Models
Comparison
Qwen3 235B vs Kimi K2 Thinking
Qwen3 235B and Kimi K2 Thinking side by side on Silicon Network: context length, capabilities, parameters, and the per-token price of each.
| Qwen3 235B | Kimi K2 Thinking | |
|---|---|---|
| API model id | qwen3-235b | kimi-k2-thinking |
| Base model | Qwen3 235B | Kimi K2 |
| Family | Qwen | Kimi |
| Parameters | 235B MoE | 1T MoE |
| Size class | Very large (200B and up) | Very large (200B and up) |
| Context length | 262,144 tokens (256K) | 262,144 tokens (256K) |
| Capabilities | Text, Reasoning, and Reasoning can be switched off | Text, Reasoning, and Reasoning can be switched off |
| Served weights | 4-bit | As published |
| Weights size | 142 GB | 707 GB |
| Input price | Unavailable | Unavailable |
| Output price | Unavailable | Unavailable |
The published rates could not be loaded just now. The pricing page reads them live.
Differences
- Both have a context window of 262,144 tokens.
- Kimi K2 Thinking is the larger model by total parameters: 1T MoE against 235B MoE.
- Both support the same capabilities: Text, Reasoning, and Reasoning can be switched off.
Whether a model is loaded on a node right now changes through the day; the pricing page shows it live. A model that is not loaded answers 404 until an operator loads it.
About these figures
Context length, capabilities, and weights size come from the model card each id is served with. Rates are the published per-token prices, refreshed every few minutes. There are no speed figures here: the network does not publish per-model throughput yet.
Silicon Network›Models›Qwen3 235B vs Kimi K2 Thinking13 items