Llama 4 Scout
Llama 4 ScoutAlternatives?
CheaperGPT-5 Nano (2025-08-07)unstated+83%-8%$0.05 / $0.40Context: 10M → 400K
BetterClaude Opus 4.5unstated×2.8+6,567%$5 / $25Context: 10M → 200K
OpenQwen3 235B A22B Instruct 2507unstated+85%+37%$0.09 / $0.55Context: 10M → 262K+2CheaperQwen3 30B A3B Instruct 2507unstatedOpen+47%-5%$0.09 / $0.30Context: 10M → 262K+1
CheaperCommand R7b+14%-56%$0.037 / $0.15Context: not verified+1GPT-5 Nano (2025-08-07)unstated+83%-8%$0.05 / $0.40Context: 10M → 400KQwen3 30B A3B Instruct 2507unstatedOpen+47%-5%$0.09 / $0.30Context: 10M → 262K+1Command R7b+14%-56%$0.037 / $0.15Context: not verified+1
Gemma 3 12BunstatedOpen+8%-58%$0.05 / $0.10Context: 10M → 131KGemma 3 27BunstatedOpen+5%-33%$0.08 / $0.16Context: 10M → 131KClaude Opus 4.5unstated×2.8+6,567%$5 / $25Context: 10M → 200KClaude Sonnet 4.5unstated×2.6+3,900%$3 / $15Context: 10M → 1MClaude Haiku 4.5unstated×2.4+1,233%$1 / $5Context: 10M → 200Ko3 (2025-04-16)unstated×2.2+2,233%$2 / $8Context: 10M → 200K
Kimi K2 0711unstatedOpen×2.1+483%$0.50 / $2Context: 10M → 128K+3Qwen3 235B A22B Instruct 2507unstatedOpen+85%+37%$0.09 / $0.55Context: 10M → 262K+2NNanbeige4 3B Thinking 2511Open+83%——Context: 10M → 66K+1Qwen3 32BunstatedOpen+73%+717%$0.70 / $2.80Context: 10M → 33K+1Command AunstatedOpen+65%+2,817%$2.50 / $10Context: 10M → 256K+2Qwen3 8BunstatedOpen+51%+107%$0.18 / $0.70Context: 10M → 33K+1Llama 4 Maverick 17B 128E Instruct FP8Open+33%—$0.20 / $0.80Context: 10M → 1M+1Llama 3.3 70B InstructunstatedOpen+13%—$0.10 / $0.32Context: 10M → 128K+1Llama 3.1 8B InstructunstatedOpen-8%—$0.02 / $0.04Context: 10M → 131K+1Llama 3.2 3B InstructunstatedOpen-22%—$0.02 / $0.02Context: 10M → 131K+1Llama 3.2 1B InstructunstatedOpen-62%—$0.005 / $0.01Context: 10M → 60K+2Muse Spark OpenxhighOpenn/a—$0.84Context: 10M → 1M+3Muse Wondermaxn/a—$4.52Context: 10M → 1M+6Muse Wonder Fulln/a——Context: 10M → 1M+1All Meta models →Run it yourself
estimateBenchmarks
in Agents & Tool UseFAQ
How much does Llama 4 Scout cost?›
$0.10 per 1M input tokens and $0.30 per 1M output tokens (cheapest host: DeepInfra). A typical benchmark task costs about $0.11 at default effort.
Is Llama 4 Scout free to use?›
There is no free API; the cheapest paid price is $0.10 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Llama 4 Scout, and what is it best at?›
#315 of 334 in Chat & Knowledge, #75 of 132 in Coding, #131 of 133 in Agents & Tool Use, #138 of 195 in Writing & Language, #106 of 124 in Vision & Documents.
Is Llama 4 Scout better than Qwen3 1.7B?›
On BFCL v4, Llama 4 Scout scores 28.1 vs 28.4 — about the same.
How can I use Llama 4 Scout?›
Through the API of DeepInfra, Google, Novita.
What is the context window of Llama 4 Scout?›
10M tokens, with up to 16K output tokens.
When was Llama 4 Scout released? Is there a newer version?›
Released 2025-04-05. It is the current version in its line.
Is Llama 4 Scout open source?›
Yes, the weights are open (llama4 licence).
Can I run Llama 4 Scout locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Llama 4 Scout read images?›
It accepts text and images as input.
What is Llama 4 Scout?›
Llama 4 Scout is an open-weights language model from Meta, released Apr 2025.
What are the best alternatives to Llama 4 Scout?›
GPT-5 Nano (2025-08-07) (cheaper), Claude Opus 4.5 (better), Qwen3 235B A22B Instruct 2507 (open weights).