Meta: Llama 4 Maverick
The Meta: Llama 4 Maverick is an AI model that accepts text and image inputs and has a context length of up to 1048576 tokens. It supports tool use but does not support reasoning or provide structured output. For users who value flexibility in input types, the Meta: Llama 4 Maverick may be worth considering due to its ability to handle both text and images. At $0.1875 per million input tokens and $0.6525 per million output tokens, it is a mid-range option compared to other models. With benchmark scores of 12.8 across two independent tests, the model's performance is respectable but not exceptional; further testing may be necessary to determine its full capabilities.
Benchmark results
Independent, published benchmarks. Blended score 13.0 across 2 benchmarks, last refreshed 2026-09-27. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| Aider Polyglot | code editing across languages | 15.6 |
| AI Index | broad capability composite | 16.5 |
- Model ID
- meta-llama/llama-4-maverick
- Vendor
- meta-llama
- Released
- April 2025
- Tokenizer
- Llama4
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.19/M input and $0.65/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.13 |
| A month of a busy support chatbot | 5M in / 2M out | $2.24 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-09-22 | $0.19 | $0.65 | 1,048,576 |
| 2026-09-21 | $0.20 | $0.80 | 1,048,576 |
| 2026-09-15 | $0.19 | $0.65 | 1,048,576 |
| 2026-09-01 | $0.20 | $0.70 | 1,048,576 |
| 2026-08-15 | $0.20 | $0.80 | 1,048,576 |
| 2026-08-10 | $0.20 | $0.70 | 1,048,576 |
| 2026-07-17 | $0.20 | $0.80 | 1,048,576 |
Category rankings
Where Meta: Llama 4 Maverick places across the 3 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #10 | JSON ExtractionData · of 25 ranked | 132 |
| #11 | Dataset AnnotationResearch · of 25 ranked | 134 |
| #23 | Function / Tool CallingAgents · of 25 ranked | 121 |
Similar models
Meta: Llama 4 Scout
Meta: Llama 3.1 8B Instruct
Meta: Llama 3.3 70B Instruct
Meta: Llama 3.1 70B Instruct
Meta: Llama Guard 4 12B
Meta: Llama 3.2 3B Instruct
Quick answers
- How much does Meta: Llama 4 Maverick cost?
- $0.19 per million input tokens and $0.65 per million output tokens.
- What is Meta: Llama 4 Maverick's context window?
- 1,048,576 tokens, roughly 1,572 pages of text in a single request.
- Does Meta: Llama 4 Maverick support tool calling?
- It supports tool calling, structured output.
- Can Meta: Llama 4 Maverick process images?
- Yes, it accepts image input.