DeepSeek model
R1 Distill Llama 70B API cost calculator
R1 Distill Llama 70B costs $0.80 per 1M input tokens and $0.80 per 1M output tokens on the DeepSeek API, with a 8K-token context window. A typical request (2K input, 500 output tokens) costs $0.0020 — about $60.00/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on R1 Distill Llama 70B
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0006 | $0.64 |
| RAG query with context | 4,000 / 500 | $0.0036 | $3.60 |
| Document summarization | 20,000 / 1,000 | $0.02 | $16.80 |
| Agent coding session | 100,000 / 5,000 | $0.08 | $84.00 |
R1 Distill Llama 70B vs other DeepSeek models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| R1 Distill Llama 70B | $0.80 | $0.80 | 8K |
| DeepSeek V4.1 Flash | $0.15 | $0.60 | 1.0M |
| DeepSeek V4 Flash Vision Exp | $0.22 | $0.66 | 1.0M |
| DeepSeek V4 Pro 0813 | $0.58 | $1.74 | 1.0M |
| DeepSeek V4 Flash 0731 | $0.04 | $0.08 |
Frequently asked questions
How much does R1 Distill Llama 70B cost per 1M tokens?
According to current pricing data, R1 Distill Llama 70B costs $0.80 per 1M input tokens and $0.80 per 1M output tokens. Processing 1M tokens each way costs $1.60.
What does a typical API request to R1 Distill Llama 70B cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.0020. At 1,000 requests per day that is $2.00 daily, or about $60.00 per month.
What is R1 Distill Llama 70B's context window?
R1 Distill Llama 70B supports a 8K-token context window (8,192 tokens).
Does R1 Distill Llama 70B support prompt caching?
No cache-read pricing is published for R1 Distill Llama 70B, so every input token is billed at the full $0.80 per 1M rate.
What is a cheaper alternative to R1 Distill Llama 70B?
Granite 4.0 Micro from Ibm-granite is currently the cheapest comparable option at $0.02 per 1M input tokens versus $0.80 for R1 Distill Llama 70B — roughly 47x cheaper on input.
Prices may differ from DeepSeek's official pricing page for batch, tiered, or fine-tuned usage. Compare all current prices on the live model pricing dashboard, see R1 Distill Llama 70B vs Granite 4.0 Micro pricing, or run R1 Distill Llama 70B head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.