AI Models

Qwen2.5 Coder 32B Instruct

qwen/qwen-2.5-coder-32b-instruct

Reasoning

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...

Input

10 897/M so'm

$0.86

Output

16 510/M so'm

$1.30

data_array 128K context

Qwen: Qwen Plus 0728

qwen/qwen-plus-2025-07-28

Reasoning

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

Input

4 293/M so'm

$0.34

Output

12 878/M so'm

$1.01

data_array 1,000K context

Qwen: Qwen Plus 0728 (thinking)

qwen/qwen-plus-2025-07-28:thinking

Reasoning

Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.

Input

4 293/M so'm

$0.34

Output

12 878/M so'm

$1.01

data_array 1,000K context

Qwen: Qwen3 14B

qwen/qwen3-14b

Reasoning

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Input

1 651/M so'm

$0.13

Output

3 962/M so'm

$0.31

data_array 132K context

Qwen: Qwen3 235B A22B

qwen/qwen3-235b-a22b

Reasoning

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Input

7 512/M so'm

$0.59

Output

30 048/M so'm

$2.37

data_array 131K context

Qwen: Qwen3 235B A22B Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507

Reasoning

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Input

1 651/M so'm

$0.13

Output

1 651/M so'm

$0.13

data_array 262K context

Qwen: Qwen3 30B A3B

qwen/qwen3-30b-a3b

Reasoning

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Input

1 981/M so'm

$0.16

Output

8 255/M so'm

$0.65

data_array 131K context

Qwen: Qwen3 30B A3B Thinking 2507

qwen/qwen3-30b-a3b-thinking-2507

Reasoning

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

Input

1 321/M so'm

$0.10

Output

6 604/M so'm

$0.52

data_array 131K context

Qwen: Qwen3 32B

qwen/qwen3-32b

Reasoning

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...

Input

1 321/M so'm

$0.10

Output

4 623/M so'm

$0.36

data_array 131K context

Qwen: Qwen3 8B

qwen/qwen3-8b

Reasoning

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...

Input

826/M so'm

$0.07

Output

6 604/M so'm

$0.52

data_array 131K context

Qwen: Qwen3 Coder 480B A35B

qwen/qwen3-coder

Reasoning

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

Input

3 632/M so'm

$0.29

Output

29 718/M so'm

$2.34

data_array 1,049K context

Qwen: Qwen3 Coder 480B A35B (free)

qwen/qwen3-coder:free

free_breakfast Free Reasoning

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

Input

Free

Output

Free

data_array 1,049K context

Qwen: Qwen3 Max

qwen/qwen3-max

Reasoning

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...

Input

12 878/M so'm

$1.01

Output

64 389/M so'm

$5.07

data_array 262K context

Qwen: Qwen3 Max Thinking

qwen/qwen3-max-thinking

Reasoning

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...

Input

12 878/M so'm

$1.01

Output

64 389/M so'm

$5.07

data_array 262K context

Qwen: Qwen3 Next 80B A3B Instruct

qwen/qwen3-next-80b-a3b-instruct

Reasoning

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

Input

1 486/M so'm

$0.12

Output

18 161/M so'm

$1.43

data_array 262K context

Qwen: Qwen3 Next 80B A3B Instruct (free)

qwen/qwen3-next-80b-a3b-instruct:free

free_breakfast Free Reasoning

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

Input

Free

Output

Free

data_array 262K context

Qwen: Qwen3 Next 80B A3B Thinking

qwen/qwen3-next-80b-a3b-thinking

Reasoning

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

Input

1 610/M so'm

$0.13

Output

12 878/M so'm

$1.01

data_array 262K context

Qwen: Qwen3 VL 235B A22B Thinking

qwen/qwen3-vl-235b-a22b-thinking

Reasoning

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....

Input

4 293/M so'm

$0.34

Output

42 926/M so'm

$3.38

data_array 131K context

Qwen: Qwen3 VL 30B A3B Thinking

qwen/qwen3-vl-30b-a3b-thinking

Reasoning

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...

Input

2 146/M so'm

$0.17

Output

25 756/M so'm

$2.03

data_array 131K context

Qwen: Qwen3 VL 32B Instruct

qwen/qwen3-vl-32b-instruct

Reasoning

Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...

Input

1 717/M so'm

$0.14

Output

6 868/M so'm

$0.54

data_array 262K context

Qwen: Qwen3 VL 8B Instruct

qwen/qwen3-vl-8b-instruct

Reasoning

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

Input

1 321/M so'm

$0.10

Output

8 255/M so'm

$0.65

data_array 256K context

Qwen: Qwen3 VL 8B Thinking

qwen/qwen3-vl-8b-thinking

Reasoning

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...

Input

1 932/M so'm

$0.15

Output

22 536/M so'm

$1.77

data_array 256K context

Qwen: Qwen3.5-9B

qwen/qwen3.5-9b

Reasoning

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...

Input

1 651/M so'm

$0.13

Output

2 477/M so'm

$0.20

data_array 262K context