tokenstat
tokenstat

Qwen3-Next 80B-A3B (Thinking)

alibaba-cn/qwen3-next-80b-a3b-thinking · rates as of · Benchmarks · Plans · Calculator

Qwen reasoning model for deliberate problem solving, math, and coding

Cheapest input
$0.14
$/MTok · LiteLLM
Cheapest output
$1.40
$/MTok
Context
131K
tokens
Offers
7
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
LiteLLMcheapestQwen3-Next-80B-A3B-Thinking$0.14$1.40$0.014
models.devqwen3-next-80b-a3b-thinkingAlibaba / Qwen$0.144$1.43$0131K
models.devqwen3-next-80b-a3b-thinkingLLM Gateway$0.15$1.20$0131K
models.devalibaba/qwen3-next-80b-a3b-thinkingVercel AI Gateway$0.15$1.20$0131K
LiteLLMqwen3-next-80b-a3b-thinking$0.15$1.20$0.015
models.devqwen3-next-80b-a3b-thinkingCortecs$0.164$1.31$0128K
models.devqwen3-next-80b-a3b-thinkingAlibaba / Qwen$0.5$6$0131K

Capabilities

  • Reasoning
  • Tool calling
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-04Released: 2025-09Family: qwen

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