Metaopen weightsLlama 4 Scout pricing
$0.10 per 1M input tokens and $0.30 per 1M output tokens. In real work that is 0.05¢ per chat answer and 0.21¢ to summarize a 20-page PDF.
What Llama 4 Scout costs per task
Token counts estimated from a measured model of the same lab (Qwen3.8 Flash), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.05¢$0.49 / 1,000 | 87 in · 683 out · 909 reasoning | 60 of 336 | estimated |
| Reply to a customer email | 0.02¢$0.24 / 1,000 | 323 in · 97 out · 587 reasoning | 65 of 336 | estimated |
| Write a 1,500-word blog post | ≥0.48¢$4.81 / 1,000 | 103 in · 0 out · 16,000 reasoning | 130 of 336 | estimated |
| Write 10 product descriptions | ≥0.48¢$4.83 / 1,000 | 342 in · 0 out · 16,000 reasoning | 151 of 336 | estimated |
| Translate 1,000 words | 0.05¢$0.53 / 1,000 | 1,375 in · 1,156 out · 136 reasoning | 41 of 336 | estimated |
| Proofread one page (500 words) | 0.06¢$0.62 / 1,000 | 770 in · 665 out · 1,159 reasoning | 73 of 336 | estimated |
| Summarize a 20-page PDF | 0.21¢$2.09 / 1,000 | 13,015 in · 497 out · 2,141 reasoning | 70 of 336 | estimated |
| Extract data from an invoice | 0.07¢$0.70 / 1,000 | 497 in · 556 out · 1,617 reasoning | 78 of 336 | estimated |
| Analyze a 200-row spreadsheet | ≥0.54¢$5.43 / 1,000 | 6,306 in · 0 out · 16,000 reasoning | 77 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.12¢$1.24 / 1,000 | 3,721 in · 966 out · 1,912 reasoning | 76 of 336 | estimated |
| Classify 100 support tickets | 0.27¢$2.67 / 1,000 | 1,451 in · 529 out · 7,879 reasoning | 98 of 336 | estimated |
| Review 500 lines of code | ≥0.53¢$5.28 / 1,000 | 4,835 in · 0 out · 16,000 reasoning | 94 of 336 | estimated |
| Write a SQL query | 0.08¢$0.81 / 1,000 | 175 in · 401 out · 2,225 reasoning | 84 of 336 | estimated |
| Run a 50-step coding agent | 25¢$253 / 1,000 | 2,241,975 in · 15,030 out · 80,850 reasoning | 121 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Llama 4 Scout through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrafp8 | $0.08 / $0.24 | - | 327K | 0% |
DeepInfrafp8 | $0.10 / $0.30 | - | 327K | |
DeepInfrafp8 | $0.15 / $0.45 | - | 327K | 0% |
 Novitabf16 | $0.18 / $0.59 | - | 131K | |
 Googleunknown | $0.25 / $0.70 | - | 1.31M |
Price history
First seen in our price history on Apr 10, 2025 at $0.08 input / $0.45 output. Since then the output price moved from $0.45 to $0.30 per 1M tokens (2 changes).
FAQ
How much does Llama 4 Scout cost?
Llama 4 Scout costs $0.10 per 1 million input tokens and $0.30 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.05¢ and summarizing a 20-page PDF about 0.21¢.
Where is Llama 4 Scout cheapest?
Among 5 providers we track, the lowest list price today is at DeepInfra: $0.08 input and $0.24 output per 1M tokens.
Is the Llama 4 Scout cost per task measured or estimated?
Estimated: Llama 4 Scout was not run directly. Tokens come from Qwen3.8 Flash and are rescaled by the tokenizer of Meta. Real usage can differ.