tokenstat
tokenstat

Qwen3-Coder 30B-A3B Instruct

alibaba-cn/qwen3-coder-30b-a3b-instruct · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.053
$/MTok · models.dev
Cheapest output
$0.222
$/MTok
Context
262K
tokens
Offers
10
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.devcheapestqwen3-coder-30b-a3b-instructCortecs$0.053$0.222$0262K
models.devqwen3-coder-30b-a3b-instructOVHcloud AI Endpoints$0.07$0.26$0262K
models.devqwen3-coder-30b-a3b-instructLLM Gateway$0.07$0.27$0262K
models.devqwen3-coder-30b-a3b-instructHelicone$0.1$0.3$0262K
models.devqwen3-coder-30b-a3b-instructNanoGPT$0.1$0.4$0128K
LiteLLMqwen3-coder-30b-a3b-instruct$0.15$0.6$0.015
models.devqwen3-coder-30b-a3b-instructScaleway$0.2$0.8$0128K
models.devqwen3-coder-30b-a3b-instructAlibaba / Qwen$0.216$0.861$0262K
models.devqwen3-coder-30b-a3b-instructGreenPT$0.285$1.08$0128K
models.devqwen3-coder-30b-a3b-instructAlibaba / Qwen$0.45$2.25$0262K

Capabilities

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