All times Eastern (ET)Provider pages checked daily at

Qwen models

Every model we track from Qwen, newest release first, with its status, any shutdown date and its standard price per 1M tokens. The latest release months come first; older ones load below. Open a model for its full price table, price history and changelog.

Compare what each model supports on Features; see where each alias points on Aliases and which models are free to call on Free.

All models

Newest release first
ProviderModelReleasedStatusInputOutputCache hit
Release date unknown
QwenQwen Flashqwen-flash—Active$0.05up to 256k prompt$0.40up to 256k prompt$0.01up to 256k prompt
QwenQwen Flash Characterqwen-flash-character—Active$0.05$0.40$0.01
QwenQwen Maxqwen-max—Active$1.60$6.40$0.32
QwenQwen MT Flashqwen-mt-flash—Active$0.16$0.49—
QwenQwen MT Liteqwen-mt-lite—Active$0.12$0.36—
QwenQwen-MT Plusqwen-mt-plus—Active$2.46$7.37—
QwenQwen Plus Characterqwen-plus-character—Active$0.50$1.40$0.10
QwenQwen Plus Character (Japanese)qwen-plus-character-ja—Active$0.50$1.40$0.10
QwenQwen3.5 Flashqwen3.5-flash—Active$0.10$0.40—
QwenQwen3.8 Maxqwen3.8-max—Active$2.00$6.00$0.25
QwenQwen-MT Turboqwen-mt-turbo—RetiredShut down Oct 10, 2026$0.16$0.49—
QwenQwen Turboqwen-turbo—RetiredShut down Oct 10, 2026$0.05$0.20$0.01
QwenQwen3 235B-A22Bqwen3-235b-a22b—RetiredShut down Oct 10, 2026$0.70$2.80—
QwenQwen3 8Bqwen3-8b—RetiredShut down Oct 10, 2026$0.18$0.70—
QwenQwen3-Coder 480B-A35B Instructqwen3-coder-480b-a35b-instruct—RetiredShut down Oct 10, 2026$1.50up to 32k prompt$7.50up to 32k prompt—
QwenQwen3 Coder Plusqwen3-coder-plus—RetiredShut down Oct 10, 2026$1.00up to 32k prompt$5.00up to 32k prompt$0.20up to 32k prompt
QwenQwen3 Maxqwen3-max—RetiredShut down Oct 10, 2026$1.20up to 32k prompt$6.00up to 32k prompt$0.24up to 32k prompt
QwenQwen3.6 Max Previewqwen3.6-max-preview—RetiredShut down Oct 10, 2026$1.30up to 128k prompt$7.80up to 128k prompt—
QwenQwQ Plusqwq-plus—RetiredShut down Oct 10, 2026$0.80$2.40—

USD per 1M tokens, standard tier. Cache hit is the price for input read from the provider's prompt cache. Where a model has prompt-size bands, the lowest band is shown; every band is on the model's page. Released is the day the model came out, or just the month when that's all that's known.