Llama Guard 3.8 B pricing
Source: litellm · updated 2026-10-27
Short answer: Llama Guard 3.8 B costs $0.020 per million input tokens and $0.060 per million output tokens. That is a 3:1 blended rate of $0.030 per million tokens, ranking it #26 of 704 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.020 |
| Output, per 1M tokens | $0.060 |
| Output รท input multiple | 3.00× |
| 3:1 blended, per 1M tokens | $0.030 |
| Context window | 128,000 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.020 | $0.015 | $0.035 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $0.200 | $0.150 | $0.350 | ||||
| 100M in / 25M out | $2.00 | $1.50 | $3.50 |
Other nebius models
| Model | Input | Output |
|---|---|---|
| Qwen 2.5 Coder 7 B | $0.010 | $0.030 |
| 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 |
| Qwen 2.5 32 B Instruct | $0.060 | $0.200 |
Compare against
Cheaper alternatives
Next cheaper option: Mistral Nemo at $0.029 per 1M input tokens. Next step up: Ling 3.0 Flash at $0.021 per 1M input tokens.