Llama 4 Maverick
Open-weight MoE model hosted by many inference providers.
Input / 1M
$0.188
Meta
Output / 1M
$0.652
Cached input
$0.05
discounted reads
Context
1.0M
8K max output
Price history
input -14.8% · verified 2h agoPrice changes
5 changes| Date | Field | From | To | Change | Source |
|---|---|---|---|---|---|
| 2h ago | Input | $0.22 | $0.188 | -14.8% | openrouter |
| 2h ago | Output | $0.85 | $0.652 | -23.2% | openrouter |
| 2h ago | Cached input | — | $0.05 | — | openrouter |
| 2026-09-13 | Input | — | $0.22 | — | seed |
| 2026-09-13 | Output | — | $0.85 | — | seed |
Specifications
- Provider
- Meta
- Model ID
- llama-4-maverick
- Modality
- text+image
- Context window
- 1.0M tokens
- Max output
- 8K tokens
- Tokenizer family
- llama
Cost at similar prices
10,000 requests/month · 2000 in / 600 out tokens
- Llama 4 Maverick$7.66
- Llama 4 ScoutMeta$7.14
- Qwen3 235B A22BAlibaba$7.60
- GPT-5.4 nanoOpenAI$11.50
- GPT-5.6 LunaOpenAI$11.20
- Grok 4 FastxAI$7.00
- Grok Code Fast 1xAI$13.00