DeepInfra
US · serverless
Consistently among the cheapest hosts for popular open-weight models.
OpenAI-compatible
- Category
- serverless
- Free tier
- No
- OpenAI API
- Compatible
- Adds on top
- None - systematically undercuts list price
Margin over the underlying model price
What DeepInfra charges
Live prices for widely-hosted open-weight models, sampled from the shared catalogue. Compare the same row against other hosts on each model page.
| Model | Input / 1M | Output / 1M | Context | Throughput |
|---|---|---|---|---|
| Ling 3.0 Flash VL | $0.060 | $0.180 | 131K | - |
| Granite 4.2 8B | $0.060 | $0.250 | 131K | - |
| DeepSeek V4 Flash 0731 | $0.060 | $0.180 | 1.0M | - |
| Ling 3.0 Flash | $0.060 | $0.180 | 131K | - |
| GLM 5.3 Flash | $0.075 | $0.250 | 1.0M | - |
| Nemotron 3.5 Lightning | $0.080 | $0.200 | 262K | - |
| Hy3 | $0.105 | $0.435 | 262K | - |
| DeepSeek V4.1 Flash | $0.200 | $0.600 | 1.0M | - |
| DeepSeek V4 Flash Vision Exp | $0.216 | $0.647 | 1.0M | - |
| Muse Glimmer 30B | $0.300 | $1.20 | 131K | - |
| Inkling Small | $0.450 | $1.20 | 524K | - |
| Inkling | $0.950 | $4.05 | 524K | - |
| GLM 5.3 | $1.20 | $4.00 | 1.0M | - |
| DeepSeek V4 Pro 0813 | $1.30 | $2.60 | 1.0M | - |
| Qwen3.8 2.4T A95B | $2.00 | $6.00 | 262K | - |
| Kimi K3 | $2.85 | $14.25 | 1.0M | - |
DeepInfra alternatives
Other services in the same category. These are genuine substitutes - services in a different category solve a different problem.
Frequently asked
Is DeepInfra OpenAI-compatible?
Yes. DeepInfra accepts the OpenAI chat-completions request shape, so most SDKs work by changing the base URL and API key.
Does DeepInfra have a free tier?
Not currently. DeepInfra bills from the first request.
How does DeepInfra charge?
Per token, pay as you go Margin over the underlying model price: none - systematically undercuts list price.