Llama 3.2.3 B Instruct pricing
Source: litellm · updated 2026-10-28
Short answer: Llama 3.2.3 B Instruct costs $0.015 per million input tokens and $0.025 per million output tokens. That is a 3:1 blended rate of $0.018 per million tokens, ranking it #23 of 713 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.015 |
| Output, per 1M tokens | $0.025 |
| Output รท input multiple | 1.67× |
| 3:1 blended, per 1M tokens | $0.018 |
| Context window | 131,072 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.015 | $0.0063 | $0.021 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $0.150 | $0.062 | $0.212 | ||||
| 100M in / 25M out | $1.50 | $0.625 | $2.12 |
Other lambda_ai models
| Model | Input | Output |
|---|---|---|
| Llama 3.2 11 B Vision Instruct | $0.015 | $0.025 |
| Hermes 3.8 B | $0.025 | $0.040 |
| Lfm 7 B | $0.025 | $0.040 |
| Llama 3.1.8 B Instruct | $0.025 | $0.040 |
| Llama 4 Maverick 17 B128 E Instruct Fp 8 | $0.050 | $0.100 |
Compare against
- Llama 3.2.3 B Instruct vs DeepSeek Flash Latest
- Llama 3.2.3 B Instruct vs Llama 3.2 11 B Vision Instruct
Cheaper alternatives
Next cheaper option: Qwen 2.5 Coder 7 B at $0.010 per 1M input tokens. Next step up: Qwen 2 1.5 B Instruct at $0.020 per 1M input tokens.