MetaCheapest
Llama 4 Maverick
Meta's open-weight model with excellent price-to-performance ratio.
Input Price
$0.20/1M tokens
Output Price
$0.60/1M tokens
Context Window
1M tokens
Latency (p50)
95msavg
Uptime
99.93%30d
Start using now
Select a billing plan and activate this model.
an_sk_8f3a...c9e1
Input$0.20/1M tokens
Output$0.60/1M tokens
Free tier1M tokens/month
No upfront commitment. Cancel anytime.
About this model
Llama 4 Maverick is Meta's latest open-weight model, offering impressive performance at rock-bottom prices. With a 1M token context window and solid reasoning capabilities, it's a strong choice for budget-conscious deployments and teams that value open-source flexibility.
What it's best for
- Budget-friendly deployments
- Open-weight model flexibility
- Fine-tuning and customization
- Batch processing
Sample use cases
1
Startup MVPs2
Internal tools and automation3
Data labeling at scale4
Open-source AI projectsLive stats
Requests today
2.4M
Avg latency
95ms
Active agents
8,432
Error rate
0.02%