Llama 4 Maverick
by Meta · meta-llama/llama-4-maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
- Input / 1M tokens
- $0.188
- Output / 1M tokens
- $0.652
- Context
- 524K
Specs
| Input price | $0.188 / 1M tokens |
|---|---|
| Output price | $0.652 / 1M tokens |
| Cached input | $0.05 / 1M tokens |
| Context window | 524K tokens |
| Max output | 16.4K tokens |
| Reads | text, image |
| Writes | text |
| Tool calling | Yes |
| Reasoning | No |
| Listed | Apr 5, 2025 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
3 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| DigitalOcean | — | 128K | 16.4K | $0.188 | $0.652 | $0.05 | 100% | 762 ms | 12 tok/s | Normal | |
| Parasail | fp8 | 524K | 32.8K | $0.35 | $1.00 | $0.17 | 100% | 575 ms | 70 tok/s | Normal | |
| — | 524K | 8.19K | $0.35 | $1.15 | — | — | — | — | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Related models
- Meta
Llama Guard 4 12B
- Input
- $0.18
- Output
- $0.18
- Context
- 164K
- Meta
Llama 4 Scout
- Input
- $0.10
- Output
- $0.30
- Context
- 1.31M
- Meta
Llama 3.3 70B Instruct
- Input
- $0.10
- Output
- $0.32
- Context
- 131K
- Meta
Llama 3.2 1B Instruct
- Input
- $0.027
- Output
- $0.201
- Context
- 60K
- Meta
Llama 3.2 3B Instruct
- Input
- $0.05
- Output
- $0.33
- Context
- 131K
- Meta
Llama 3.1 70B Instruct
- Input
- $0.40
- Output
- $0.40
- Context
- 131K