Llama 4 Maverick 17 B128 E Instruct Fp 8 pricing
Source: litellm · updated 2026-10-27
Short answer: Llama 4 Maverick 17 B128 E Instruct Fp 8 costs $0.050 per million input tokens and $0.100 per million output tokens. That is a 3:1 blended rate of $0.062 per million tokens, ranking it #70 of 704 tracked models by input price.
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.050 |
| Output, per 1M tokens | $0.100 |
| Output รท input multiple | 2.00× |
| 3:1 blended, per 1M tokens | $0.062 |
| Context window | 131,072 tokens |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total | 1M in / 250K out | $0.050 | $0.025 | $0.075 |
|---|---|---|---|---|---|---|---|
| 10M in / 2.5M out | $0.500 | $0.250 | $0.750 | ||||
| 100M in / 25M out | $5.00 | $2.50 | $7.50 |
Other lambda_ai models
| Model | Input | Output |
|---|---|---|
| Llama 3.2 11 B Vision Instruct | $0.015 | $0.025 |
| Llama 3.2.3 B 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 |
Compare against
- Llama 4 Maverick 17 B128 E Instruct Fp 8 vs Llama 4 Scout 17 B16 E Instruct
- Llama 4 Maverick 17 B128 E Instruct Fp 8 vs GPT-5 Nano
Cheaper alternatives
Next cheaper option: Nova Micro at $0.035 per 1M input tokens. Next step up: Gemma 4 26 B at $0.030 per 1M input tokens.