Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Qwen

Qwen3.6 27B Thinking

Qwen3.6 27B is a native vision-language dense model with stronger agentic coding and STEM reasoning than Qwen 3.5 27B. It also improves spatial intelligence (including object localization/detection), plus video understanding, document OCR, and visual-agent workflows.

  • Reasoning
  • Vision
  • Video Input

Added Apr 23, 2026

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.203
Output
$2.24
Cache read
$0.102
Compare provider prices

Specifications

Context window
262.1K
Max output
65.5K
Parameters
27B

Benchmarks

Leaderboard results

These leaderboards tested Qwen3.6 27B, another version of this model.

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 17, 2026

Epoch Capabilities Index

146.7

#76 of 115

FrontierMath v2 (Tiers 1–3)

35.1%

#63 of 83

GPQA Diamond

85.9%

#66 of 119

OTIS Mock AIME 2024–2025

91.1%

#57 of 121

Mystery Game Puzzles

7.0%

#75 of 77

EQ-Bench

EQ-Bench data, MIT · Updated Nov 17, 2026

EQ-Bench 4

1015

#30 of 31

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

27.1

#113 of 149

UGI Willingness

2.8

#93 of 149

UGI Writing

42.5

#78 of 149

Filtered and ranked to models on NanoGPT.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.203$2.24$0.102N/AN/A
Auto
Auto (Anonymized)
$0.203$2.24$0.102N/AN/A
Reka
Reka
UNK
$0.203$2.24N/AN/AN/A
Chutes
Chutes
FP8
US
$0.263$2.10$0.0262N/AN/A
SiliconFlow
SiliconFlow
FP8
SG
$0.315$3.36N/AN/AN/A
DeepInfra
DeepInfra
FP8
US
$0.336$3.36N/AN/AN/A
Uomi
Uomi
GLB
$0.355$3.49N/AN/AN/A
Alibaba
Alibaba
SG
$0.63$3.78N/AN/AN/A
Novita
Novita
US
$0.63$3.78N/AN/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclear
Batch API
ProviderInputOutputCached input
Auto
Autoqwen/qwen3.6-27b:thinking
$0.203/M$2.24/M$0.102/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare Qwen3.6 27B Thinking with similar models from the same provider or model family.

Qwen3.6 27B

qwen/qwen3.6-27b

Qwen3.6 27B is a native vision-language dense model with stronger agentic coding and STEM reasoning than Qwen 3.5 27B. It also improves spatial intelligence (including object localization/detection), plus video understanding, document OCR, and visual-agent workflows.

Qwen3.8 Omni Flash

qwen/qwen3.8-omni-flash

Qwen3.8 Omni Flash is a fast omni-modal reasoning model for understanding text, images, audio, and video. It is especially suited to meeting summaries, transcripts and subtitles, speaker-aware audiovisual analysis, and long-form content review. It returns text and supports a nearly one-million-token context window, tool calling, and structured output.

Qwen3.8 Max 0902

qwen/qwen3.8-max-0902

Qwen3.8 Max 0902 is Alibaba's September 2 checkpoint of its flagship Qwen3.8 Max model for coding, knowledge work, data analysis, and long-running agent workflows. It supports text, image, video, PDF input, selectable thinking, tool calling, structured output, and a near-million-token context window.

Qwen3.8 Flash

qwen/qwen3.8-flash

Qwen3.8 Flash is Alibaba's latest fast multimodal model, with a million-token context window for coding, agentic workflows, visual understanding, long documents, codebases, and videos.

Qwen3.6 Flash

qwen/qwen3.6-flash

Qwen3.6 Flash is Alibaba's fast native vision-language model in the Qwen 3.6 family. It improves over 3.5 Flash with stronger coding/agent performance and better spatial intelligence, including object localization and detection.

Qwen 3.8 27B Antislop

qwen/qwen3.8-27b-antislop

Qwen 3.8 27B Antislop is a creative-writing finetune designed to reduce formulaic prose. Available capabilities include image understanding, tool calling, and optional reasoning, with context windows up to 262,144 tokens.