tokenstat
tokenstat

Mistral: Mixtral 8x22B

mistralai/mixtral-8x22b-instruct-v0.1 · rates as of · Benchmarks · Plans · Calculator

Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Cheapest input
$0.6
$/MTok · LiteLLM
Cheapest output
$0.6
$/MTok
Context
66K
tokens
Offers
7
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. Free/$0 listings are hidden by default (2 omitted). Show free/$0 offers.

SourceProviderInputOutputCache readContext
LiteLLMcheapestmistralai/mixtral-8x22b-instruct-v0.1$0.6$0.6$0.06
LiteLLMcheapestmixtral-8x22b-instruct-v0.1$0.6$0.6$0.06
LiteLLMcheapestnscale/mistralai/mixtral-8x22b-instruct-v0.1$0.6$0.6$0.06
models.devmistralai/mixtral-8x22b-instruct-v0.1NanoGPT$0.9$0.9$066K
LiteLLMmistralai/Mixtral-8x22B-Instruct-v0.1$0.9$0.9$0.09
LiteLLMMixtral-8x22B-Instruct-v0.1$0.9$0.9$0.09
LiteLLManyscale/mistralai/Mixtral-8x22B-Instruct-v0.1$0.9$0.9$0.09

Capabilities

  • In: text
  • Out: text
Released: 2025-12-11Family: mixtral

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