapest.
Models served87 with open weights
Cheapest input, per M$0.10GLM-5.3-Flash
Uptime, last 24 h99.9%average of its 7 OpenRouter endpoints
Sign-upCard requiredno free credits stated
| Model | Precision | Context | Tools | Input | Output | Cache |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | fp8 | 1.04M | ✓ | $0.30 | $1.00 | $0.007 |
| MiMo-V2.6-Flash | not checked yet | 1.05M | — | $0.12 | $0.28 | $0.11 |
| DeepSeek V4.1 Flashreprices often | fp8 | 1.04M | ✓ | $0.30 | $1.00 | $0.007 |
| GLM-5.3-Flash | fp4 | 1M | ✓ | $0.10 | $0.45 | $0.03 |
| GLM-5.3reprices often | fp4 | 1M | ✓ | $0.90 | $3.00 | $0.15 |
| Kimi K3reprices often | fp4 | 1M | ✓ | $3.00 | $15.00 | $0.30 |
| GLM 5.2 | not stated by the host | 1M | — | $1.30 | $4.40 | $0.20 |
| MiniMax M3.1 Flashcheapest | fp4 | 1M | ✓ | $0.10 | $0.50 | $0.005 |
8 of 8 models · prices per million tokens · precision and context: read at InferenceNet's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as InferenceNet declares them to OpenRouter
| Condition | What it says | Source |
|---|---|---|
| Sign-up | Card required | docs.inference.net |
| Free credits | None stated | — |
| Where data goes | Optional US-only inference endpoint | docs.inference.net |
| Headquarters region | US West | — |
| Price list | Where its per-token prices are published | inference.net |
| API documentation | Its own docs | docs.inference.net |
| Status page | Outages and incidents, as InferenceNet reports them | status.inference.net |
| Terms of service | Its terms | inference.net |
Links checked Oct 8.