MetaLlama 4 Maverick
- Released
- Apr 5, 2025
- Tracked since
- 2026-07-23
Intelligence index10Ranks 371 of 664 models with this metric
Coding index16.3Ranks 211 of 259 models with this metric
Agentic index0.6Ranks 152 of 156 models with this metric
Capability profile
5 axes vs. site averageLlama 4 Maverick
Site average
Pricing
per 1M tokens- Input
- $0.260
- Output
- $0.910
- Cache read
- $0.240
Performance
- Output throughput
- 116 tokens/sec
- Time to first token
- 910ms
- First answer token
- 910ms
- End-to-end response
- 5.23s
History
9Intelligence index
14.3→10
Output
$0.850→$0.910
Output throughput
110→116
Cheaper at this level
Models with a comparable intelligence index and a lower output price- Qwen3.5 4B (Reasoning)
AlibabaIntelligence 13.1$0.150−84% - Qwen3.5 4B (Non-reasoning)AlibabaIntelligence 10.8$0.150−84%
- DeepSeek V4 Flash 0420 (Non-reasoning)
DeepSeekIntelligence 18.9$0.200−78% - Qwen3.5 9B (Reasoning)AlibabaIntelligence 13.7$0.200−78%
- Hy3-preview (Reasoning)
TencentIntelligence 22.7$0.210−77%