AI Models Directory

OpenRouter-style model index with deep metadata: pricing, context windows, architecture, and parameters.

Showing 466 - 480 of 548 matching models from 548 total

Qwen
Budget tiertext + image -> text

Qwen2.5-VL-32B is a multimodal vision-language model fine-tuned through reinforcement learning for enhanced mathematical reasoning, structured outputs, and visual problem-solving...

Long contextVisionBudget input
Context128K
Input$0.20 / 1M
Output$0.60 / 1M
Qwen
Budget tiertext + image -> text

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects.

VisionBudget inputHugging Face
Context33K
Input$0.80 / 1M
Output$0.80 / 1M
Qwen
Budget tiertext -> text

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass.

Long contextReasoningTool calling
Context131K
Input$0.46 / 1M
Output$1.82 / 1M
Qwen
Budget tiertext -> text

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass.

Long contextReasoningTool calling
Context262K
Input$0.07 / 1M
Output$0.10 / 1M
Qwen
Budget tiertext -> text

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks.

Long contextReasoningTool calling
Context131K
Input$0.15 / 1M
Output$1.50 / 1M
Qwen
Budget tiertext -> text

Qwen: Qwen3 30B A3B

Standard context

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,...

ReasoningTool callingBudget input
Context41K
Input$0.08 / 1M
Output$0.28 / 1M
Qwen
Budget tiertext -> text

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking.

Long contextReasoningTool calling
Context131K
Input$0.08 / 1M
Output$0.40 / 1M
Qwen
Budget tiertext -> text

Qwen: Qwen3 4B (free)

Standard context

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks.

ReasoningTool callingBudget input
Context41K
Input$0.00 / 1M
Output$0.00 / 1M
Qwen
Budget tiertext -> text

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation,...

Long contextTool callingBudget input
Context160K
Input$0.07 / 1M
Output$0.27 / 1M
Qwen
Budget tiertext -> text

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.

Long contextTool callingBudget input
Context262K
Input$0.22 / 1M
Output$1.00 / 1M
Qwen
Budget tiertext -> text

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.

Long contextTool callingBudget input
Context262K
Input$0.22 / 1M
Output$1.80 / 1M
Qwen
Budget tiertext -> text

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.

Long contextTool callingBudget input
Context262K
Input$0.00 / 1M
Output$0.00 / 1M
Qwen
Budget tiertext -> text

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus.

1M+ contextTool callingBudget input
Context1M
Input$0.20 / 1M
Output$0.97 / 1M
Qwen
Budget tiertext -> text

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows.

Long contextTool callingBudget input
Context262K
Input$0.12 / 1M
Output$0.75 / 1M
Qwen
Budget tiertext -> text

Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B.

1M+ contextTool callingBudget input
Context1M
Input$0.65 / 1M
Output$3.25 / 1M