DeepInfra
Pay-per-token inference API for open-weight models including DeepSeek, Kimi, GLM, Qwen, Llama and gpt-oss.
Among the hosts reselling open-weight models, DeepInfra lists the lowest per-token price on several shared models: DeepSeek-V4-Flash-0731 is $0.06 / $0.18 against $0.14 / $0.28 on Nebius, and gpt-oss-120b is $0.037 / $0.17. A cheaper Flex tier exists for some models. That suits cost-sensitive workloads without compliance requirements, because although inputs are stated not to be stored to disk, no DPA, GDPR terms or EU region are documented.
- Headquarters
- 🇺🇸 United States
- Parent jurisdiction
- 🇺🇸 United States
- EU self-serve plan
- No / not documented
- GDPR DPA
- No / not documented
- Billing
- payg
- Open source
- No
- Website
- deepinfra.com
- Source last checked
- 2026-10-06
- Pricing evidence
- Published rates
Pricing
Calculated from the listed vendor rates; exclusions still apply. How to read these estimates.
| Model | Input / 1M tokens | Output / 1M tokens | Cached / 1M tokens | Context | Details |
|---|---|---|---|---|---|
| Kimi-K3 | $2.85 | $14.25 | $0.285 | 1024k | frontieropen weights |
| DeepSeek-V4-Pro | $1.3 | $2.6 | $0.1 | 1024k | frontieropen weights |
| GLM-5.3 | $0.563 | $2.5 | $0.125 | 1048k | frontieropen weights |
| DeepSeek-V4-Flash-0731 | $0.06 | $0.18 | $0.015 | 1024k | midopen weights |
| gpt-oss-120b | $0.037 | $0.17 | — | 131k | midopen weights |
Standard-tier prices; a cheaper Flex tier exists for some models (e.g. GLM-5.3 $0.45/$2.00). Data-privacy docs state inputs are not stored to disk, but no DPA, GDPR terms or EU region are documented.
Managed alternatives
At 500M input tokens / month, 50M output tokens / month. Adjust usage and requirements.
DeepInfra · gpt-oss-120b: $324/yr estimated.
No cheaper managed estimate matches your filters. Adjust your usage or compare with your actual contract bill.
The price difference leaves out migration costs, operating costs and any features you’d need to replace. We compare the selected model or the cheapest listed model in the chosen capability tier. Sharing a tier does not mean equal quality.
Self-hosted options
Operating cost is not estimated. These options are not counted as savings against managed services.
Want a European-owned provider? See European alternatives to DeepInfra among european LLM APIs.
Found a wrong rate or plan restriction? Report a correction with a current source.