kimi-k2.7-code
unofficialchat
kimi-k2.7-code specifications
| Context window | 262K |
|---|---|
| Max output tokens | — |
| Release date | — |
| Input | Text, Image |
| Output | Text |
kimi-k2.7-code pricing in rubles
You pay for what you use, per token and per unit. The final request cost is returned in the API response.
| Type | Price |
|---|---|
| Input tokens | 190 ₽ per 1M tokens |
| Output tokens | 800 ₽ per 1M tokens |
| Cache read | 38 ₽ per 1M tokens |
Prices are in rubles and may change with exchange rates.
What kimi-k2.7-code can do
- Image understanding
- Function calling
- feature.ide
- Reasoning mode
- Streaming responses
kimi-k2.7-code API: connection and code examples
The service exposes a single OpenAI-compatible API. Set our base_url and the key from your dashboard.
OpenAI Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.neuralbridge.ru/v1",
)
response = client.chat.completions.create(
model="moonshotai/kimi-k2.7-code-08130",
messages=[{"role": "user", "content": "Привет! Расскажи о себе."}],
)
print(response.choices[0].message.content)Python (requests)
import requests
response = requests.post(
"https://api.neuralbridge.ru/v1/chat/completions",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "moonshotai/kimi-k2.7-code-08130",
"messages": [{"role": "user", "content": "Привет! Расскажи о себе."}],
},
)
print(response.json()["choices"][0]["message"]["content"])cURL
curl https://api.neuralbridge.ru/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k2.7-code-08130",
"messages": [{"role": "user", "content": "Привет! Расскажи о себе."}]
}'API endpoints
POST /v1/chat/completionsprimary | Chat Completions The main chat endpoint: takes a message history and returns the model reply. Supports streaming and regular modes. |
POST /v1/responses | Responses Alternative chat format with state and structured output. |
POST /v1/messages | Messages Anthropic format: the same chat for clients and SDKs written for Claude. |
POST /v1/converse | Converse Amazon Bedrock Converse format, for clients written against it. |
POST /v1/converse-stream | Converse Stream Streaming variant of the Bedrock Converse format. |
POST /v1/generateContent | Generate Content Google Gemini format, for clients and SDKs written against it. |
POST /v1/streamGenerateContent | Stream Generate Content Streaming variant of the Gemini format. |
Supported request parameters
| Parameter | Default | Allowed values | Description |
|---|---|---|---|
temperature | 1 | — | Controls how varied the answer is: higher values make the output more random, lower values more predictable. |
top_p | 1 | — | Nucleus sampling: only the most probable tokens whose probabilities add up to P are considered. |
max_tokens | — | — | Upper limit on the number of tokens the model may generate in its answer. |
presence_penalty | 0 | — | Penalizes tokens that already appeared in the text, nudging the model toward new topics. |
frequency_penalty | 0 | — | Penalizes tokens in proportion to how often they already appeared — fights repetition. |
stop | — | — | List of stop strings: generation halts as soon as the model produces any of them. |
seed | — | — | Pins randomness: repeating a request with the same seed and parameters returns the same result. |
response_format | — | — | Response format: plain text or strict JSON following a given schema. |
stream | false | — | Deliver the answer as a stream while it is generated instead of one chunk at the end. |
reasoning_effort | — | low, medium, high | Thinking level: how much effort the model spends reasoning before answering. Higher means deeper analysis, more time and more tokens. |
tools | — | — | — |
tool_choice | — | — | — |
parallel_tool_calls | — | — | — |