tokenstat
homepricingstatshelpsign in
tokenstat
Alibaba / Qwen

Qwen3 8B

qwen/qwen3-8b-fp8 · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.035
$/MTok · models.dev
Cheapest output
$0.138
$/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/qwen3-8b-fp8Novita AI$0.035$0.138$0128K
LiteLLMqwen/qwen3-8b-fp8—$0.035$0.138$0.0035—
LiteLLMnovita/qwen/qwen3-8b-fp8—$0.035$0.138$0.0035—
LiteLLMqwen3-8b-fp8—$0.035$0.138$0.0035—

Capabilities

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

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