# DeepSeek R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a language model from DeepSeek with a 128K-token context window. Provider list price is $2 per million input tokens and $2 per million output; on Allocate you pay $2.14 and $2.14 with the 7% transaction fee. The weights are open under MIT, so you can fine-tune it and own the result.

## Pricing

| | Provider list | On Allocate |
| --- | --- | --- |
| Input, per M tokens | $2 | $2.14 |
| Output, per M tokens | $2 | $2.14 |

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

## Facts

| Field | Value |
| --- | --- |
| Lab | DeepSeek |
| Modality | Language |
| Context window | 128K tokens |
| License | MIT |
| Open weights | Yes |
| Fine-tunable | Yes, on your data |
| Catalog id | deepseek/deepseek-r1-distill-llama-70b |

## What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $2 + 350 × $2 = $3,100 a month. Billed on Allocate it is $3,317 with the 7% transaction fee.

## Common questions

### How much does DeepSeek R1 Distill Llama 70B cost per million tokens?

Provider list price is $2 per million input tokens and $2 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $2.14 in and $2.14 out.

### What context window does DeepSeek R1 Distill Llama 70B have?

131,072 tokens (128K). At roughly 0.75 words per token, that is about 98k words of English text per request.

### Can I fine-tune DeepSeek R1 Distill Llama 70B?

Yes. DeepSeek R1 Distill Llama 70B is an open-weights model under the MIT license. The license is permissive, so the fine-tuned weights are yours to use commercially. On Allocate the trained weights stay inside your boundary and belong to you.

### How do I call DeepSeek R1 Distill Llama 70B on Allocate?

Send deepseek/deepseek-r1-distill-llama-70b in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.

---

[HTML page](https://allocate.network/models/deepseek-deepseek-r1-distill-llama-70b) · [Machine-readable catalog](https://allocate.network/catalog.json)