tokenstat
tokenstat

Qwen3 Coder 480B A35B

qwen/qwen3-coder · rates as of · Benchmarks · Plans · Calculator

Qwen coding model for software agents, repository edits, and code reasoning

Cheapest input
$0.13
$/MTok · models.dev
Cheapest output
$0.5
$/MTok
Context
262K
tokens
Offers
6
3 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-coderNanoGPT$0.13$0.5$0262K
LiteLLMopenrouter/qwen/qwen3-coder$0.22$0.95$0.022
LiteLLMqwen/qwen3-coder$0.22$0.95$0.022
OpenRouterqwen/qwen3-coderOpenRouter$0.3$1$0.1262K
models.devqwen/qwen3-coderFastRouter$0.3$1.20$0262K
models.devqwen/qwen3-coderKilo Gateway$0.975$4.88$0262K

Capabilities

  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-04Released: 2025-07-23Family: 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