# DeepSeek R1 Distill Llama 70B API prices

DeepSeek R1 Distill Llama 70B (deepseek-thinking) — 131k context, 131k max output.
7 metered per-token offers from 7 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Helicone | $0.03 | $0.13 | — | 128k |
| FastRouter | $0.03 | $0.14 | — | 131k |
| Alibaba (China) | $0.287 | $0.861 | — | 33k |
| Kilo Gateway | $0.8 | $0.8 | — | 8k |
| NovitaAI | $0.8 | $0.8 | — | 8k |
| OpenRouter | $0.8 | $0.8 | — | 8k |
| DigitalOcean | $0.99 | $0.99 | — | 33k |

## Summary

- Cheapest input: $0.03 per 1M tokens (Helicone)
- Cheapest output: $0.13 per 1M tokens (Helicone)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-01-23
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/deepseek-r1-distill-llama-70b/
Full dataset: https://llmprice.gitlab.io/data/catalog.json