Kimi K2.6 API
AvailableKimi K2.6 is the general agentic release of the Kimi K2 line, and the Kimi id that appears in the most GitHub files. It is served here by our second upstream provider. On our 2026-11-18 check it answered correctly with thinking on and off, filled a tool call and streamed at about 14 tokens per second, which is slow; we list it for the exact-model case rather than as a default. Thinking returns in reasoning_content and reasoning_effort "none" switches it off.
Quickstart
Set INFERENCE_API_KEY to your key from the API Keys page, then run:
curl https://api.inferenceapis.com/v1/chat/completions \
-H "Authorization: Bearer $INFERENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/Kimi-K2.6",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello! What can you do?"}
]
}'
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.inferenceapis.com/v1",
api_key=os.environ["INFERENCE_API_KEY"],
)
response = client.chat.completions.create(
model="moonshotai/Kimi-K2.6",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello! What can you do?"},
],
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.inferenceapis.com/v1",
apiKey: process.env.INFERENCE_API_KEY,
});
const response = await client.chat.completions.create({
model: "moonshotai/Kimi-K2.6",
messages: [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Hello! What can you do?" },
],
});
console.log(response.choices[0].message.content);
When to use it
- Your code or prompts were written for Kimi K2.6 (it is the most-referenced Kimi id on GitHub) and you want the exact model
- Agentic coding tasks where the K2.6 behaviour is what you tested against
- Speed matters: about 14 tokens per second in our measurement, the slowest chat model here
- You just want a current Kimi: K2.7 Code is faster and K3.1 Pro is stronger
What it costs in practice
| Workload | Cost |
|---|---|
| Chat assistant — 10,000 turns of 800 tokens in, 300 out | $21.49 |
| Long prompts or RAG — 10,000 requests of 8,000 in, 500 out | $101 |
| Generation-heavy — 10,000 requests of 500 in, 2,000 out | $95.90 |
Computed from the live rates below. This is a reasoning model, and thinking is billed as output, so real output counts run above the visible answer; see controlling reasoning to keep that down. There is no subscription or minimum; new accounts start with free credit.
Endpoint
Content-Type: application/json
/openai/v1/… is accepted too, so Groq-style base URLs work with only the host changed.
Model IDs and aliases
Send any of these as model; they all resolve to this model and bill at its rate.
| ID | Note |
|---|---|
moonshotai/Kimi-K2.6 | Canonical |
kimi-k2.6 | Alias |
kimi-k2-6 | Alias |
Request body
| Parameter | Type | Description |
|---|---|---|
model required |
string | Model ID: moonshotai/Kimi-K2.6 — also accepted: kimi-k2.6, kimi-k2-6 |
messages required |
array | Conversation so far. Each item has a role (system, user or assistant) and content. |
max_tokens |
integer | Maximum number of tokens to generate (includes reasoning tokens — use a few hundred or more). |
temperature |
number | Sampling temperature. Higher values give more varied output. |
top_p |
number | Nucleus sampling cutoff. |
stream |
boolean | Stream the response as server-sent events. The final chunk includes usage. |
tools |
array | Tool definitions for function calling (OpenAI format). |
response_format |
object | {"type": "json_object"} for JSON mode. |
stop |
string | array | Sequences where the model stops generating. |
seed |
integer | Seed for more reproducible sampling. |
Response
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"model": "moonshotai/Kimi-K2.6",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hi! I can answer questions, write and edit text, help with code and more.",
"reasoning": "The user is greeting me and asking about capabilities..."
},
"finish_reason": "stop"
}
],
"usage": { "prompt_tokens": 28, "completion_tokens": 17, "total_tokens": 45 }
}
Controlling reasoning
Send reasoning_effort: "none" to switch thinking off. Model families disagree on the parameter for this, and the wrong one is silently ignored, so the gateway accepts one spelling on every model (also "minimal", reasoning: {"enabled": false} and thinking: {"type": "disabled"}) and sends the switch this model honours; the X-Thinking: off response header confirms it. On the Responses API use reasoning: {"effort": "minimal"}. Leave thinking on for multi-step coding and maths; turn it off for extraction, classification, routing and chat. All models compared.
resp = client.chat.completions.create(
model="moonshotai/Kimi-K2.6",
reasoning_effort="none", # thinking off; omit it to let the model reason
messages=[{"role": "user", "content": "Extract the invoice number from: ..."}],
max_tokens=500,
)
print(resp.choices[0].message.content)Token counts are single measurements from September 17, 2026 and vary with the question; the direction is what matters.
Pricing
| Input | $0.98 / 1M tokens |
| Output | $4.55 / 1M tokens |
| Billing | Pay as you go from prepaid credits. No subscription, no daily request or token cap. See all pricing. |
Notes
- Slow: 14 tokens per second and about half a second to the first token in our measurement. Stream it, and prefer Kimi K2.7 Code (same family, several times faster here) unless you need K2.6 itself.
- JSON mode was not tested on this host; tool calling was and passed.
Compare Kimi K2.6 with…
Errors
Errors use the OpenAI envelope: {"error": {"message", "type", "code"}}. 401 missing or invalid key · 402 insufficient_balance · 404 model_not_found · 503 model_unavailable · 502 backend error, safe to retry. Full table with what to retry: API documentation. Errors from other providers: provider error reference.
