Llama 3.1.8 B Instruct pricing
Source: openrouter · updated 2026-10-28
Short answer: Llama 3.1.8 B Instruct costs $0.020 per million input tokens and $0.040 per million output tokens. That is a 3:1 blended rate of $0.025 per million tokens, ranking it #26 of 713 tracked models by input price.
Input / 1M
$0.020
Output / 1M
$0.040
Output ÷ input
2.00×
Context window
131,072
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.020 |
| Output, per 1M tokens | $0.040 |
| Output ÷ input multiple | 2.00× |
| 3:1 blended, per 1M tokens | $0.025 |
| Context window | 131,072 tokens |
| Vendor | meta-llama |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.020 | $0.010 | $0.030 |
| 10M in / 2.5M out | $0.200 | $0.100 | $0.300 |
| 100M in / 25M out | $2.00 | $1.00 | $3.00 |
Other meta-llama models
| Model | Input | Output |
|---|---|---|
| Llama 3.2.1 B Instruct | $0.027 | $0.201 |
| Llama 3.2.3 B Instruct | $0.050 | $0.330 |
| Llama 4 Scout | $0.100 | $0.300 |
| Llama 3.3 70 B Instruct | $0.100 | $0.320 |
| Llama Guard 4 12 B | $0.180 | $0.180 |
Compare against
Cheaper alternatives
Next cheaper option: Qwen 2 1.5 B Instruct at $0.020 per 1M input tokens. Next step up: GPT OSS 20 B at $0.015 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.