← All models
Balanced — strong quality at a mid priceOpen Weights
R1 Distill Llama 70B Pricing
DeepSeek · deepseek-deepseek-r1-distill-llama-70b
Input / 1M tokens
$0.800
Output / 1M tokens
$0.800
Context window
8,192 tokens
Max output
8,192 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0013
1,000 requests / month$1.28/mo10,000 requests / month$12.80/mo100,000 requests / month$128.00/moEstimate your own workloadOpens the calculator with R1 Distill Llama 70B preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Strong chain-of-thought reasoning and math/coding performance for a 70B-class model at low token cost.
The business tradeoff
Quality varies with inference stack and quantization; lacks native tool use or vision compared with same-size proprietary models.
Cheaper from DeepSeek
Head-to-head
Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.