Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows
9 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Open flagship GLM for long-horizon coding agents and million-token context work
81 providers
Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window
6 providers
MiniMax multimodal model for long-context coding, perception, and agent planning
49 providers
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution
26 providers
Open MiMo model for multimodal coding agents and long-context automation
27 providers
Open MoE flagship with million-token context for coding and long agent runs
71 providers
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
68 providers
Open multimodal Llama for strong reasoning with efficient everyday serving
8 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b | 76.5 | 1.04858M | $0.24 | $0.98 | 2026-10-05 | |||
| GLM-5.2zhipuai/glm-5.2 | Zhipu AI |
62.1 | 1M | $1.195 | $4.183 | 2026-06-13 | ||
| LongCat-2.0meituan/longcat-2.0 | 59.5 | 1M | $0.3 | $1.2 | 2026-06-30 | |||
| MiniMax-M3minimax/MiniMax-M3 | MiniMax |
59.0 | 1.04858M | $0.3 | $1.2 | 2026-06-01 | ||
| MiMo-V2.5-Proxiaomi/mimo-v2.5-pro | Xiaomi |
57.2 | 1.04858M | $0.435 | $0.87 | 2026-04-22 | ||
| MiMo-V2.5xiaomi/mimo-v2.5 | Xiaomi |
56.1 | 1.04858M | $0.14 | $0.28 | 2026-04-22 | ||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek |
55.4 | 1M | $0.66 | $1.98 | 2026-04-24 | ||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | DeepSeek |
52.6 | 1M | $0.15 | $0.6 | 2026-04-24 | ||
| Llama 4 Maverick 17B Instructmeta/llama-4-maverick-17b-instruct | Meta |
5.2 | 1M | $0.14 | $0.59 | 2025-04-05 |