Skip to content
OSMEXO

Llama 4 Scout

meta/llama-4-scout
  • Meta
  • Family · Llama 4 Scout
  • Released 5 Apr 2025
  • Open weights
  • Text · Image → Text
  • Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context1.3M
Max output16K
Input / 1M$0.10
Output / 1M$0.303× input
Scores · standing
Intelligence6.5#375/490
Coding8.2#180/196
Usage
Tokens / day2.5B▼ 23% 7d
Usage rank#149
Requests / day1.4M
Tool calls / req0.00
Per request · 30 days
Avg input2.3K0.2× median
Avg output1490.2× median
Tool-call failures10%5.3× median

Benchmarks

bar = share of the top score · Benchmark data: Artificial Analysis
MATH-500#77 of 167
84.4%
MMLU-Pro#132 of 273
75.2%
GPQA Diamond#281 of 445
58.7%
IFBench#199 of 328
39.5%
LiveCodeBench#165 of 269
29.9%
SciCode#154 of 160
21.3%
Long-context reasoning#266 of 393
27.7%
AIME#71 of 160
28.3%
Speed · median across 3 providers, latest day
Output speed#293/33431 tok/s2.1× slower than median
Fastest provider41 tok/sbest of 3 providers
First token#1080.73 s1.4× quicker than median

#7 cheapest of 34 with a similar score

Value
Intelligence Index
678910$0.1$0.2$0.5$1Llama 4 Scout
Blended price per 1M tokens (log)

Technical details

Tokenizer
Llama4
Knowledge cutoff
2024-08-31
License
other
Parameters
109B
Moderation
none
Downloads · likes
105.4K · 1.4K
Request parameters 15
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • temperature
  • top_p
  • top_k
  • min_p
  • max_tokens
  • stop
+5 more
  • seed
  • frequency_penalty
  • logit_bias
  • presence_penalty
  • repetition_penalty

When to use

Best for

  • Question answering over extremely long documents
  • Image understanding in chat apps
  • Low-cost multimodal assistants
  • Structured output extraction

Think twice for

  • Hardest coding tasks
  • Image generation
  • Frontier reasoning tasks

Research papers

Alternatives

other vendors · similar capability

Want Llama 4 Scout on OSMEXO?

Sign in to request it. Requests are reviewed; a request does not guarantee availability.