Metallama familyActive

Llama 4 Maverick

Open multimodal Llama model for strong reasoning and fast responses

JSONEmbed chartCompare
Context
1,048,576
Max output
65,536
Input / 1M
$0.15
Output / 1M
$0.60
Providers
7
01Profile

Profile

Released
2025-04-05
Last updated
2026-04-30
Knowledge cutoff
2024-08
Weights
Open
02Capabilities

Capabilities

Input
text · image
Output
text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
Cache write
03Pricing

Pricing across 6 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

ProviderProvider model idInputOutputCache readContext
heliconellama-4-maverick$0.15$0.60Not listed131,072
nano-gptmeta-llama/llama-4-maverick$0.15$0.60$0.071,048,576
kilometa-llama/llama-4-maverick$0.19$0.65Not listed128,000
openroutermeta-llama/llama-4-maverick$0.19$0.65Not listed1,048,576
digitaloceanllama-4-maverick$0.20$0.70Not listed128,000
neonllama-4-maverick$0.50$1.50Not listed1,000,000
vercelmeta/llama-4-maverickNot listedNot listedNot listed128,000
04History

Change history

12+ recent events since 2025-04-05

2026-09-14Price cutkiloinput / 1M$0.20→ $0.19
2026-09-14Price cutkilooutput / 1M$0.70→ $0.65
2026-09-14ContextkiloMax output115,200→ 16,384
2026-09-14Price cutopenrouterinput / 1M$0.20→ $0.19
2026-09-14Price cutopenrouteroutput / 1M$0.70→ $0.65
2026-09-14ContextopenrouterMax output115,200→ 16,384
2026-08-31ContextkiloContext window1,048,576→ 128,000
2026-08-31ContextkiloMax output16,384→ 115,200
2026-08-31Price cutopenrouteroutput / 1M$0.80→ $0.70
2026-08-31ContextopenrouterMax output16,384→ 115,200
2026-08-30ContextkiloContext window1,048,576→ 128,000
2026-08-30ContextkiloContext window128,000→ 1,048,576
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews