tokenstat
homepricingstatshelpsign in
tokenstat
Alibaba / Qwen

Qwen3 Coder 480B A35B Instruct

Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.2
$/MTok · models.dev
Cheapest output
$0.8
$/MTok
Context
262K
tokens
Offers
5
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-Coder-480B-A35B-Instruct-FP8Submodel$0.2$0.8$0262K
LiteLLMtensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8—$0.45$1.80$0—
models.devQwen/Qwen3-Coder-480B-A35B-Instruct-FP8Together AI$2$2$0.2262K
LiteLLMQwen/Qwen3-Coder-480B-A35B-Instruct-FP8—$2$2$0.2—
LiteLLMQwen3-Coder-480B-A35B-Instruct-FP8—$2$2$0.2—

Capabilities

  • Tool calling
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-04Released: 2025-08-23Family: 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