Today's price · per 1M tokens
Input
$0.110
per 1M tokens
Output
$0.340
per 1M tokens
Blended
$0.168
blended $/1M — 3:1 weighted input:output
Price receipt
We read Groq's own pricing page on Jul 4, 2026 and found Llama 4 Scout (17Bx16E) 128k listed with a price on the same row — that read is where the number above comes from, recorded as a correction. We keep the page text we read; its content hash is 2edf4f7dbe.
Overview
Meta's Llama 4 Scout served on Groq's LPU for high-speed inference — a natively multimodal MoE (17B active, 16 experts) with a 10M-token context. $0.11/$0.34 per 1M tokens.
Deploy this open model on rented GPUs
Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.
Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.
Capabilities
struck through = not supportedBenchmark performance
accuracy % · higher is better- AA Intelligence Index: 10.3 (Artificial Analysis composite across reasoning, knowledge and coding evals)
- AA Agentic Index: 1.1 (Tool use, planning, autonomy)
- AA-Omniscience Index: -52.1 (−100–100)
- Ranks #60 of 69 benchmarked models by average score
- Ranks #130 of 161 comparably-measured models by percentile score, across 13 independent measurements
- Ranks #19 of 161 comparably-tested models by normalized performance per dollar
- Strongest at HumanEval — 80%, #26 of 49
2600 tokens/sec output
Source: Groq model card · updated Jun 1, 2026 · See full rankings →
Specifications
- Provider
- Groq
- Context window
- 10M tokens
- Modality
- text, image
- Parameters
- 17B (16 experts)
- Open source
- Yes — open weights available
- Released
- Apr 6, 2025
- Status
- Retired ended Jul 17, 2026
- Last updated
- Jul 4, 2026
- Tags
Availability verified: Jul 25, 2026 — per Groq's own deprecation notice