DeepSeek R1 Distill Llama 70 B pricing
Source: litellm · updated 2026-11-18
Short answer: DeepSeek R1 Distill Llama 70 B costs $0.250 per million input tokens and $0.750 per million output tokens. That is a 3:1 blended rate of $0.375 per million tokens, ranking it #322 of 833 tracked models by input price.
Input / 1M
$0.250
Output / 1M
$0.750
Output ÷ input
3.00×
Context window
128,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.250 |
| Output, per 1M tokens | $0.750 |
| Output ÷ input multiple | 3.00× |
| 3:1 blended, per 1M tokens | $0.375 |
| Context window | 128,000 tokens |
| Vendor | nebius |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.250 | $0.188 | $0.438 |
| 10M in / 2.5M out | $2.50 | $1.88 | $4.38 |
| 100M in / 25M out | $25.00 | $18.75 | $43.75 |
Other nebius models
| Model | Input | Output |
|---|---|---|
| Qwen 2.5 Coder 7 B | $0.010 | $0.030 |
| Llama Guard 3.8 B | $0.020 | $0.060 |
| Meta Llama 3.1.8 B Instruct | $0.020 | $0.060 |
| Qwen 2 VL 7 B Instruct | $0.020 | $0.060 |
| Mistral Nemo Instruct 2407 | $0.040 | $0.120 |
Compare against
Cheaper alternatives
Next cheaper option: Qwen 3.6 Flash Variant 1 at $0.165 per 1M input tokens. Next step up: Qwen 3.5 397 B A17 B at $0.172 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.