OpenRouter

openrouter.ai

Platform Stats

Total Models5

Organizations2

Verified Benchmarks0

Multimodal Models1

Pricing Overview

Avg Input (per 1M)$0.50

Avg Output (per 1M)$1.40

Cheapest Model$0.25

Premium Model$1.00

Supported Features

Number of models supporting each feature

web Search

function Calling

structured Output

code Execution

batch Inference

finetuning

Input Modalities

Models supporting different input types

text

5 (100%)

image

1 (20%)

audio

0 (0%)

video

0 (0%)

Models Overview

Top performers and pricing distribution

Pricing Distribution

Input pricing per 1M tokens

$0-1

4 models

$1-5

1 models

Top Performing Models

By benchmark avg

#1Qwen3-Max

72.0%

#2Qwen3-VL-235B-A22B

68.1%

#3Devstral-2-123B

37.5%

#4Qwen3-235B-A22B

12.0%

Most Affordable Models

Qwen3-VL-235B-A22B

$0.25/1M

Qwen3-235B-A22B

$0.25/1M

Qwen3-Max

$0.50/1M

Available Models

5 models available through OpenRouter

			License
#01Qwen3-VL-235B-A22B Alibaba's Qwen3-VL-235B-A22B multimodal MoE model with 235B parameters and 256K context	Alibaba / Qwen	Sep 23, 2025	Apache 2.0
#02Qwen3-235B-A22B Alibaba's Qwen3-235B-A22B MoE model with 235B parameters, 256K context, and hybrid thinking	Alibaba / Qwen	Apr 28, 2025	Apache 2.0
#03Qwen3-Max Alibaba's Qwen3-Max, a proprietary trillion-parameter model with 262K context and hybrid reasoning	Alibaba / Qwen	Sep 5, 2025	Proprietary
#04Qwen3-Coder-480B Alibaba's Qwen3-Coder-480B MoE model with 480B parameters, 256K context, and agentic coding capabilities	Alibaba / Qwen	Jul 22, 2025	Apache 2.0
#05Devstral-2-123B Mistral's Devstral 2 with 123B parameters, 256K context, and strong SWE-bench Verified performance	Mistral AI	Dec 9, 2025	Modified MIT

Resources

Official Website