Llama 4 Scout
Meta · meta-llama/llama-4-scout
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...
Llama 4 Scout ranks #103 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.20 blended per million tokens, it is cheaper than 81% of models with published API pricing. Its 327,680-token context window is 1.3× the catalog median (262,144 tokens).
open weightsimagetexttext+image->text
Context
Max context: 327680
Max output: 16384
Max output: 16384
Pricing
Input / 1M: 0.10
Output / 1M: 0.30
Blend / 1M: 0.20
Output / 1M: 0.30
Blend / 1M: 0.20
Quality
Quality index: —
Provider
Provider: Meta
Moderated: no
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.20per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.20 |
| 10,000,000 | $2.00 |
| 100,000,000 | $20.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Meta
- Llama 3.1 8B Instruct$0.07 / 1M
- Llama 3.2 1B Instruct$0.11 / 1M
- Muse Spark 1.3 Contributor$0.15 / 1M
- Muse Spark 1.2 Contributor$0.15 / 1M
- Llama Guard 4 12B$0.18 / 1M
Closest API price
- Nemotron 3.5 Content Safety$0.20 / 1M
- Step 3.5 Flash$0.20 / 1M
- Ministral 3 14B 2512$0.20 / 1M
- Voxtral Small 24B 2507$0.20 / 1M
- Gemma 4 26B A4B$0.20 / 1M · Q 64.9