Qwen

Qwen 3.8 27B

Qwen 3.8 27B is Qwen’s open-weight dense vision-language model for coding, professional workflows, research, multimodal interaction, and long-running agent tasks.

qwen-3-8-27b

Pricing

~99.9%

Input: $0.000196 / 1,000,000 tokens
Output: $0.002456 / 1,000,000 tokens
Cache read: $0.000049 / 1,000,000 tokens
Cache write: $0.000196 / 1,000,000 tokens

How pricing works

Discount history

99.9%Nov 8, 03:58 AM UTC

Nov 7, 11:59 PMNov 8, 03:58 AM UTC

Model details

Input: text, image, video
Output: text
Context window: 262,144 tokens
Maximum output: 65,536 tokens
Availability: $2.6KUncapped capacity
Updated: 11/8/2026, 4:00:11 AM UTC

Capacity is reserved when your request is accepted.

Capabilities

ChatStreamingWeb searchVisionTool callingReasoningJSON mode

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p