TOKENROUTER.APP by Augmentable.ai

Visit tokenrouter.app ↗

🔬 Tested by TokenRouter

Same prompt. Every model. Judge for yourself.

We run a fixed set of prompts against every model in the catalog and keep the outputs — so you can compare what they actually produce, not what the docs claim.

The prompt Generate a single red circle on a fully transparent background. Output a PNG with alpha.

flux-2-flex output — flux-2-flex black-forest-labs ✗ failed 10s

flux-2-max output — flux-2-max black-forest-labs ✗ failed 12s

flux-2-pro output — flux-2-pro black-forest-labs ✗ failed 9s

flux-kontext-max output — flux-kontext-max black-forest-labs ✗ failed 9s

flux-kontext-pro output — flux-kontext-pro black-forest-labs ✗ failed 6s

black-forest-labs/FLUX.1-dev output — black-forest-labs/FLUX.1-dev black-forest-labs 2s

FLUX.1 Kontext [max] output — FLUX.1 Kontext [max] black-forest-labs ✗ failed 9s

FLUX.1 Kontext [pro] output — FLUX.1 Kontext [pro] black-forest-labs ✗ failed 6s

FLUX1.1 [pro] output — FLUX1.1 [pro] black-forest-labs ✗ failed 3s

FLUX.2 [dev] output — FLUX.2 [dev] black-forest-labs ✗ failed 13s

FLUX.2 [flex] output — FLUX.2 [flex] black-forest-labs ✗ failed 10s

FLUX.2 [max] output — FLUX.2 [max] black-forest-labs ✗ failed 18s

seedream-4-0-250828 output — seedream-4-0-250828 bytedance ✗ failed 5s

gemini-2.5-flash-image output — gemini-2.5-flash-image google 6s

gemini-3.1-flash-image output — gemini-3.1-flash-image google 7s

gemini-3.1-flash-image output — gemini-3.1-flash-image google 7s $0.0861

gemini-3.1-flash-lite-image output — gemini-3.1-flash-lite-image google ✗ failed 6s

OpenAI: GPT-5 Image output — OpenAI: GPT-5 Image openai 69s

OpenAI: GPT-5 Image Mini output — OpenAI: GPT-5 Image Mini openai 40s

OpenAI: GPT-5.4 Image 2 output — OpenAI: GPT-5.4 Image 2 openai 116s

gpt-image-1 output — gpt-image-1 openai ✗ failed 28s

gpt-image-1-mini output — gpt-image-1-mini openai ✗ failed 31s

gpt-image-1.5 output — gpt-image-1.5 openai ✓ passed 29s

gpt-image-1.5-2025-12-16 output — gpt-image-1.5-2025-12-16 openai ✓ passed 30s

gpt-image-2 output — gpt-image-2 openai ✓ passed 34s

gpt-image-2-all output — gpt-image-2-all openai ✓ passed 37s

gpt-image-2-vip output — gpt-image-2-vip openai ✗ failed 42s

Qwen Image output — Qwen Image qwen ✗ failed 8s

Juggernaut Lightning Flux by RunDiffusion output — Juggernaut Lightning Flux by RunDiffusion rundiffusion ✗ failed 5s

Juggernaut Pro Flux by RunDiffusion 1.0.0 output — Juggernaut Pro Flux by RunDiffusion 1.0.0 rundiffusion ✗ failed 5s

SD XL output — SD XL stabilityai ✗ failed 4s

Outputs generated 2026-08-26. Costs are measured from the provider's own billing where reported. Nothing here is simulated.