Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
28 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
5 providers
Thinking Kimi model for slower research passes, planning, and hard technical questions
23 providers
Dense open Qwen model for self-hosted chat, reasoning, and coding
16 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek |
128K | $0.209 | $0.31 | 2025-12-01 | ||
| DeepSeek Reasonerdeepseek/deepseek-reasoner | DeepSeek |
1M | $0.242 | $0.726 | 2025-12-01 | ||
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | Moonshot AI |
262.144K | $0.4 | $2.5 | 2025-11-06 | ||
| Qwen3 32Balibaba/qwen3-32b | Alibaba Qwen |
131.072K | $0.7 | $2.8 | 2025-04-28 |