Llama 4 Maverick
meta/llama-4-maverick- Meta
- Family · Llama 4 Maverick
- Released 5 Apr 2025
- Open weights
- Text · Image → Text
- Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context512K
Max output16K
Input / 1M$0.19
Output / 1M$0.653.5× input
Scores · standing
Intelligence9.3#265/490
Coding16.3#151/196
Usage
Tokens / day2.0B▼ 14% 7d
Usage rank#159
Requests / day1.4M
Tool calls / req0.01
Per request · 30 days
Avg input2.0K0.1× median
Avg output1420.2× median
Cache hit37%0.5× median
Reasoning share0%0.0× median
Tool-call failures2.9%1.6× median
Consumption
Peak 3.5B 21 OctLow 1.7B 3 OctRank today #159
News & trends
News · latest from Meta
- Meta Networking at the 2026 OCP Global Summit: Open Innovation for Scale-Up, Scale-Out, and Scale-Across AI NetworksMeta Engineering · 26 Oct
- Scale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72NVIDIA · 15 Oct
- Meta Muse Spark Open is live on Together AITogether AI · 15 Oct
- Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta15 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisSpeed · median across 2 providers, latest day
Output speed#233/33446 tok/s1.4× slower than median
Fastest provider77 tok/sbest of 2 providers
First token#380.46 s2.3× quicker than median
First answer token#130.58 sthinking included
#19 cheapest of 42 with a similar score
Value
Intelligence Index
Blended price per 1M tokens (log)
Technical details
- Tokenizer
- Llama4
- Knowledge cutoff
- 2024-08-31
- License
- other
- Parameters
- 402B
- Moderation
- none
- Downloads · likes
- 11.6K · 519
Request parameters 16
- tools
- tool_choice
- response_format
- structured_outputs
- temperature
- top_p
- top_k
- max_tokens
- stop
- seed
+6 more
- frequency_penalty
- logit_bias
- logprobs
- presence_penalty
- repetition_penalty
- top_logprobs
When to use
Best for
- Image understanding in chat apps
- General knowledge Q&A
- Math and academic question answering
- Long document analysis
- Self-hosted multimodal assistants
Think twice for
- Image generation
- Multi-hour autonomous agent runs
- Instruction-heavy pipelines needing top accuracy
Research papers
- Training Small Language Models for Transferable Tool Selection22 Oct
- Forty Questions: Identifying a Language Model from One-Word Answers20 Oct
- Ideological Stance Detection in a Low-Resource Language: Polarization in Bangladeshi Public vs Private University Discourse on Social Media3 Oct
- Automated IEP Generation from Traditional Chinese Parent-Teacher Interviews via Corpus-Grounded Feature Diffusion8 Jun
- True (VIS) Lies: Analyzing How Generative AI Recognizes Intentionality, Rhetoric, and Misleadingness in Visualization Lies1 Apr
- AgentAssay: Token-Efficient Regression Testing for Non-Deterministic AI Agent Workflows3 Mar
- Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning26 Jan
- Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models25 Sep
Alternatives
other vendors · similar capability- 8.5
- 11.6
- 13.1
- 6.7
Want Llama 4 Maverick on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.