Qwen logo

Qwen AI models

24 Qwen models on FastRouter, all behind one OpenAI-compatible API. Compare pricing, context windows and benchmarks, then open any model for its providers and code samples.

Filter in catalog
Models
24
Largest context
1.05M
Qwen3.8 Max
Lowest input /1M
$0.08
Qwen3 32B
Top intelligence
20.1
Qwen3.8 27B

All Qwen models

Qwen logo

Qwen-Image 2.1 Turbo is the fast, lowest-cost tier of the Qwen-Image 2.1 series and the most balanced and cost-effective model in the Qwen-Image line, supporting both text-to-image (T2I) and image-to-image/editing (I2I). Image editing accepts up to 10 reference images, and the model can automatically decide whether to output a standard image or one with a transparent (alpha) channel based on the prompt. It generates 1-6 images per request, with output resolution from 512x512 up to 2048x2048 (PNG) and aspect ratios from 1:8 to 8:1. Negative prompts are not supported.

qwen/qwen-image-2.1-turboOct 9, 2026
Context
4K
Price /1M
— in$0.016/img out
Elo
1025
Qwen logo

Qwen3.8-Flash is Qwen's fast, low-cost model with a one-million-token context window, billed at a flat rate across the entire window.

qwen/qwen3.8-flashAug 26, 2026
Context
1M
Price /1M
$0.11 in$0.38 out
Intel
—
Qwen logo

Qwen-Image 3.0 Pro is the high-quality tier of the Qwen-Image 3.0 series, offering stronger text rendering, more realistic textures, and better semantic adherence for both text-to-image (T2I) and image-to-image/editing (I2I). Output resolution ranges from 512x512 up to 2048x2048 (PNG).

qwen/qwen-image-3-proAug 5, 2026
Context
4K
Price /1M
$0.003/img in$0.04/img out
Elo
1095
Qwen logo

Qwen-Image 3.0 is a general-purpose image generation and editing model that balances quality and speed. It excels at complex text rendering (multi-line, paragraph-level layouts), fine detail, and realistic textures, and supports both text-to-image (T2I) and image-to-image/editing (I2I) on DashScope's multimodal-generation endpoint.

qwen/qwen-image-3Jul 21, 2026
Context
4K
Price /1M
$0.003/img in$0.03/img out
Elo
1076
Alibaba logo

Qwen3.7-Plus is the cost-efficient model in Alibaba's Qwen3.7 series, taking text and image input with a 1M-token context window, hybrid reasoning and tool calling for chat, coding and agent workloads.

qwen/qwen3.7-plusJun 3, 20265.7s latency
Context
1M
Price /1M
$0.40 in$1.60 out
Intel
—
Qwen logo

Qwen3.7-Max is the largest and most capable model in the Qwen3.7 series, a next-generation flagship designed for agent-centric work.

qwen/qwen3.7-maxMay 21, 20262.8s latency
Context
256K
Price /1M
$2.50 in$7.50 out
Intel
—
Qwen logo

Qwen3.6-27B is a dense 27B model from the Qwen3.6 series for coding and general-purpose reasoning.

qwen/qwen3.6-27bApr 27, 20261.2s latency
Context
262K
Price /1M
$0.32 in$3.20 out
Intel
—
Qwen logo

Qwen3.6-35B-A3B is Alibaba's Mixture-of-Experts model with 35B total and 3B active parameters (256 experts), prioritizing stability and real-world utility for coding.

qwen/qwen3.6-35b-a3bApr 18, 2026
Context
262K
Price /1M
$0.10 in$0.95 out
Intel
—
Alibaba logo

Qwen3.6 Plus combines linear attention with sparse Mixture-of-Experts routing for efficient long-context inference. It accepts text, image and video input, supports a 1M-token context window, and offers hybrid reasoning and tool calling.

qwen/qwen3.6-plusApr 2, 2026
Context
1M
Price /1M
$0.50 in$3.00 out
Intel
—
Qwen logo

Qwen3.5-9B uses a hybrid Gated Delta Networks and sparse MoE architecture with a 262K context window, thinking mode, tool calling and multi-token prediction.

qwen/qwen3.5-9bMar 10, 2026
Context
262K
Price /1M
$0.10 in$0.15 out
Intel
—
Qwen logo

Qwen3.5-35B-A3B is an efficient MoE model (35B total, 3B active) with a 262K context window, thinking mode, tool calling and 201 languages.

qwen/qwen3.5-35b-a3bFeb 25, 2026
Context
262K
Price /1M
$0.14 in$1.00 out
Intel
—
Qwen logo

Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model with a 262K context window (extensible to 1M), thinking mode, tool calling, multi-token prediction and 201 languages.

qwen/qwen3.5-27bFeb 25, 2026
Context
262K
Price /1M
$0.26 in$2.60 out
Intel
—
Qwen logo

Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 MoE model (397B total, 17B active) with a 262K context window, thinking mode, tool calling and support for 201 languages.

qwen/qwen3.5-397b-a17bFeb 16, 20261.5s latency
Context
262K
Price /1M
$0.45 in$3.00 out
Intel
—
Qwen logo

Qwen Image 2512 is an improved version of Qwen Image with better text rendering, finer natural textures, and more realistic human generation. This 20B MMDiT model achieved top ranking among open-source models after 10,000 blind comparison rounds on AI Arena, released December 31, 2025, and is licensed under Apache 2.0.

qwen/qwen-image-2512Dec 31, 2025
Context
4K
Price /1M
— in$0.02/img out
Elo
999
Qwen logo

Qwen3-VL 30B A3B is a compact vision-language MoE model in the Qwen3-VL series with strong visual perception, reasoning and agent capabilities.

qwen/qwen3-vl-30b-a3b-instructOct 6, 2025
Context
262K
Price /1M
$0.15 in$0.60 out
Intel
—
Qwen logo

Qwen3-VL is the most powerful vision-language model in the Qwen series, with upgrades in text understanding, visual perception and reasoning, longer context, spatial and video comprehension, and agent interaction.

qwen/qwen3-vl-235b-a22b-instructSep 23, 2025
Context
262K
Price /1M
$0.20 in$0.88 out
Intel
—
Qwen logo

Qwen3-Next is a next-generation foundation model architecture focused on scaling efficiency for both total parameters and context length.

qwen/qwen3-next-80b-a3b-instructSep 11, 20251.4s latency
Context
262K
Price /1M
$0.09 in$1.10 out
Intel
—
Alibaba logo

Qwen3.8-27B is Alibaba's compact, deployment-friendly open-weight model from the Qwen3.8 generation, released under Apache 2.0. It is a 27.8-billion-parameter dense model using a hybrid decoder that alternates Gated DeltaNet linear attention with grouped-query full attention, with native text, image, and video understanding, a 262,144-token context window, and configurable reasoning effort toggled on or off per request. It targets coding, professional work, research, and long-horizon agentic tasks in a footprint small enough to self-host on high-end consumer hardware.

qwen/qwen3.8-27bAug 14, 2025
Context
262K
From /1M
$0.20$2.50
$0.15 in$1.88 out
Intel
20.1
Alibaba logo

Qwen3.8-Max is Alibaba's flagship sparse mixture-of-experts model, with 2.4 trillion total parameters and approximately 95 billion active per forward pass, accepting text, image, and video input and returning text with a 1M-token context window. Hybrid thinking mode is enabled by default with three reasoning-effort tiers, and pricing is flat across the full context window with no long-prompt surcharge. Target workloads include software engineering, long-horizon agentic work, office productivity, and visual tasks such as turning screenshots or design files into working pages.

qwen/qwen3.8-maxAug 3, 2025
Context
1.05M
Price /1M
$1.65 in$4.95 out
Intel
—
Qwen logo

Qwen-Image is an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing. It supports parallel CFG and LoRA merging (up to 3 LoRAs), configurable inference steps, and an optional turbo mode for faster generation using optimized settings (10 steps, CFG=1.2).

qwen/qwen-imageJul 31, 2025
Context
4K
Price /1M
— in$0.02/img out
Elo
909
Qwen logo

Qwen3-Coder-480B-A35B-Instruct is Qwen3's most agentic code model, with strong agentic coding and browser-use performance comparable to Claude Sonnet.

qwen/qwen3-coder-480b-a35b-instruct-turboJul 23, 2025
Context
262K
Price /1M
$0.30 in$1.00 out
Intel
—
Qwen logo

Qwen3-235B-A22B-Instruct-2507 is the updated non-thinking version of Qwen3-235B-A22B with significant gains in instruction following, reasoning, comprehension, math, science, coding and tool usage.

qwen/qwen3-235b-a22b-instruct-2507Jul 21, 2025
Context
262K
Price /1M
$0.09 in$0.55 out
Intel
—
Qwen logo

Qwen3-Embedding-8B is the largest model in the Qwen3 Embedding series, purpose-built for text embedding and retrieval tasks. It ranks No.1 on the MTEB multilingual leaderboard, supports 100+ languages, and produces embeddings up to 4096 dimensions with support for user-defined output dimensions (Matryoshka Representation Learning) from 32 to 4096. The model is instruction-aware, allowing custom task instructions to be prepended to inputs for improved retrieval performance, and supports a 32K token context length.

qwen/qwen3-embedding-8bJun 4, 2025
Context
33K
Price /1M
$0.01 in— out
Intel
—
Qwen logo

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

qwen/qwen3-32bApr 28, 2025
Context
41K
Price /1M
$0.08 in$0.28 out
Intel
—

Frequently asked questions

Model scores sourced from ArtificialAnalysis

Qwen AI Models: API Pricing & Benchmarks | FastRouter.ai