Llama 4 Scout
by Meta · meta-llama/llama-4-scout · #68 cheapest of 422 paid models
Prices updated Sep 19, 2026, 5:57 PM UTC · refreshed hourly
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.10
per 1M tokens
Output
$0.30
per 1M tokens
Blended (3:1)
$0.15
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Llama 4 Scout (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.15 | $0.0105 | — |
| 50% | $0.15 | $0.0105 | −0% |
| 90% | $0.15 | $0.0105 | −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 | $0.00014 | $0.14 |
| Document summary | 8,000 | 1,000 | $0.0011 | $1.10 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0036 | $3.60 |
| Long-context analysis | 150,000 | 5,000 | $0.0165 | $16.50 |
Performance
Intelligence Index
6.5
AA composite quality
Coding Index
8.2
Math Index
14
Agentic Index
0.5
Output speed
96 tok/s
median
Time to first token
0.64s
median
Time to first answer
0.64s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 75.2% |
| GPQA Diamond | 58.7% |
| Humanity's Last Exam | 3.8% |
| LiveCodeBench | 29.9% |
| SciCode | 21.3% |
| MATH-500 | 84.4% |
| AIME | 28.3% |
| AIME 2025 | 14.0% |
| IFBench | 39.5% |
| AA-LCR (Long Context Reasoning) | 27.7% |
| Terminal-Bench Hard | 1.5% |
| Terminal-Bench 2.1 | 3.7% |
| τ²-Bench (Telecom) | 15.5% |
| τ³-Bench Banking | 3.3% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 762 |
| UI components | 783 |
| Data viz | 908 |
| Game dev | 796 |
| Code categories | 805 |
Specs
Context window
1.31M
tokens
Max output
16K
tokens
Input modalities
text, image
Tokenizer
Llama4