Llama 4 Maverick
Open multimodal Llama model for strong reasoning and fast responses
Cheapest input
$0.18
$/MTok · models.dev
Cheapest output
$0.8
$/MTok
Context
1.0M
tokens
Offers
4
3 sources
Price changes
Cheapest list input/output only. Not a daily candle chart: rates move rarely, so this is an event log. Arrow down means cheaper.
- ↑ riseOutput $0.6 → $0.8
- ↑ riseInput $0.15 → $0.18
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestmeta-llama/llama-4-maverick | NanoGPT | $0.18 | $0.8 | $0 | 1.0M |
| models.devmeta-llama/llama-4-maverick | Kilo Gateway | $0.2 | $0.8 | $0 | 1.0M |
| OpenRoutermeta-llama/llama-4-maverick | OpenRouter | $0.2 | $0.8 | $0 | 1.0M |
| LiteLLMmeta-llama/llama-4-maverick-17b-128e-instruct | — | $0.2 | $0.6 | $0.02 | — |
Capabilities
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Knowledge cutoff: 2024-08-31Released: 2025-04-05Family: llama
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence14.3
- AA coding16.3
- AA agentic1.3
Sources: Arena AI, Artificial Analysis. See /benchmarks.