Capabilities
7-day heat trend
−2.4%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 17% of tracked models
- Faster than 8% of tracked models
- Efficiency rank: #912 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About llama-4-scout
Llama 4 Scout on Cerebras is a preview model for fast open-model inference.
llama-4-scout is a Text model from Cerebras (US). HotON.ai tracks it at $0.65 per 1M input tokens and $0.85 per 1M output tokens, with a 8K-token context window, ~124 tokens/sec throughput and 99.3% availability. Its composite efficiency score is 88/100 at an estimated $0.002 per successful task.
Compare llama-4-scout
Related market news
Frequently asked questions
How much does llama-4-scout cost per 1M tokens?+
llama-4-scout is tracked at $0.65 per 1M input tokens and $0.85 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.80 per 1M tokens. Figures are illustrative demo data.
What is llama-4-scout best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is llama-4-scout?+
llama-4-scout delivers about 124 tokens/sec with 99.3% tracked availability, suitable for latency-sensitive, real-time applications.
Is llama-4-scout cheaper than other AI models?+
Within the HotON.ai tracked set, llama-4-scout is cheaper than 17% of models on input price and ranks #912 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.