tokenstat
tokenstat

Llama 3.3 70B

snowflake/llama3.3-70b · rates as of · Benchmarks · Plans · Calculator

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

Cheapest input
$0.72
$/MTok · LiteLLM
Cheapest output
$0.72
$/MTok
Context
128K
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
LiteLLMcheapestsnowflake/llama3.3-70b$0.72$0.72$0.072
LiteLLMcheapestllama3.3-70b$0.72$0.72$0.072
models.devllama3-3-70bTinfoil$1.75$2.75$0128K
models.devTEE/llama3-3-70bNanoGPT$2$2$0128K

Capabilities

  • Tool calling
  • Attachments
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2023-12Released: 2025-07-03Family: 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