Runware

Run any AI model at the lowest cost. Pay less, build more. 🔗

[Runware @runware]

Gemini 3.5 Flash is now on Runware 🔥

- Google's strongest agentic & coding model yet
- frontier intelligence, 1M token input limit, 65K token max output
- outperforms Gemini 3.1 Pro on coding & agentic benchmarks
- full tool support: search, code execution, function calling

[Runware @runware]

Launch MiniMax M3: https://t.co/KZH9vOZfs6

[Runware @runware]

Start building with MiniMax’s new flagship open-weight model on Runware’s API now

[MiniMax (official) @MiniMax_AI]

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities

- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- Natively Multimodal from Step Zero

API: https://t.co/fHRdSV7BwZ
Token Plan: https://t.co/BDCycxepZw
🚀New! MiniMax Code: https://t.co/GvB4YiB6Ul

Weights & Tech Report in ~10 Days

[Runware @runware]

Ideogram 4.0 on Runware

[Ideogram @ideogram_ai]

Introducing Ideogram 4.0: the best open image model in the world.

Think it. Make it. Own it.

Download the weights, fine-tune on your own data, and run it on your hardware. Live on every Ideogram plan and the API today.

[Runware @runware]

Launch Ideogram 4.0:

https://t.co/KOGZYdBTP8

[Runware @runware]

Ideogram 4.0 is now on Runware on D0🖌️

- Multilingual text rendering
- JSON prompting for reproducible design workflows
- Bounding-box and composition control for posters, packaging, and branded graphics
- Transparent backgrounds and 2K output

[Runware @runware]

How to best use Aleph 2.0: check our detailed guide

https://t.co/nWbdd9623B

[Runware @runware]

Launch Aleph 2.0:

https://t.co/mDnZz4NLM6

[Runware @runware]

Aleph 2.0 from @Runway ML is now on Runware ✂️

- Edit one frame → change carries through your whole clip
- Only changes what you asked for, everything else stays
- Edits across multiple shots in a single pass
Up to 30s at 1080p

[Runware @runware]

Launch Grok Imagine Video 1.5 Preview: https://t.co/p7L92axTa8

[Runware @runware]

Grok Imagine Video 1.5 Preview is now on Runware 🎬

- #1 on Image-to-Video Arena, +52 Elo vs. 1.0
- Up to 15 seconds at 480p or 720p
- Native audio: music, SFX & dialogue

[Runware @runware]

@toniasamsonova 🔥🔥

[Runware @runware]

Launch Exactly Illustrative Training:

https://t.co/QUf0DHBhj5

[Runware @runware]

Exactly AI Illustrative Training is now on Runware⚙️

- Train a custom model on your brand's visual style
- 10–50 images produces a reusable brand-aligned model
- Text-to-image + image-to-image with zero style prompting required
- Consistent output across campaigns & products

[Runware @runware]

Launch Claude Opus 4.8: https://t.co/lW7JwEKQ2J

[Runware @runware]

Claude Opus 4.8 is now on Runware 🧠

- Stronger benchmark scores across coding, reasoning & agentic tasks
- 4× less likely to let code flaws pass unremarked
- Fast mode available: same model, with a 2.5× speed boost
- Best-aligned Opus model yet

[Runware @runware]

Launch Nano Banana 2: https://t.co/nz1sFnAVWN

[Runware @runware]

Nano Banana 2 now takes video as input 🍌

- Drop a video, get context-aware images out
- Thumbnails & infographics generated from your footage
- Character and style consistency across frames
- Edit outputs with a reference image + prompt

Feature available on Runware now

[Runware @runware]

Read the guide:

https://t.co/oiyQ46xIaV

[Runware @runware]

How to best use FLUX Virtual Try-On: check our detailed guide

[Runware @runware]

@BFL_ml's FLUX Virtual Try-On is now on Runware on D0👗

- Pass a person image + garment reference to get a photorealistic try-on output
- Works with packshots, model shots & multi-garment canvases
- Built for fashion, e-comm & branded content