Side by side

See the difference.

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

Scroll to compare models →

Comparison of Inkling-Small, Ideogram V4.5 Text to Image
2 modelsthinkingmachinesInkling-SmallRemove ×ideogramIdeogram V4.5 Text to ImageRemove ×
What’s differentInkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable…Generate high-quality images, posters, and logos with Ideogram 4.5, with accurate text rendering and low, medium, or high quality tiers.
DateJul 27, 2026ListedSep 30, 2026Released
Listed rate$0.45 in / $1.20 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗See provider quotes
Provider endpoints4 endpoints →1 endpoint →
AA Image ↗2.1Not reported1,015.68 ↗Text-to-image · all categories · quality=highIndependent result95% CI 1,000.68–1,030.68 · n=2,634
Context window524.3K—
Max output262.1K—
Parameters——
Tool callingSupportedNot reported
Structured outputSupportedNot reported
Image inputSupportedNot reported
Audio inputSupportedNot reported
ReasoningSupportedNot reported
Prompt cachingSupportedNot reported
Open weightsSupportedNot reported

Add another model

Search all models →