Llama 4 Maverick
by Meta · meta-llama/llama-4-maverick · #170 cheapest of 457 paid models
Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.35
per 1M tokens
Output
$1.00
per 1M tokens
Blended (3:1)
$0.512
3 input : 1 output
Cache read
$0.17
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Llama 4 Maverick with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.512 | $0.0367 | — |
| 50% | $0.445 | $0.0277 | −25% |
| 90% | $0.391 | $0.0205 | −44% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000475 | $0.475 |
| Document summary | 8,000 | 1,000 | $0.0038 | $3.80 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0125 | $12.50 |
| Long-context analysis | 150,000 | 5,000 | $0.0575 | $57.50 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
16.3
Math Index
—
Agentic Index
0.6
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 862 |
| UI components | 888 |
| Data viz | 882 |
| 3D | 881 |
| Game dev | 827 |
| Code categories | 868 |
Specs
Context window
524K
tokens
Max output
33K
tokens
Input modalities
text, image
Tokenizer
Llama4