Llama 4 Maverick
MetaOpen weightsNon-reasoningVerifiedReleased Apr 5, 2025Input: text, image
Overall score
21.6
Rank 209 of 222 · 16.9–26.2
Context window
1M
1,000,000 tokens
Price per 1M tokens
$0.19 in · $0.65 out
Source: OpenRouter
Blended price
$0.30
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Reasoning59.3
- 2Multimodal56.0
- 3Instruction following#9350.3
- 4Knowledge47.6
Benchmark results (2)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| MazeBench | 0 | #20 of 42 |
Multimodal
| Design Arena Website | 871 | #88 of 91 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (OpenRouter) | $0.19 | $0.65 | — |
| OpenRouter meta-llama/llama-4-maverick | $0.19 | $0.65 | $0.050 |
Self-hosted cost varies
Open weights
From the Hugging Face repository.
- Parameters
- 402B
- Licence
- other
- Downloads (30 days)
- 9.9K
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Similar score
- Nova Pro21.6 · —
- GPT-4 Turbo21.5 · $15.00
- Llama 3 70B21.3 · —
- LFM2-24B-A2B20.6 · Free
- Ministral 3 8B20.0 · $0.15