Side-by-side comparison
Kimi K2 Thinking vs Devstral Medium
MoonshotAI
Kimi K2 Thinking
🔧 Tools
{} JSON
Input / 1M
$0.6000
Output / 1M
$2.5000
Mistral
Devstral Medium
🔧 Tools
{} JSON
Input / 1M
$0.4000
Output / 1M
$2.0000
| Kimi K2 Thinking | Devstral Medium | |
|---|---|---|
| Provider | MoonshotAI | Mistral |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 262,144 | 131,072 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | tools, json_mode | tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.6000 | 0.4000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 2.5000 | 2.0000 |
Frequently asked questions
Which is cheaper, Kimi K2 Thinking or Devstral Medium?
Devstral Medium is cheaper than Kimi K2 Thinking on a 50/50 input/output blend by about $0.35 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Kimi K2 Thinking or Devstral Medium?
Kimi K2 Thinking has the larger context window at 262k tokens versus 131k tokens for Devstral Medium. That means Kimi K2 Thinking can ingest about 2.0x as much text per request.
What is the difference between Kimi K2 Thinking and Devstral Medium?
Kimi K2 Thinking comes from MoonshotAI; Devstral Medium comes from Mistral. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.