The Serverspace GPT АPI control panel now includes a set of eight modern language models. You can pick the right one for each use case — from chatbots to deep analytics and code-heavy workflows.
Which models are available:
- Claude Opus 4.5 — Anthropic’s flagship model for deep reasoning, long context, research, and complex multi-step tasks.
- Claude Sonnet 4.5 — a balanced model that combines strong reasoning with fast responses, great for advanced assistants and business use cases.
- Claude Haiku 4.5 — a lightweight, fast model for chats, online support, and embedded assistants where speed and cost matter.
- GPT-5.1 — OpenAI’s flagship model for sophisticated assistants, analytics, and production-grade content workflows.
- GPT-5.1 Codex — a GPT-5.1 variant optimized for working with code: helps write, refactor, and understand programs.
- Gemini 3 Pro — Google’s general-purpose model for assistants, smart apps, and search-style scenarios.
- gpt-oss-20b — a mid-sized general-purpose model with a solid balance of quality, speed, and cost for chatbots and internal helpers.
- Qwen3-Next 80B-A3B Instruct — a large model with strong reasoning, suitable for complex multi-step tasks, code, and multilingual workloads.
This lineup lets you match the model to the job: lighter LLMs for high-volume, cost-sensitive tasks like chatbots and internal assistants, and flagship models for heavy analytics, complex multi-step requests, and production-quality output. Everything runs on a single infrastructure and a unified API — no zoo of mismatched tools or painful extra integrations.
To plug LLMs into your services, just log in to the Serverspace control panel, open the GPT API section, pick a model and connect it to your application.