Model comparison
Kimi K2.7 Code vs Mistral Medium (latest)
Kimi K2.7 Code (Moonshot) and Mistral Medium (latest) (Mistral) side by side: what each costs per million tokens through Rapid Router, how much context each takes, what each supports, and where independent benchmarks place them. Same API, same key; switching is a one-string change.
| Kimi K2.7 Code | Mistral Medium (latest) | |
|---|---|---|
| Input price per 1M | $2.85 | $1.50 |
| Output price per 1M | $14.25 | $7.50 |
| Context window | 262K tokens | 262K tokens |
| Max output | 262K tokens | 262K tokens |
| Input types | text, image, video | text, image |
| Capabilities | tools, JSON, vision, reasoning | tools, JSON, vision, reasoning |
| Author | Moonshot | Mistral |
What a month costs on each
| Workload | Kimi K2.7 Code | Mistral Medium (latest) |
|---|---|---|
| Chatbot month (15M in, 4M out) | $99.75 | $52.50 |
| RAG month (40M in, 3M out) | $156.75 | $82.50 |
| Coding month (60M in, 10M out) | $313.50 | $165.00 |
On a typical 75/25 input-output mix, Mistral Medium (latest) costs less (about 47% less than Kimi K2.7 Code). Kimi K2.7 Code takes the longer prompt at 262K tokens. Try your own numbers in the cost calculator.
Call either one
curl https://rapidrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $RAPIDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "moonshotai/kimi-k2.7-code", "messages": [{"role": "user", "content": "Hello"}]}'
# the other one: change the model string
-d '{"model": "mistralai/mistral-medium", ...}'Common questions
Which is cheaper, Kimi K2.7 Code or Mistral Medium (latest)?
Mistral Medium (latest) is cheaper on a typical mix of 75% input and 25% output tokens, by about 47%. Through Rapid Router both are billed at the provider list price per million tokens.
Which has the larger context window?
Kimi K2.7 Code, at 262K tokens. Mistral Medium (latest) offers 262K tokens.
Can I switch between Kimi K2.7 Code and Mistral Medium (latest) without changing code?
Yes. Both are callable at https://rapidrouter.ai/api/v1 with the same OpenAI-compatible request; only the model string changes (moonshotai/kimi-k2.7-code or mistralai/mistral-medium).
How do I pay for Kimi K2.7 Code or Mistral Medium (latest)?
Top up a Rapid Router balance by card in US dollars, and both models debit that balance per request.
More Kimi models: Moonshot API pricing · More Mistral: Mistral API pricing