We've partnered with @StainlessAPI to build out our next generation of SDKs. They're the team that helps design and maintain SDKs for companies like OpenAI, Anthropic, and Cloudflare. Together we launched our MCP server, now the Python SDK beta, and soon a new TypeScript SDK.
@replicate
-
Replicate Launches New Python SDK Beta with Full API Support
By
–
We've got a new Python SDK, now in beta. This new SDK makes it even easier to run AI models from your Python code, and it has full support for every operation in our HTTP API. Release notes: https://
github.com/replicate/repl
icate-python-beta/releases/tag/v2.0.0-beta.1
… -
LTX-2 Video Generation Now Available on Replicate Platform
By
–
-
Datalab’s State-of-the-Art Text Extraction Models Now Available
By
–
Datalab's models are state-of-the-art for text extraction, and are based on the popular open-source Marker and Surya projects. They're fast and cost between $2-$6 per 1000 pages.
-
Dumb Things 2.0 AI Hackathon with DigitalOcean and OpenAI
By
–
Because y'all loved the first Dumb Things AI Hackathon, we're running it back with @digitalocean and @OpenAI
! Come join us on Saturday, October 25th for Dumb Things 2.0 AI Hackathon. As always, expect food, prizes, and plenty of vibes Register here: -
Replicate partners with Reve for advanced image generation models
By
–
We're excited to partner with @reve to bring their image models to Replicate Create images with stunning aesthetics, accurate text rendering, prompt adherence, and simple natural-language image edits. Try today: http://
replicate.com/reve -
Veo 3.1: Generate Videos from Image Locations
By
–
Push the bounds of Veo 3.1's built-in logic with image input
— Replicate (@replicate) 17 octobre 2025
"Show me what happens in this location" pic.twitter.com/hD0YZX4mWZPush the bounds of Veo 3.1's built-in logic with image input "Show me what happens in this location"
-
Create seamless before-to-after transitions with first and last frame input
By
–
Use first/last frame input to create seamless before-to-after transitions, like for designing a room: pic.twitter.com/z1DR2arB4W
— Replicate (@replicate) 17 octobre 2025Use first/last frame input to create seamless before-to-after transitions, like for designing a room:
-
Create UGC-Style Videos with Reference Image Input
By
–
Create UGC-style videos with reference image input: pic.twitter.com/4pzi5ZP2xi
— Replicate (@replicate) 17 octobre 2025Create UGC-style videos with reference image input:
-
Sort Models by Creation Date in Replicate HTTP API
By
–
You can now sort models by creation date in our HTTP API. This makes it easier to find the hottest new models programmatically. https://
replicate.com/changelog/2025
-10-08-models-api-sorting
…