MMeta · Released Apr 5, 2025
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...
- Released
- Apr 5 2025
- Context window
- 524K 16K out
- Input / 1M tokens
- $0.19
- Output / 1M tokens
- $0.65
Where to run it
3 providers compared
Cheapest: DigitalOcean at $0.19 / $0.65 per 1M input / output tokens — 45% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| DigitalOcean | $0.19 | $0.65 | $0.05 | 128K | 16K | 98.4%24h | Cheapest |
| ParasailFP8 | $0.35 | $1.00 | $0.17 | 524K | 33K | 98.8%24h | +68% |
| Googleus-east5 | $0.35 | $1.15 | — | 524K | 8K | — | +81% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Llama 4 Maverick. Scores appear here automatically once it does.
Specs
Details
- Model ID
meta-llama/llama-4-maverick- Developer
- Meta
- Release date
- Apr 5, 2025 ·
- Context window
- 524,288 tokens
- Max output
- 16,384 tokens
- API price
- $0.19 / $0.65 per 1M input / output tokens
- Providers
- 3
- Input types
- text, image
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date, prices and providers from OpenRouter's catalog; buying directly from a provider can cost a little differently. Uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.