Llama 4 Maverick
by Meta · meta-llama/llama-4-maverick · #115 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
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
$0.188
per 1M tokens
Output
$0.652
per 1M tokens
Blended (3:1)
$0.304
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Llama 4 Maverick (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.304 | $0.0198 | — |
| 50% | $0.304 | $0.0198 | −0% |
| 90% | $0.304 | $0.0198 | −0% |
*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 | $0.000289 | $0.2895 |
| Document summary | 8,000 | 1,000 | $0.002152 | $2.15 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00693 | $6.93 |
| Long-context analysis | 150,000 | 5,000 | $0.0314 | $31.39 |
Performance
Intelligence Index
9.3
AA composite quality
Coding Index
16.3
Math Index
19.3
Agentic Index
0.6
Output speed
111 tok/s
median
Time to first token
0.57s
median
Time to first answer
0.57s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 80.9% |
| GPQA Diamond | 67.1% |
| Humanity's Last Exam | 4.9% |
| LiveCodeBench | 39.7% |
| SciCode | 31.7% |
| MATH-500 | 88.9% |
| AIME | 39.0% |
| AIME 2025 | 19.3% |
| IFBench | 43.0% |
| AA-LCR (Long Context Reasoning) | 50.0% |
| Terminal-Bench Hard | 6.8% |
| Terminal-Bench 2.1 | 7.9% |
| τ²-Bench (Telecom) | 17.8% |
| τ³-Bench Banking | 3.7% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 883 |
| UI components | 914 |
| Data viz | 895 |
| 3D | 929 |
| Game dev | 861 |
| Code categories | 895 |
Specs
Context window
1.05M
tokens
Max output
16K
tokens
Input modalities
text, image
Tokenizer
Llama4