tokenstat
tokenstat

Qwen3 4B

qwen/qwen3-4b-fp8 · rates as of · Benchmarks · Plans · Calculator

Qwen instruction model for multilingual chat, reasoning, and tool use

Cheapest input
$0.03
$/MTok · models.dev
Cheapest output
$0.03
$/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.devcheapestqwen/qwen3-4b-fp8Novita AI$0.03$0.03$0128K
LiteLLMqwen/qwen3-4b-fp8$0.03$0.03$0.003
LiteLLMnovita/qwen/qwen3-4b-fp8$0.03$0.03$0.003
LiteLLMqwen3-4b-fp8$0.03$0.03$0.003

Capabilities

  • Reasoning
  • Open weights
  • In: text
  • Out: text
Released: 2025-04-29

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