tokenstat
tokenstat

Qwen3 30B A3B FP8

qwen/qwen3-30b-a3b-fp8 · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.0509
$/MTok · models.dev
Cheapest output
$0.335
$/MTok
Context
128K
tokens
Offers
9
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.devcheapest@cf/qwen/qwen3-30b-a3b-fp8Cloudflare$0.0509$0.335$033K
LiteLLM@cf/qwen/qwen3-30b-a3b-fp8$0.0509$0.335$0.0051
LiteLLMcloudflare/@cf/qwen/qwen3-30b-a3b-fp8$0.0509$0.335$0.0051
LiteLLMqwen3-30b-a3b-fp8$0.0509$0.335$0.0051
models.devworkers-ai/@cf/qwen/qwen3-30b-a3b-fp8Cloudflare$0.051$0.34$0128K
models.devqwen/qwen3-30b-a3b-fp8Jiekou.AI$0.09$0.45$041K
models.devqwen/qwen3-30b-a3b-fp8Novita AI$0.09$0.45$041K
LiteLLMqwen/qwen3-30b-a3b-fp8$0.09$0.45$0.009
LiteLLMnovita/qwen/qwen3-30b-a3b-fp8$0.09$0.45$0.009

Capabilities

  • Reasoning
  • Tool calling
  • Open weights
  • In: text
  • Out: text
Released: 2026-01Family: qwen

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