Agents-A1 Models by Intern Science
1 model2026Up to 262k ctx
Details
ResearcherIntern Science
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2026
Max context262k
Capabilities
VisionAll models
MultimodalAll models
ReasoningAll models
Function CallingAll models
Tool UseAll models
About
Agents-A1 is Intern Science's open-source 35B-A3B Mixture-of-Experts family for long-horizon agentic work across search, engineering, scientific research, instruction following, and tool calling.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
Agents-A1Current
Use when the workload needs 262k context, reasoning, and tool use.
2026-06262k contextreasoningtool use
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Agents-A1 | Use when the workload needs 262k context, reasoning, and tool use. | 2026-06 | 262k contextreasoningtool use | Current |
Release Timeline
1 release group2026-06
1 current
Agents-A1
Current262k contextreasoningtool use
Specifications(1 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | Fn Calling | Tool Use |
|---|---|---|---|---|---|---|---|---|
| Agents-A1 | 2026-06 | 262k | 35B total, 3B active | Yes | Yes | Yes | Yes | Yes |
Frequently Asked Questions
- What is Agents-A1 used for?
- Agents-A1 is used for agents, vision, and vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
- How does Agents-A1 compare to MOSS-Audio?
- Agents-A1 by Intern Science is strongest where you need agents, while MOSS-Audio by MOSI AI is the closest related family to check for multimodal. Agents-A1 has 1 listed variant and reaches up to 262k context, so compare the specs and pricing tables before choosing a production model.
- Which Agents-A1 model should I use?
- If price is the main constraint, use the pricing table first because Agents-A1 does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Agents-A1 with 262k context and reasoning, tool use, function calling, and multimodal inputs.
