Last refreshed 2026-06-29. Next refresh: weekly.
Why use Kimi K2.5 on Vercel AI Gateway?
Vercel AI Gateway offers Kimi K2.5 with pay-as-you-go pricing at $0.60/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Kimi K2.5 across 10 providers to find the best fit for your use caseInput / 1M
$0.60
Output / 1M
$3.00
Cache
read $0.10
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AI_GATEWAY_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],Model ID
moonshotai/kimi-k2.5Request example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="moonshotai/kimi-k2.5",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "moonshotai/kimi-k2.5", not the LLMReference slug "kimi-k2-5".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Kimi K2.5 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | — | — |
| Fireworks AI | $0.60 | $3.00 |
| OpenRouter | $0.44 | $2.00 |
| Together AI | $0.50 | $2.80 |
| NVIDIA NIM | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.60 |
| Output tokens | $3.00 |
Capabilities
VisionMultimodalJSON / Tool useStructured Outputs
About Kimi K2.5
Kimi K2.5 is Moonshot AI's Kimi model focused on code generation and software engineering. It offers a 256K-token context window and scores 87.9 on GPQA.
Get Started
Model Specs
Released2026-03-15
Parameters1T (MoE, 384 experts)
Context256k
ArchitectureMixture of Experts