qwen/ · 32 models
Access 32 Qwen models through AnonRouter's privacy-first gateway, including Qwen 2.5 7B, Qwen 3 235B A22B Instruct 2507, and Qwen 3 235B A22B Thinking 2507. Compare pricing, context windows, and capabilities across Qwen's text, image, audio, embeddings routes — every request anonymized, with no payload logging.
Models
32
Modalities
4
Text, Image, Audio, Embeddings
From (input)
$0.0125
per 1M tokens
Max context
1M
Private routes
23 / 32
not anonymous-only
Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification.
Built for in-depth research and handling long, complex documents. Ideal for technical work, multimodal input, and high-precision tasks.
Built for in-depth research and handling long, complex documents. Ideal for technical work, multimodal input, and high-precision tasks.
Turbo variant of Qwen3 Coder 480B, optimized for faster inference on code tasks.
Optimized for speed and efficiency.
Qwen 3.5 35B A3B is a highly efficient MoE model with 35B total parameters and only 3B active parameters. It surpasses the larger Qwen3-235B-A22B while being 6.7x smaller, excelling at reasoning, coding, and general knowledge tasks.
Qwen 3.5 is Alibaba flagship reasoning model featuring a 397B parameter Mixture-of-Experts architecture with 17B active parameters. It excels at complex reasoning, coding, and general knowledge tasks.
A 9B dense model with 262K native context window (extendable to 1M). Features Gated DeltaNet hybrid attention architecture for efficient long-context processing. Supports 201 languages, thinking/reasoning mode, and function calling.
The Qwen 3.6 27B native vision-language dense model builds upon the 3.5-27B version, with key improvements in agentic coding capabilities and enhanced STEM reasoning and inference skills. In the vision modality, it demonstrates significant advances in spatial intelligence, object localization, and detection, while video understanding, document OCR, and visual agent capabilities continue to improve steadily.
Qwen 3.6 27B FP8 running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.
Qwen 3.6 35B A3B FP8 running in a Trusted Execution Environment (TEE). A fast mixture-of-experts model with ~3B active parameters per token. Hardware attestation evidence is available for independent verification of enclave identity and configuration.
Qwen 3.6 Plus Uncensored is Alibaba's latest flagship reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.
Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.
Qwen 3.7 Plus is Alibaba's latest flagship reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.
Qwen3 30B A3B running in a Trusted Execution Environment (TEE). A MoE model with 30.5B total parameters and 3.3B activated per inference, supporting ultra-long 256K context, with hardware attestation evidence available for independent verification.
Qwen3-VL 235B vision-language model with MoE architecture. The most powerful VL model in the Qwen series with superior visual perception, OCR, and multimodal reasoning.
Qwen3 VL 30B A3B running in a Trusted Execution Environment (TEE). A multimodal model unifying text generation with visual understanding for images and videos, with hardware attestation evidence available for independent verification.
Qwen3.6 35B A3B Uncensored running in a Trusted Execution Environment (TEE). An uncensored variant of Alibaba's Qwen3.6 MoE model with 35B total parameters and ~3B active, supporting 262K context and multimodal input across text, images, and video, with hardware attestation evidence available for independent verification.
Qwen3 32B served through Amazon Bedrock with support for AWS zero-data-retention mode.
Qwen3 Coder 30B A3B Instruct served through Amazon Bedrock with support for AWS zero-data-retention mode.
Qwen3 Coder Next served through Amazon Bedrock with support for AWS zero-data-retention mode.
Qwen3.6 35B A3B served on DeepInfra serverless inference.
Text-to-speech model with 9 voices served through Venice.
Text-to-speech model with 9 voices served through Venice.
Image inpainting and editing model served through Venice.
Image generation model served through Venice.
Image generation model served through Venice.
Image inpainting and editing model served through Venice.
Image generation model served through Venice.
Image inpainting and editing model served through Venice.
Embedding model for semantic search and retrieval, served through Venice.
Embedding model for semantic search and retrieval, served through Venice.
