ModelGo (@ModelGo_AI) header
ModelGo (@ModelGo_AI) profile picture

One gateway for model access and enterprise AI governance. šŸ  Discord: https://teapawt.org/t.co/GKq7D6lCKW

Singapore
Joined October 2026
Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)Photo by ModelGo (@ModelGo_AI)
Gemini 4 Neon is now on @ModelGo_AI . Bring documents, images and audio into complex agent workflows. Google DeepMind reports an Artificial Analysis Intelligence Index score of 61 for Gemini 4 Neon at xhigh thinking, placing it #3 overall at that time. Try it: modelgo.ai/models/gemini-4-n… #AI #Gemini #gemini_4 #AI #AImodels @GeminiApp
Starting today, Gemini 4 Neon is available to Google AI Pro and Ultra subscribers on mobile, desktop, and web. This new model excels at work that requires frontier-level reasoning and fast responses. 🧵

1
70
GPT-6.2 Sol is now on ModelGo, with 26% off šŸ”„. Put it to work on everyday coding and agent tasks. In OpenAI’s launch chart, GPT-6.2 Sol shows higher BenchCAD 2.1 Core scores than GPT-6.1 Sol at comparable evaluated costs. Try it: modelgo.ai/models/gpt-6.2-so…
Replying to @OpenAI
GPT-6.2 Sol—an efficient and versatile model for everyday work. It powers through multistep agentic workflows, writes clearly and naturally, and is intuitive to collaborate with. Many OpenAI employees use GPT-6.2 Sol as their go-to model across technical and non-technical work.
2
79
GPT-6.2 Astra is now on ModelGo, with 26% off. Try it for complex coding and professional projects. Try it: modelgo.ai/models/gpt-6.2-as…
Replying to @OpenAI
GPT-6.2 Astra—a frontier model built for your hardest projects. It sets new highs on evals across professional work and scientific research at less than a third of the cost per task of GPT‑6 Astra. You’ll see the difference in things like slideshows, websites, and 3D designs.
1
71
āš ļø Please note: If you experience any issues with billing, models, or API calls while using modelgo.ai, please first check the logic in your agent’s code. If the issue persists, please: 1ļøāƒ£ Visit our Discord community: discord.gg/tJEwEZRJGc, where our engineers are online every day to help. 2ļøāƒ£ Email [email protected] or [email protected]. We respond to all support requests within 24 hours. Thanks!
1
34
I used GPT-6.2 Astra on @ModelGo_AI recreate Spain’s Sagrada FamĆ­lia entirely with code. That's amazing!
Some of you have been asking very politely. Some of you have just been asking. GPT-6.2 Astra and Sol are now available. Super efficient and built to perform where it counts—the real world. openai.com/index/introducing…
2
2
113
MausBot now speaks ModelGo 🐭⚔ Connect one API key, choose a different model for each bot, and keep its tools, computer use, and reasoning workflow intact. Try it in Settings ↓ Get a ModelGo key: modelgo.ai Get MausBot: mausbot.com
Replying to @ModelGo_AI
@ModelGo_AI is now in MausBot. One API key, every model: Gemini, DeepSeek, Grok, Kimi, Qwen, GLM, MiniMax and more. • Paste your key in Settings → AI • Give every bot its own model • They keep their tools, computer use and thinking
2
85
Qwen4-Max is now on @ModelGo_AI for developers building coding and document agents. It combines native vision with a one-million-token context window. In its Nov 16 evaluation, Qwen reports 75.7 on DeepSWE v1.1 for Qwen4-Max, versus 69.3 for Qwen3.8-Max-0902. Input is $1.8182 and output $5.4545 / 1M tokens. Try it: modelgo.ai/models/qwen4-max #AI #AIModels #API #qwen4 @Alibaba_Qwen
šŸ“¢ Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery! Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window. Highlights: - Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation. - Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables. - Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery. - $1.5/M tokens for input, $4.5/MĀ tokens for output, and $0.075/M tokens forĀ implicitĀ caching — allĀ lower than Qwen3.8-Max, withĀ implicit cachingĀ downĀ by 70%. The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder. Start building today! šŸš€ - Blog: qwen.ai/blog?id=qwen4-max - API: qwencloud.com/models/qwen4-m… - Token Plan: qwencloud.com/pricing/token-… More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. šŸ‘€
1
138
One link. Endless ways to share. šŸ”— Copy your ModelGo referral link and post it on social, or share it with friends anywhere online. When a friend signs up through your link and tops up $10, you both earn rewards: • You get $5 in model credits + 3%–6% of their paid usage • Your friend gets $2 in exclusive model credits Copy. Share. Earn. #ModelGo #AIModels #ReferralRewards
2
80
How to build a Christmas world with AI šŸŽ„āœØ Try Claude Opus 5.5 on modelgo.ai, with Three.js for the 3D. Start with the scene, refine the lights and details, then add clickable gifts and a camera that follows the tiny train. Iterate in layers. #AI #UXDesign #christmas #AIModels
4
199
Qwen3.8-Max-0902 Qwen3.7-Text-Rerank Qwen3.7-Text-Embedding-Flash Qwen3.7-Text-Embedding are now on ModelGo. Bring text, images and video into your agent workflow. @Alibaba_Qwen #qwen #AIModels #API
3
2
97
Qwen reports a TerminalBench 3.0 score of 29.0, up from 11.3 for the previous Qwen3.8-Max—a concrete improvement in its agentic coding evaluation.
20
Qwen3.8-Max-0902 debuted at #1 on Arena WebDev on Sep 2, 2026. modelgo.ai/models/qwen3.8-ma…
38
怐New on ModelGo怑 šŸ¦• GLM 5.2 Fast Preview Input: $2.4242 / 1M tokens Output: $8.4848 / 1M tokens Cache read: $0.6061 / 1M tokens šŸ¦– Qwen3.8-27B Input: $0.4545 / 1M tokens Output: $1.8182 / 1M tokens Cache read: $0.0909 / 1M tokens Cache write (5 min): $0.5682 / 1M tokens šŸ¦Ž GLM 5.3 Prime Input: $2.4242 / 1M tokens Output: $8.4848 / 1M tokens Cache read: $0.6061 / 1M tokens #glm #qwen #AIModels #AI @Alibaba_Qwen
1
98
🐳 You can now add your ModelGo.ai API key to DS-Bot and access today’s most popular AI models through one OpenAI-compatible endpoint. DS-Bot is an open-source app for building teams of long-lived AI bots, with bot-to-bot collaboration and group chats. Setup guide → modelgo.ai/docs/agents/ds-bo… #AI #AIagent #API #AImodels #DeepSeekHarness #DSBot #modelgo #personalbot #grokbotalternatives @Fei2411
3
141
MiniMax H3 Image is live on ModelGo. Use up to 16 reference images. Generate or edit in up to 4K. Try it → modelgo.ai/models/minimax-h3… #AI #AIModel #minimaxh3image
1
2
154
Full pricing: • Text in: $2.2727 • Image in: $1.5152 • Image out: $3.7879 All per 1M tokens.
34
ModelGo retweeted
Introducing Grok Bot 1.0. AI teammates that work alongside your whole team. Share Bots, collaborate with them in Slack and Teams, invite them to meetings, and watch them learn and become more helpful.
2,864
1,341
1,024
15,282
56,135,313
ModelGo is now available in MausBot šŸŽ‰@mausbot_ You can now choose ModelGo as your AI provider and access more model options directly inside MausBot. Glad to see the integration live—looking forward to seeing what MausBot users build with ModelGo. Integration doc: modelgo.ai/docs/agents/openm…
As many bots as you like, on Starter. MausBot 0.1.152: • ModelGo, a new AI provider • Make any number of bots: 5 stay awake, 2 work at once • One tap swaps a paused bot in for the one you use least • Advanced mode is back Updates itself.
1
6
443
Fable 5.2 is now live on ModelGo. Built for long-horizon reasoning, agentic coding, and demanding knowledge work. • Input: $8 / 1M tokens • Output: $40 / 1M tokens • Cache reads: $0.20 / 1M tokens Start building → modelgo.ai
4
74