# DeepSeek R1 0528 API prices

DeepSeek R1 0528 (deepseek-thinking) — 164k context, 164k max output.
12 metered per-token offers from 13 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NanoGPT | $0.4 | $1.7 | $0.2 | 164k |
| Deep Infra | $0.5 | $2.15 | $0.35 | 164k |
| Meganova | $0.5 | $2.15 | — | 164k |
| OpenRouter | $0.5 | $2.15 | $0.35 | 164k |
| submodel | $0.5 | $2.15 | — | 75k |
| Alibaba (China) | $0.574 | $2.294 | — | 131k |
| Cortecs | $0.652 | $2.57 | $0.163 | 164k |
| TensorX | $0.66 | $2.6 | $0.165 | 164k |
| Jiekou.AI | $0.7 | $2.5 | — | 164k |
| Kilo Gateway | $0.7 | $2.5 | $0.35 | 164k |
| NovitaAI | $0.7 | $2.5 | $0.35 | 164k |
| Hugging Face | $3 | $5 | — | 164k |

## Summary

- Cheapest input: $0.4 per 1M tokens (NanoGPT)
- Cheapest output: $1.7 per 1M tokens (NanoGPT)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-05-28
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/deepseek-r1-0528/
Full dataset: https://llmprice.gitlab.io/data/catalog.json