DeepSeek R1 Distill Llama 70B
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Cheapest input
$0.03
$/MTok · models.dev
Cheapest output
$0.13
$/MTok
Context
131K
tokens
Offers
5
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestdeepseek-r1-distill-llama-70b | Helicone | $0.03 | $0.13 | $0 | 128K |
| LiteLLMDeepSeek-R1-Distill-Llama-70B | — | $0.2 | $0.6 | $0.02 | — |
| models.devdeepseek-r1-distill-llama-70b | Alibaba / Qwen | $0.287 | $0.861 | $0 | 33K |
| models.devdeepseek-r1-distill-llama-70b | DigitalOcean | $0.99 | $0.99 | $0 | 131K |
| LiteLLMdeepseek-r1-distill-llama-70b | — | $0.99 | $0.99 | $0.099 | — |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2025-01Released: 2025-01-01Family: deepseek-thinking