tokenstat
tokenstat

Qwen3.5 397B A17B FP8

Qwen/Qwen3.5-397B-A17B-FP8 · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.6
$/MTok · LiteLLM
Cheapest output
$3.60
$/MTok
Context
262K
tokens
Offers
4
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
LiteLLMcheapestQwen/Qwen3.5-397B-A17B-FP8$0.6$3.60$0
LiteLLMcheapestQwen3.5-397B-A17B-FP8$0.6$3.60$0
LiteLLMcheapesttensormesh/Qwen/Qwen3.5-397B-A17B-FP8$0.6$3.60$0
models.devQwen/Qwen3.5-397B-A17B-FP8Neuralwatt$0.69$4.14$0.1725262K

Capabilities

  • Reasoning
  • Tool calling
  • Open weights
  • In: text
  • Out: text
Released: 2026-02-01Family: 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