Qwen 3.8 Max

4 providers

Qwen 3.8 Max is available from 4 providers. The lowest input price is $2 per million tokens from Fireworks AI. It supports up to 1M tokens of context.

Cheapest input ($/M): $2 via Fireworks AI
Cheapest output ($/M): $6 via Fireworks AI
Max context: 1M
Max output: 131.1K
Released: Jul 22, 2026
Open weights: Yes
Input modalities: ImageText
Output modalities: Text

Features

ReasoningToolsStructured outputFilesTemperature

Providers offering Qwen 3.8 Max


Fireworks AI	accounts/fireworks/models/qwen3p8-max	$2	$6	$0.25	-	-
Opper	fireworks/qwen3p8-max	$2	$6	$0.25	-	-
Venice AI	qwen-3-8-max	$2.5	$7.5	$0.3125	1M	131.1K
TrustedRouter	qwen/qwen-3-8-max	$2.6375	$7.9125	-	1M	-

Qwen 3.8 Max

4 providers

Qwen 3.8 Max is available from 4 providers. The lowest input price is $2 per million tokens from Fireworks AI. It supports up to 1M tokens of context.

Cheapest input ($/M): $2 via Fireworks AI
Cheapest output ($/M): $6 via Fireworks AI
Max context: 1M
Max output: 131.1K
Released: Jul 22, 2026
Open weights: Yes
Input modalities: ImageText
Output modalities: Text

Features

ReasoningToolsStructured outputFilesTemperature

Providers offering Qwen 3.8 Max


Fireworks AI	accounts/fireworks/models/qwen3p8-max	$2	$6	$0.25	-	-
Opper	fireworks/qwen3p8-max	$2	$6	$0.25	-	-
Venice AI	qwen-3-8-max	$2.5	$7.5	$0.3125	1M	131.1K
TrustedRouter	qwen/qwen-3-8-max	$2.6375	$7.9125	-	1M	-