DeepSeek-R1-Distill-Llama-70B pricing
DeepSeek-R1-Distill-Llama-70B, Reasoning-tier from SambaNova, costs $0.70 per 1M input tokens and $1.40 per 1M output tokens.
Input$0.70per 1M tokens
Output$1.40per 1M tokens
Context window—tokens
TierReasoningSambaNova
Price your own workload against DeepSeek-R1-Distill-Llama-70B in the calculator →
Specs and pricing
| Provider | SambaNova |
| Tier | Reasoning |
| Context window | — |
| Max output | — |
| Input price | $0.70 / 1M tokens |
| Output price | $1.40 / 1M tokens |
| Modalities | text |
Note. SambaNova Cloud pricing API returns prices in cents per 1M tokens (70/140), converted here to USD per 1M tokens.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $0.70 | $0.35 | $1.05 |
| 10,000,000 in / 2,500,000 out | $7.00 | $3.50 | $10.50 |
| 100,000,000 in / 25,000,000 out | $70.00 | $35.00 | $105.00 |
Cheaper alternatives
Same tier (Reasoning), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Trinity Large (Thinking) | Parasail | $0.22 | $0.85 | 58.8% cheaper blended |
| GPT-5.1-codex-mini | Azure OpenAI Service | $0.25 | $2.00 | 28.6% cheaper blended |
| QwQ 32B | Cloudflare Workers AI | $0.66 | $1.00 | 13.3% cheaper blended |