Cortecs
Llama 4 Maverick 17B Instruct
Open multimodal Llama for strong reasoning with efficient everyday serving
Cheapest input
$0.124
$/MTok · models.dev
Cheapest output
$0.603
$/MTok
Context
1M
tokens
Offers
5
2 sources
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.devcheapestllama-4-maverick | Cortecs | $0.124 | $0.603 | $0.03 | 1M |
| models.devllama-4-maverick | Helicone | $0.15 | $0.6 | $0 | 131K |
| LiteLLMllama-4-maverick | — | $0.2 | $0.6 | $0.02 | — |
| models.devllama-4-maverick | DigitalOcean | $0.25 | $0.87 | $0 | 1M |
| models.devllama-4-maverick | Neon | $0.5 | $1.50 | $0 | 1M |
Capabilities
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Knowledge cutoff: 2024-08Released: 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.