One catalog
Use text, image and video models through one account.
- —
- Models
- —
- Providers
- —
- Modalities
- 1
- Unified API
View all models
Native protocols
Keep OpenAI and Anthropic request formats where supported.
Transparent pricing
Compare ArgoLink and official prices before you send a request.
Visible usage
Review token usage, requests and cost from the console.
Model catalog
Featured Models
QUICK START
Start in Three Steps
Sign In
Open your user center to view only your own balance, access, and usage.
Issue a Key
Name the key, set its limits, and use every enabled model.
Switch the URL
Set the API Base URL in your client and keep its native protocol.
Kimikimi-k2.7-code
Kimi model optimized for coding
$0.76/ 1M input tokens-20%$0.95official price
- Thinking always enabled
- Only one valid thinking shape
- Code-oriented Kimi route
- Modality
- Text
- Endpoint
- /v1/responses
- Model ID
- kimi-k2.7-code
- Provider
- Kimi
Kimi K2.7 Code API overview
Documented endpoint
Text requests go to /v1/responses. The parameter table below lists the fields this surface documents.
Model provider
Kimi K2.7 Code is published by Kimi and is called through the API model ID kimi-k2.7-code.
Kimi K2.7 Code API pricing
تُحتسب تكلفة Kimi K2.7 Code أقل بنسبة 20% من السعر الرسمي في كل بند أدناه.
| Item | ArgoLink rate | Official price | You save |
|---|---|---|---|
| Input tokens | $0.76 / 1M tokens | -20% | |
| Cached input tokens | $0.152 / 1M tokens | -20% | |
| Cache write tokens | $0 / 1M tokens | -20% | |
| Output tokens | $3.2 / 1M tokens | -20% |
Kimi K2.7 Code API reference
Create an API key in the console, then use the Base URL, endpoint, and request body shown on this page.
bashPOST /v1/responses
curl -sS https://54-151-42-83.sslip.io/v1/responses \
-H "Authorization: Bearer $ARGOLINK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2.7-code",
"input": "Explain what this model is good at in one sentence.",
"stream": false
}'pythonPOST /v1/responses
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["ARGOLINK_API_KEY"],
base_url="https://54-151-42-83.sslip.io/v1",
)
response = client.responses.create(
model="kimi-k2.7-code",
input="Explain what this model is good at in one sentence.",
)
print(response.output_text)javascriptPOST /v1/responses
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.ARGOLINK_API_KEY,
baseURL: "https://54-151-42-83.sslip.io/v1",
});
const response = await client.responses.create({
model: "kimi-k2.7-code",
input: "Explain what this model is good at in one sentence.",
});
console.log(response.output_text);Kimi K2.7 Code request parameters
| Parameter | Type | Requirement | What it does |
|---|---|---|---|
model | string | required | The catalog identifier for this page: kimi-k2.7-code. |
input | string or array | required | The prompt for the recommended Responses request. |
stream | boolean | optional | Set to true to receive incremental events instead of one response. |
tools | array | optional | Tool definitions supported by the selected protocol; see the protocol guide before adding them. |
Kimi K2.7 Code API compared with similar models
| Model | Model ID | Provider | Rate | Best for |
|---|---|---|---|---|
| Kimi K2.7 Code | kimi-k2.7-code | Kimi | $0.76 / 1M input tokens | Kimi model optimized for coding |
| GPT-6 Astra | gpt-6-astra | OpenAI | $8 / 1M input tokens | Hardest end-to-end reasoning and agentic work |
| GPT-5.6 Luna | gpt-5.6-luna | OpenAI | $0.16 / 1M input tokens | Cost-efficient multimodal |
| GPT-5.6 Terra | gpt-5.6-terra | OpenAI | $1.6 / 1M input tokens | Balanced multimodal |
More models from this provider
Other models in this modality
Kimi K2.7 Code API FAQ
How do I call Kimi K2.7 Code through ArgoLink?
Create an API key in the console, then send a request to https://54-151-42-83.sslip.io/v1/responses with the model field set to kimi-k2.7-code and your key in the Authorization header. The quickstart above has a runnable request for each supported protocol.
How much does Kimi K2.7 Code cost?
Kimi K2.7 Code costs $0.76 / 1M input tokens. That is 20% below the official rate of $0.95 for the same unit.
Which API protocols work with Kimi K2.7 Code?
Kimi K2.7 Code is reachable over the OpenAI Responses protocol, the OpenAI Chat Completions protocol and the Anthropic Messages protocol, using the model ID kimi-k2.7-code. Any client that can point at a custom base URL works without a vendor SDK change.
What exactly is billed for Kimi K2.7 Code?
Tokens. Input, output and, where the table above lists them, cached-input and cache-write tokens are metered separately at the rates shown, and settled against the usage the request reports.
How should I send the thinking field to Kimi K2.7 Code?
Omit it. If you send it explicitly the only valid shape is {"type":"enabled","keep":"all"}. Thinking is always enabled and reasoning_effort is unsupported.
What happens if I send thinking.type=disabled?
Do not. The current upstream compatibility layer may return HTTP 200 while changing the response model to auto, which no longer satisfies a fixed-model contract.