tokenstat
tokenstat

Llama 4 Scout 17B

meta-llama/Llama-4-Scout-17B-16E-Instruct · rates as of · Benchmarks · Plans · Calculator

Open multimodal Llama model for long-context analysis and efficient agents

Cheapest input
$0.08
$/MTok · LiteLLM
Cheapest output
$0.3
$/MTok
Context
328K
tokens
Offers
6
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
LiteLLMcheapestdeepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct$0.08$0.3$0.008
LiteLLMcheapestmeta-llama/Llama-4-Scout-17B-16E-Instruct$0.08$0.3$0.008
models.devmeta-llama/Llama-4-Scout-17B-16E-InstructDeepInfra$0.1$0.3$0328K
models.devmeta-llama/llama-4-scout-17b-16e-instructGroq$0.11$0.34$0.011131K
LiteLLMmeta-llama/llama-4-scout-17b-16e-instruct$0.11$0.34$0.011
models.devmeta-llama/llama-4-scout-17b-16e-instructNovita AI$0.18$0.59$0131K

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • Out: text
Knowledge cutoff: 2024-08Released: 2025-04-05Family: llama

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash