OpenDesign

@OpenDesignHQ

The vibe design workspace for everyone and every team. 90K+ GitHub ⭐ · open-source · by any agent

open-design.ai/?utm_source=tw…

Joined March 2026

65 Following

22.6K Followers

Replies Reposts Media Articles

Pinned
OpenDesign
@OpenDesignHQ
Sep 9
We benchmarked DeepSeek V4.1 Flash by @deepseek_ai . It reached 98% of GPT-6 Astra’s score at 1.4% of the cost on everyday design tasks based on user requests. Every model except Astra scored lower AND cost more. Are open models overtaking closed ones? Full results below ↘️
328
OpenDesign
@OpenDesignHQ
2h
WAIT WE HIT 100K @github STARS? IN JUST 163 DAYS?! github.com/nexu-io/open-d…
2
OpenDesign
@OpenDesignHQ
3h
Claude Haiku 5.5 is live in OpenDesign. $0.018/task. 22% cheaper than DeepSeek V4.1 Flash, in under half the time—with a higher score in our design benchmark. Available on every paid plan, with generous usage allowances both in-app and via API. Results & plan benefits below ↘️
Claude
@claudeai
19h
00:11
Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.
9
OpenDesign
@OpenDesignHQ
Sep 30
We benchmarked GPT-6.1 Sol on everyday design tasks. 90.1/100—our highest design-quality score, at ~24% of GPT-6 Astra’s cost per artifact. Now in OpenDesign Go, with a limited-time usage boost of up to 10× across eligible plans. Full results below ⬇️
OpenDesign
@OpenDesignHQ
Sep 30
GPT-6.1 Sol is now live in OpenDesign Go—with usage that feels nearly unlimited ☀️ Enjoy a limited-time boost of up to 10×—up to $750 worth of Sol usage. API keys included, with more models on the way.
8
OpenDesign
@OpenDesignHQ
Sep 30
GPT-6.1 Sol is now live in OpenDesign Go—with usage that feels nearly unlimited ☀️ Enjoy a limited-time boost of up to 10×—up to $750 worth of Sol usage. API keys included, with more models on the way.
OpenDesign
@OpenDesignHQ
Sep 29
Introducing OpenDesign Go The first benchmark-curated design model plan. $8 first month—20% cheaper than OpenCode Go and Higher usage limits. Up to 300K+ calls/mo. 10 models: GPT-6 Luna, DeepSeek V4.1 Flash and more. Supports API keys. Use Go with OpenCode, Hermes and more.
6