Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
Efficient Mistral model for fast chat, extraction, and production assistants
Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning
Dense open Qwen model for self-hosted chat, reasoning, and coding
Efficient Mistral-NVIDIA open model for multilingual chat and local deployment
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek |
163.84K | $0.269 | $0.4 | 2025-12-01 | ||
| DeepSeek Reasonerdeepseek/deepseek-reasoner | DeepSeek |
1M | $0.147 | $0.295 | 2025-12-01 | ||
| MoonshotAI: Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | Moonshot AI |
262.144K | $0.6 | $2.5 | 2025-11-06 | ||
| Mistral Small 3.2mistral/mistral-small-2506 | Mistral AI |
128K | $0.1 | $0.3 | 2025-06-20 | ||
| Qwen3 30B A3Balibaba/qwen3-30b-a3b | Alibaba Qwen |
131.072K | $0.08 | $0.29 | 2025-04-28 | ||
| Qwen3 32Balibaba/qwen3-32b | Alibaba Qwen |
131.072K | $0.7 | $2.8 | 2025-04 | ||
| Mistral Nemomistral/mistral-nemo | Mistral AI |
128K | $0.15 | $0.15 | 2024-07-01 |