tokenstat
homepricingstatshelpsign in
tokenstat
DeepInfra

Llama 3.1 70B Euryale

deepinfra/Sao10K/L3.1-70B-Euryale-v2.2 · rates as of · Benchmarks · Plans · Calculator

Open Llama instruction model for multilingual chat, reasoning, and coding

Cheapest input
$0.306
$/MTok · models.dev
Cheapest output
$0.357
$/MTok
Context
20K
tokens
Offers
4
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
models.devcheapestSao10K/L3.1-70B-Euryale-v2.2NanoGPT$0.306$0.357$020K
LiteLLMdeepinfra/Sao10K/L3.1-70B-Euryale-v2.2—$0.65$0.75$0.065—
LiteLLMSao10K/L3.1-70B-Euryale-v2.2—$0.65$0.75$0.065—
LiteLLML3.1-70B-Euryale-v2.2—$0.65$0.75$0.065—

Capabilities

  • In: text
  • Out: text
Released: 2024-07-23Family: llama

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