Llama 3.2.3 B Instruct Fast pricing
Source: litellm · updated 2026-10-29
Short answer: Llama 3.2.3 B Instruct Fast costs $0.050 per million input tokens and $0.300 per million output tokens. That is a 3:1 blended rate of $0.113 per million tokens, ranking it #79 of 722 tracked models by input price.
Input / 1M
$0.050
Output / 1M
$0.300
Output ÷ input
6.00×
Context window
131,072
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.050 |
| Output, per 1M tokens | $0.300 |
| Output ÷ input multiple | 6.00× |
| 3:1 blended, per 1M tokens | $0.113 |
| Context window | 131,072 tokens |
| Vendor | zerogpu |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.050 | $0.075 | $0.125 |
| 10M in / 2.5M out | $0.500 | $0.750 | $1.25 |
| 100M in / 25M out | $5.00 | $7.50 | $12.50 |
Other zerogpu models
| Model | Input | Output |
|---|---|---|
| Lfm 2.5 1.2 B Instruct | $0.020 | $0.050 |
| Lfm 2.5 1.2 B Thinking | $0.020 | $0.050 |
| Llama 3.1.8 B Instruct Fast | $0.150 | $0.280 |
Compare against
Cheaper alternatives
Next cheaper option: Ling 3.1 Flash at $0.075 per 1M input tokens. Next step up: Mistral 7 B V0.3 at $0.100 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.