Groq Operational
Llama 4 Scout (17Bx16E) — pricing & price history
Bottom line: Llama 4 Scout (17Bx16E) costs $0.11 per 1M input tokens and $0.34 per 1M output tokens on Groq, with a 131K-token context window.
API model id: llama-4-scout-17b · Verified against the provider's pricing page as of 2026-06-22.
Input / 1M tokens
$0.11
Output / 1M tokens
$0.34
Context window
131K
Provider status
Operational
Price history
| Date | Input /1M | Output /1M |
|---|---|---|
| 2026-10-18 | $0.11 | $0.34 |
| 2026-10-17 | $0.11 | $0.34 |
| 2026-10-16 | $0.11 | $0.34 |
| 2026-10-15 | $0.11 | $0.34 |
| 2026-10-14 | $0.11 | $0.34 |
| 2026-10-13 | $0.11 | $0.34 |
| 2026-10-12 | $0.11 | $0.34 |
| 2026-10-11 | $0.11 | $0.34 |
| 2026-10-10 | $0.11 | $0.34 |
| 2026-10-09 | $0.11 | $0.34 |
| 2026-10-08 | $0.11 | $0.34 |
| 2026-10-07 | $0.11 | $0.34 |
Cheaper alternatives with similar context
| Model | Provider | Input /1M | Output /1M | Context |
|---|---|---|---|---|
| Command R7B (12-2024) | Cohere | $0.04 | $0.15 | 128K |
| DeepSeek V4 Flash | DeepSeek | $0.14 | $0.28 | 1M |
| Llama 3.3 70B (via OpenRouter) | OpenRouter | $0.1 | $0.32 | 131K |
| GPT-4.1 nano | OpenAI | $0.1 | $0.4 | 1M |
| Gemini 2.5 Flash-Lite | Google Gemini | $0.1 | $0.4 | 1.048576M |
| DeepSeek V4 Pro (via OpenRouter) | OpenRouter | $0.21 | $0.42 | 1.048576M |
Routing agents: call price_history("groq--llama-4-scout-17b") or cheapest_model(min_context=131072) over our MCP/x402 API to use this programmatically. Docs →