Compare
Add up to four models. The bill starts at 1M input tokens, 1M output tokens, and 1,000 units.
Monthly bill
Token models use the token counts. Other models use units times the flat rate.
Lowest bill: tencent/Hy4-preview · $3.34
Add another
Search by name, then add up to four.
| Google: Gemini 3.8 Flash | tencent/Hy4-preview | |
|---|---|---|
| Provider | DeepInfra | |
| Modality | text, image, video, audio | text |
| Context | 1.0M | 1.0M |
| Input | $0.825/1M | $0.834/1M |
| Output | $4.125/1M | $2.501/1M |
| Cache read | $0.0825/1M | $0.042/1M |
| Cache write | $0.0417/1M | Not published— |
Tiers and extras
- Google: Gemini 3.8 Flash
- Web search: $0.014 per request; Image input: $0.825 per 1M tokens; Audio: $0.825 per 1M tokens; Audio cache: $0.0825 per 1M tokens; Reasoning: $4.125 per 1M tokens
- tencent/Hy4-preview
- —