agents-a1-free · intern-ai
Agents-A1 is a 35B Mixture-of-Experts (MoE) agentic model developed by InternScience for complex, long-horizon tasks across search, engineering, scientific research, instruction following, and tool use. The model is trained to scale both long-horizon agent trajectories and heterogeneous agent capabilities through a multi-stage training framework that combines full-domain supervised fine-tuning, domain-specialized teacher models, and multi-teacher on-policy distillation. Agents-A1 supports both text and image inputs and is designed for general-purpose agent workflows that require multi-step reasoning, planning, tool interaction, and sustained task execution.
Agents-A1 is a 35B Mixture-of-Experts (MoE) agentic model developed by InternScience for complex, long-horizon tasks across search, engineering, scientific research, instruction following, and tool use. The model is trained to scale both long-horizon agent trajectories and heterogeneous agent capabilities through a multi-stage training framework that combines full-domain supervised fine-tuning, domain-specialized teacher models, and multi-teacher on-policy distillation. Agents-A1 supports both text and image inputs and is designed for general-purpose agent workflows that require multi-step reasoning, planning, tool interaction, and sustained task execution.
Agents A1 (free) has a 262,144 token context window.
Agents A1 (free) accepts text and image input.
Agents A1 (free) is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to agents-a1-free — no other code changes needed.
Agents A1 (free) is developed by intern-ai. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Agents A1 (free) was released on June 26, 2026 by intern-ai.
Intern-S2-Preview is InternLM’s 35B scientific multimodal foundation model, designed for…
Use Agents A1 (free) via the AIHubMix unified API — one interface for every major LLM.