Llama 4 Scout
Intelligence
6.45
#460 of 520 models
Output speed
100.1 tok/s
Measured generation rate
Cost / index task
$0.118
Measured evaluation workload
End-to-end latency
6ms
First answer 1ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
26 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
Domain capability
03 / Operation
Speed, tokens & price
Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.
Token pricing
- Input / 1M
- $0.190
- Output / 1M
- $0.680
- Cache read / 1M
- —
- Cache write / 1M
- —
- Cache-hit discount
- —
Response & usage
- Output speed
- 100.1 tok/s
- First chunk
- 1ms
- First answer
- 1ms
- Output / task
- 1.9k
- Reasoning / task
- 0
Evaluation workload
- Canonical input
- 394.37M
- Canonical output
- 3.9M
- Answer / task
- 1.9k
- Index time / task
- 19.9s
- Run cost
- $77.582
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 96.3 tok/s | 1ms | 1ms | 6ms |
| Long | 100.1 tok/s | 1ms | 1ms | 6ms |
| Hundred K | 94.1 tok/s | 4ms | 4ms | 9ms |
| Medium Parallel | 86.4 tok/s | 1ms | 1ms | 6ms |
04 / Access
License & availability
Recorded license
LLAMA 4 COMMUNITY LICENSE AGREEMENT
The publisher-linked license text defines permitted use and redistribution. Review it before using the model.
- Weight access
- Open weights
- Classification
- Commercial License
- Reasoning
- No
Routing and providers
- OpenRouter ID
- meta-llama/llama-4-scout
- Tokenizer
- Llama4
- Instruct type
- —
- Captured endpoints
- 3
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| DeepInfra | fp8 | 327.7k | — |
| Novita | bf16 | 131.1k | — |
| unknown | 1.31M | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.