DeepInfra pricing: per-token model rates
Checked Nov 10, 2026 on DeepInfra’s official pages (sources below). Prices change often: confirm with the provider before you buy.
DeepInfra serves open models behind an OpenAI-compatible API. Language models are billed per token; some other models are billed by execution time. There are no long-term contracts.
Figures below are quoted from deepinfra.com/pricing as read on Nov 10, 2026. Prices change: confirm on DeepInfra's page before you buy.
Selected language models (per 1M tokens)
- DeepSeek-V4-Flash
- Input$0.09
- Cached input$0.018
- Output$0.18
- Qwen3.8-Flash
- Input$0.113
- Cached input$0.0141
- Output$0.382
- gemma-4-31B-it-Ultra
- Input$0.27
- Cached input–
- Output$0.76
- DeepSeek-V4-Pro
- Input$1.30
- Cached input$0.10
- Output$2.60
- GLM-5.3 (list price)
- Input$0.90
- Cached input$0.20
- Output$4.00
GLM-5.3 was shown at 38% off its list price ($0.5625 input, $2.50 output) on Nov 10. Discounts change; check the page.
DeepInfra pricing FAQ
How does DeepInfra charge?
Per token for language models, by execution time for some other models, with no long-term contract.
Where do these DeepInfra prices come from?
DeepInfra's own pricing page (https://deepinfra.com/pricing), read on Nov 10, 2026. We do not estimate bills or add up costs across providers.
Sources (official pages, read Nov 10, 2026)
Spot something out of date? Email hello@youraitools.co and we’ll fix it.