Llama 4 Scout pricing & benchmarks
Llama 4 Scout is available from Meta at $0.100 per million input tokens and $0.300 per million output tokens ($0.150 blended at 3:1). It accepts up to 1,310,720 tokens of context. 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...
Pricing
Per million tokens · OpenRouter
Input$0.100
Output$0.300
Blended (3:1)$0.150
Specification
meta-llama/llama-4-scout
Context window1.3M
Max output16K
ReleasedApr 2025
LicenceOpen weights
Modalitiesin:text, in:image, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 51.8% ±3.2 | — | 2025-04-08 | Independently run · Epoch AI |
| OTIS Mock AIME | 7.8% ±3.0 | — | 2025-04-08 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| gpt-oss-120b | OpenAI | $0.070 (−53%) | 75.8% | Compare → |
| Phi 4 | Microsoft | $0.088 (−42%) | 56.1% | Compare → |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.113 (−25%) | 91.0% | Compare → |
| GPT-5 Nano | OpenAI | $0.138 (−8%) | 69.4% | Compare → |
Where to run Llama 4 Scout
4 hosts · 2.4× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfra ⚠ 328K context, not 1.3M |
$0.150 | $0.100 / $0.300 | 328K | fp8 | 99.8% |
| Groq ⚠ 131K context, not 1.3M |
$0.167 | $0.110 / $0.340 | 131K | — | 99.7% |
| Novita ⚠ 131K context, not 1.3M |
$0.282 | $0.180 / $0.590 | 131K | bf16 | 99.8% |
| Google (us-east5) | $0.362 | $0.250 / $0.700 | 1.3M | — | 99.9% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Llama 4 Scout
FAQ
How much does Llama 4 Scout cost?
Llama 4 Scout costs $0.100 per million input tokens and $0.300 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.150 per million tokens.
What is Llama 4 Scout's context window?
Llama 4 Scout accepts up to 1,310,720 tokens of context, and can generate up to 16,384 output tokens.
How good is Llama 4 Scout on benchmarks?
Llama 4 Scout scores 51.8% on GPQA Diamond, independently run and published by Epoch AI. 2 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Llama 4 Scout?
Yes — 4 models in our catalogue cost less per token than Llama 4 Scout and score at least as high on the same benchmark. The cheapest is gpt-oss-120b at $0.070 per million tokens blended.