Kimi k2 vs Kimi K2.5
Live API pricing and availability, side by side. Both models run on FastInfra's OpenAI-compatible endpoint — switching between them is a one-line change.
Pricing
Price per 1M tokens
Prices are live and sync automatically from wholesale providers.
| Kimi k2 | Kimi K2.5 | |
|---|---|---|
| Input | $0.60 | $0.47 |
| Output | $2.42 | $2.36 |
| Default provider | OpenRouter | DeepInfra |
| Providers available | 1 | 3 |
On input tokens, Kimi K2.5 is currently 1.3× cheaper than Kimi k2 on FastInfra. Output-token pricing and quality trade-offs differ per workload — test both with the free tier.
Quickstart
Try both in 30 seconds
Same endpoint, same SDK — only the model string changes.
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")
for model in ["moonshotai/kimi-k2", "moonshotai/kimi-k2.5"]:
response = client.chat.completions.create(
model=model,
messages=[{"role": "user", "content": "Hello!"}]
)
print(model, "->", response.choices[0].message.content)