Llama 3.2.3 B pricing
Source: litellm · updated 2026-10-27
Short answer: Llama 3.2.3 B costs $0.040 per million input tokens and $0.080 per million output tokens. That is a 3:1 blended rate of $0.050 per million tokens, ranking it #52 of 704 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.040 |
| Output, per 1M tokens | $0.080 |
| Output รท input multiple | 2.00× |
| 3:1 blended, per 1M tokens | $0.050 |
| Context window | 131,072 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.040 | $0.020 | $0.060 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $0.400 | $0.200 | $0.600 | ||||
| 100M in / 25M out | $4.00 | $2.00 | $6.00 |
Other llamagate models
| Model | Input | Output |
|---|---|---|
| Llama 3.1.8 B | $0.030 | $0.050 |
| Gemma 3.4 B | $0.030 | $0.080 |
| Qwen 3.8 B | $0.040 | $0.140 |
| DeepSeek Coder 6.7 B | $0.060 | $0.120 |
| Codellama 7 B | $0.060 | $0.120 |
Compare against
Cheaper alternatives
Next cheaper option: Nex N2.5 Mini at $0.025 per 1M input tokens. Next step up: Qwen 3.7 Flash at $0.030 per 1M input tokens.