Llama 3.1.8 B pricing
Source: litellm · updated 2026-10-28
Short answer: Llama 3.1.8 B costs $0.240 per million input tokens and $0.240 per million output tokens. That is a 3:1 blended rate of $0.240 per million tokens, ranking it #265 of 713 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.240 |
| Output, per 1M tokens | $0.240 |
| Output รท input multiple | 1.00× |
| 3:1 blended, per 1M tokens | $0.240 |
| Context window | 128,000 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.240 | $0.060 | $0.300 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $2.40 | $0.600 | $3.00 | ||||
| 100M in / 25M out | $24.00 | $6.00 | $30.00 |
Other snowflake models
| Model | Input | Output |
|---|---|---|
| Openai GPT-5 Nano | $0.150 | $0.600 |
| Llama 4 Maverick | $0.240 | $0.970 |
| Openai GPT-5 Mini | $0.300 | $1.20 |
| Llama 3.1 70 B | $0.720 | $0.720 |
| Llama 3.3 70 B | $0.720 | $0.720 |
Compare against
Cheaper alternatives
Next cheaper option: DeepSeek at $0.190 per 1M input tokens. Next step up: Hunyuan A13 B Instruct at $0.140 per 1M input tokens.