kimi-k2.6 API
Use kimi-k2.6 from the Kimi family via RunAPI. Per-call pricing, no subscription, and failed generations are never charged.
# Base URL
https://runapi.ai
# Endpoints
POST /v1/chat/completions
curl https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2.6",
"messages": [
{
"role": "user",
"content": "Plan and implement a small CLI tool: scaffold the project, write the commands, add tests, and run them until they pass."
}
]
}'
from openai import OpenAI
client = OpenAI(
base_url="https://runapi.ai/v1",
api_key="your-runapi-key"
)
response = client.chat.completions.create(
model="kimi-k2.6",
messages=[{"role": "user", "content": "Plan and implement a small CLI tool: scaffold the project, write the commands, add tests, and run them until they pass."}]
)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://runapi.ai/v1",
apiKey: "your-runapi-key"
});
const response = await client.chat.completions.create({
model: "kimi-k2.6",
messages: [{ role: "user", content: "Plan and implement a small CLI tool: scaffold the project, write the commands, add tests, and run them until they pass." }]
});
kimi-k2.6 targets the sweet spot of quality and cost within the Kimi family. It shares the same API key, request shape, and async task lifecycle as every other RunAPI model — switch to this variant by changing one model ID parameter. Install the Kimi skill to load docs, typed schemas, pricing notes, and setup steps into your coding workspace. Billing is metered per completed request in USD with no subscription or minimum spend, and failed generations are never charged.
- Pay-per-call pricing in USD with no subscription
- Failed generations are never charged
- Streaming when supported by the model
- Schema-validated parameters and tool calls
- Switch variant by changing one model ID parameter
- Unified billing across all models and providers
Pricing
Technical details
| Model ID | kimi-k2.6 |
| Provider | Moonshot AI |
| Modality | text |
| Task type | synchronous |
| Billing unit | 1K tokens |
| API endpoint | /v1/chat/completions |
| Commercial license | Yes — included via API |
| Status | Operational |
Model skill — kimi-k2.6
Install the skill once, then use the variant ID from this page while building.
| Endpoint | Protocol |
|---|---|
| /v1/chat/completions | OpenAI compatible |
Use kimi-k2.6 with a model skill
Install
Install the model skill for the %{model} line. The skill loads docs, typed schemas, pricing notes, and setup steps into your coding workspace so your agent has the right context.
Configure
Set the model field to the full model ID shown on this page and configure your RunAPI API key as an environment variable. The same key works across all models and providers.
Call
Use the skill instructions while adding prompt, input, and callback handling to your application. RunAPI routes the request to the provider, manages the async lifecycle, and returns structured JSON.
Receive
Read the task response by polling the task ID, streaming when supported, or handling the webhook callback at your configured URL. Generated outputs are stored and retrievable by task ID.
What's different about kimi-k2.6
1T / 32B active; 256K context; 58.6% SWE-bench Pro; 300-agent swarm
1T / 32B active; 256K context; native multimodal input
Best for
Customer support
Answer customer questions from a private knowledge base, reducing ticket volume.
Document analysis
Draft contract summaries and flag key clauses for attorney review.
Code generation
Auto-generate unit tests, code reviews, and refactoring suggestions in CI.
Frequently asked questions about kimi-k2.6
Is the model ID stable across versions?
Yes. RunAPI keeps the model ID stable and handles compatible version refreshes without changing your request shape. You do not need to update your code when the provider releases a new compatible version.
What's the rate limit on this variant?
Per-key rate limits scale with your usage tier. The pricing page shows current limits. If you need higher throughput, contact support to discuss tier upgrades.
Can I switch variants later?
Yes. Variant is a parameter in the request. Switch by changing the model ID — no code changes, no re-authentication, no separate billing setup. All variants share the same API key and request shape.
Does it stream?
Where streaming is available, RunAPI streams end-to-end. LLM models support token-level streaming. Media models use async task polling or webhook callbacks for result delivery.
Where do I report quality issues?
Open an issue on the public GitHub repo or email support at [email protected]. Include the task ID and model ID so the team can investigate the specific generation.
Do I need a separate provider account?
No. Your RunAPI API key is enough to access this variant and every other model in the catalog. You do not need accounts with the underlying provider.