tokenstat
tokenstat

Mistral: Ministral 8B (latest)

mistral/ministral-8b · rates as of · Benchmarks · Plans · Calculator

Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads

Cheapest input
$0.1
$/MTok · models.dev
Cheapest output
$0.1
$/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
models.devcheapestmistral/ministral-8bVercel AI Gateway$0.1$0.1$0128K
LiteLLMmistral/ministral-8b$0.1$0.1$0.01
LiteLLMministral-8b$0.1$0.1$0.01
LiteLLMvercel_ai_gateway/mistral/ministral-8b$0.1$0.1$0.01

Capabilities

  • Tool calling
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2024-10Released: 2024-10-01Family: ministral

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