Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of Topaz Denoise Image, Reflection: Beam 1.0 501B A23B, Recraft V4.1 Flash Text to Image
3 modelstopazTopaz Denoise ImageRemove ×reflectionReflection: Beam 1.0 501B A23BRemove ×recraftRecraft V4.1 Flash Text to ImageRemove ×
What’s differentProfessional photo denoising powered by Topaz Labs. Normal, Strong and Extreme presets clean noise at source resolution; Denoise Max adds generative detail recovery. Best for high-ISO and night photography.Apache-2.0 text model with 501B total and 23B active parameters; ships BF16, FP8 and NVFP4 weights.Supply preferred RGB palette colors and a background color directly, alongside the text prompt and custom image dimensions.
DateAug 11, 2026ListedOct 16, 2026ReleasedSep 23, 2026Released
Listed rateSee provider quotes$0.25 in / $1.00 out/ 1M tokensNebius · via OpenRouter · all routes ↗nebius/fp8 · quantization=fp8$0.007/ imagefal · all routes ↗
Provider endpoints0 endpoints →6 endpoints →2 endpoints →
AA Intelligence ↗4.3.2Not reported30.33 ↗Effort not specifiedIndependent resultNot reported
AA-Briefcase ↗1.1Not reported976.2 ↗Effort not specifiedIndependent resultNot reported
GDPval-AA ↗2.1Not reported1,177.08 ↗Effort not specifiedIndependent resultNot reported
AutomationBench-AA ↗AA Index 4.3.2 collectionNot reported48.46% ↗Effort not specifiedIndependent resultNot reported
Terminal-Bench 4.0 · AA ↗Not reported3.03% ↗Effort not specifiedHarness unreportedIndependent resultNot reported
SciCode ↗AA Index 4.3.2 collectionNot reported48.5% ↗AA · Under reviewEffort not specifiedIndependent resultNot reported
Humanity’s Last Exam ↗AA Index 4.3.2 collectionNot reported34.66% ↗Effort not specifiedIndependent resultNot reported
GDP.pdf ↗AA Index 4.3.2 collectionNot reported11.6% ↗Effort not specifiedIndependent resultNot reported
CritPt ↗AA Index 4.3.2 collectionNot reported13.14% ↗AA · Under reviewEffort not specifiedIndependent resultNot reported
AA-Omniscience ↗AA Index 4.3.2 collectionNot reported1.5 ↗Effort not specifiedIndependent resultNot reported
AA-LCR ↗1.1Not reported78% ↗Effort not specifiedIndependent resultNot reported
AA Image ↗2.1Not reportedNot reported949.34 ↗Text-to-image · all categoriesIndependent result95% CI 937.34–961.34 · n=5,770
LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported55.5% ↗Effort: max · single run · equal mean of 7 suitesIndependent resultNot reported
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported67.9% ↗Effort: max · single runIndependent resultNot reported
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported72.8% ↗Effort: max · single runIndependent resultNot reported
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported0% ↗Effort: max · single runIndependent resultNot reported
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported83.9% ↗Effort: max · single runIndependent resultNot reported
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported17.3% ↗Effort: max · single runIndependent resultNot reported
LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported66.4% ↗Effort: max · single runIndependent resultNot reported
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported80.2% ↗Effort: max · single runIndependent resultNot reported
Context window—1M65.5K
Max output—943.7K59K
Parameters—501B—
Tool callingNot reportedSupportedNot reported
Structured outputNot reportedSupportedNot reported
ReasoningNot reportedSupportedNot reported
Prompt cachingNot reportedSupportedNot reported
Open weightsNot reportedSupportedNot reported

Add another model

Search all models →