Meta Llama 3.1 70 B Instruct pricing
Source: litellm · updated 2026-10-28
Short answer: Meta Llama 3.1 70 B Instruct costs $0.670 per million input tokens and $0.670 per million output tokens. That is a 3:1 blended rate of $0.670 per million tokens, ranking it #421 of 713 tracked models by input price.
Input / 1M
$0.670
Output / 1M
$0.670
Output ÷ input
1.00×
Context window
131,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.670 |
| Output, per 1M tokens | $0.670 |
| Output ÷ input multiple | 1.00× |
| 3:1 blended, per 1M tokens | $0.670 |
| Context window | 131,000 tokens |
| Vendor | ovhcloud |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.670 | $0.168 | $0.838 |
| 10M in / 2.5M out | $6.70 | $1.68 | $8.38 |
| 100M in / 25M out | $67.00 | $16.75 | $83.75 |
Other ovhcloud models
| Model | Input | Output |
|---|---|---|
| Mistral Small 3.2 24 B Instruct 2506 | $0.090 | $0.280 |
| Mistral 7 B Instruct V0.3 | $0.100 | $0.100 |
| Mamba Codestral 7 B V0.1 | $0.190 | $0.190 |
| Llava V1.6 Mistral 7 B Hf | $0.290 | $0.290 |
Cheaper alternatives
Next cheaper option: Gemma 2 27 B It at $0.650 per 1M input tokens. Next step up: Qwen 3.5 Plus at $0.300 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.