LLM Reference

Cosmos 3 Super Text2Image

Researched today

Last refreshed 2026-06-01. Next refresh: weekly.

Open SourceMultimodalVisionOpen SourceImage

Cosmos 3 Super Text2Image has model metadata, but missing tracked provider pricing keeps it from being a default production pick.

Decision context: Vision task fit, 0 tracked provider routes, and research from 2026-06-01.

Use it for

  • Teams evaluating vision
  • Workloads that can use a 4k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Strict JSON or tool-calling flows
  • Teams that need a tracked hosted API route today

Cheapest output

-

No tracked output price

Provider routes

0

No provider route in seed

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-06-01

Researched today

fresh

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

About

Cosmos 3 Super Text2Image is a 64B-parameter fine-tuned variant of Cosmos 3 Super specialized for high-fidelity text-to-image generation. Takes text prompts up to 4096 tokens and outputs JPEG images at 256p, 480p, or 720p in aspect ratios 16:9, 4:3, 1:1, 3:4, or 9:16. Ranked #1 on Artificial Analysis text-to-image leaderboard (open models). Available via Hugging Face Diffusers (DiffusionPipeline) and vLLM-Omni.

Cosmos 3 Super Text2Image has a 4k-token context window.

Capabilities

MultimodalFine-tuning

API Versions

cosmos-3-super-text2image

Rankings

Specifications

FamilyCosmos 3
Released2026-05-31
Parameters64B
Context4k
ArchitectureMixture-of-Transformers fine-tune
Specializationimage-generation
LicenseOpenMDW 1.1
Trainingfinetuned

Created by

Accelerated AI for enterprise solutions

Santa Clara, California, United States
Founded 2015
Website