Llama 4 Scout 17B Instruct
Open Llama with long-context vision for efficient multimodal agents.
- Capability
- 127.8ECI · #140 of 158
- Input
- $0.17per 1M tokens
- Output
- $0.59per 1M tokens
- Context
- 10M16K max output
What it costs
- Input
- $0.17per million tokens
- Output
- $0.59per million tokens
- Blended (3:1)
- $0.275cheaper than 69% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.635 |
| Team assistant25M input + 5M output tokens | $7.20 |
| Production app250M input + 50M output tokens | $72.00 |
Median of 13 paid API providers on models.dev.
Independent benchmarks
#140 of 158 scored models
The shaded band is Epoch AI’s confidence range (124.9–130.4); the tick marks the median scored model.
Scores from Epoch AI, run independently of Meta.
The details
- Lab
- Meta
- Released
- Apr 5, 2025
- Knowledge cutoff
- Aug 2024
- Context window
- 10,000,000 tokens
- Max output
- 16,384 tokens
- Inputs
- Text, Images
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- Availability
- 13 API providerslisted on models.dev
More from Meta
About Llama 4 Scout 17B Instruct
How much does Llama 4 Scout 17B Instruct cost?
Llama 4 Scout 17B Instruct costs $0.17 input / $0.59 output per million tokens (median across 13 API providers). At a 3:1 input-to-output mix that is $0.275 per million tokens, cheaper than 69% of the 469 priced models we track.
What is the context window of Llama 4 Scout 17B Instruct?
Llama 4 Scout 17B Instruct accepts up to 10,000,000 tokens per request and can write up to 16,384 tokens in one response.
How good is Llama 4 Scout 17B Instruct?
Epoch AI gives Llama 4 Scout 17B Instruct a Capabilities Index score of 127.8 (likely range 124.9–130.4), ranking it #140 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 51.8%, OTIS Mock AIME 2024–2025 7.8%.
Is Llama 4 Scout 17B Instruct open source?
Yes. Meta publishes the weights, so it can be downloaded and self-hosted.
What inputs does Llama 4 Scout 17B Instruct support?
Llama 4 Scout 17B Instruct accepts text and images and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Llama 4 Scout 17B Instruct released?
Meta released Llama 4 Scout 17B Instruct on Apr 5, 2025. Its training data runs to Aug 2024.
What are the best alternatives to Llama 4 Scout 17B Instruct?
The closest current models from other labs on capability, price and release date are Gemma 3 27B IT (Google, ECI 127.5, $0.10 / $0.299), Qwen3 30B A3B (Alibaba (Qwen), ECI 134.2, $0.109 / $0.50), GPT-4o mini (OpenAI, ECI 123.8, $0.15 / $0.60) and DeepSeek-V3 (DeepSeek, ECI 131.7, $0.32 / $1.10).