Best LLMs for Agent Workflows
9 models · ranked by real Agent Workflows usage
Key facts · week of 2026-08-10
The top 3 models (Tencent: Hy3, Xiaomi: MiMo-V2.5, DeepSeek: DeepSeek V4 Flash 0423) account for 31.0% of all usage.
§This week's biggest riser is DeepSeek: DeepSeek V4 Flash 0731, up from #8 to #5.
§The cheapest model in the usage top 10 is OpenAI: GPT-5.6 Luna (batch) at $0.09999999999999999 per 1M input tokens (usage rank #7).
§The largest context window in the top 10 is Xiaomi: MiMo-V2.5 at 1.1M tokens.
§
Cite as: AI Tier List, LLM Usage Rankings (2026-08-10), www.aitierlist.xyz/en/models/agent-workflow-execution — data: OpenRouter
Which model should you pick?
- When quality comes first
- DeepSeek: DeepSeek V4 Flash 0731
- Artificial Analysis agentic benchmark score 48.4 — highest in this ranking
- The proven default
- Tencent: Hy3
- 12.5% usage share — #1 in real usage
- When cost matters
- NVIDIA: Nemotron 3 Ultra (free)
- Cheapest in the top 15 — Free/1M input
- For long docs & codebases
- Xiaomi: MiMo-V2.5
- 1.1M token context window
Full ranking · 9 models
| Rank | Model | Share |
|---|---|---|
1 | Tencent: Hy3 | |
2 | Xiaomi: MiMo-V2.5 | |
3 | DeepSeek: DeepSeek V4 Flash 0423 | |
4 | Z.ai: GLM 5.2 (batch) | |
5 | DeepSeek: DeepSeek V4 Flash 0731 | |
6 | DeepSeek: DeepSeek V4 Pro | |
7 | OpenAI: GPT-5.6 Luna (batch) | |
8 | NVIDIA: Nemotron 3 Ultra (free) | |
9 | MiniMax: MiniMax M3 (batch) |
Model Comparisons
Related AI Tool Tier Lists
Get notified when Agent Workflows rankings move
This ranking refreshes every week. We email you when it moves — once a week, no spam.
FAQ
What is the most-used LLM for Agent Workflows?
Tencent: Hy3 by tencent ranks first for Agent Workflows by real token usage. It accounts for roughly 12.5% of tokens in this segment. Xiaomi: MiMo-V2.5, DeepSeek: DeepSeek V4 Flash 0423, Z.ai: GLM 5.2 (batch) follow.
How are these rankings calculated?
Models are ranked by tokens actually consumed through OpenRouter, not by benchmark scores. This page counts only usage tagged as Agent Workflows tasks. It refreshes weekly and currently tracks 9 models.
Which is the cheapest LLM for Agent Workflows?
Among the paid models in this ranking, OpenAI: GPT-5.6 Luna (batch) is cheapest at $0.10 per 1M input tokens. 1 models in the list are free to use.
Is Tencent: Hy3 still the most-used LLM for Agent Workflows right now?
Yes. As of the week of 2026-08-10, Tencent: Hy3 is #1 by real usage. It climbed from #3 last week. The ranking refreshes weekly, so this page changes as soon as it does.
Which model has the longest context window?
Xiaomi: MiMo-V2.5 has the longest context window in this ranking at 1.1M tokens.
Token usage and share data aggregated by OpenRouter, refreshed weekly. Prices are USD per 1M tokens. Benchmark scores come from Artificial Analysis; models it hasn't measured show —.