DEVELOPER DOCS

Integrate in five minutes

OpenAI, Anthropic Messages, Responses and Gemini compatible. Change only the API key, base URL and model name.

Send your first request

Create an API key in the dashboard, then run:

Shell

curl https://api.kimiseek.app/v1/chat/completions \
  -H "Authorization: Bearer $KIMISEEK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash-0731",
    "messages": [{"role":"user","content":"Hello"}],
    "stream": true
  }'

Authentication

Use a Bearer token for every request. Keys start with ks- and can be copied from the dashboard key list.

Security

Never expose an API key in browser code or a public repository.

Supported models and pricing

Copy a model ID from this table into the model field. Rates are KimiSeek's current selling prices for real-time requests.

Model and API ID	Pricing tier	Input	Cached input	Output	Context
DeepSeek V4 Pro 0813`deepseek-v4-pro-0813`Alias: `deepseek-v4-pro`	Peak (01:00–04:00, 06:00–10:00 UTC)	¥6.75	¥0.225	¥20.25	1M
	Off-peak (all other hours)	¥3.375	¥0.1125	¥10.125	1M
DeepSeek V4 Flash 0731`deepseek-v4-flash-0731`Alias: `deepseek-v4-flash`	Off-peak (all other hours)	¥1.125	¥0.0375	¥3.375	1M
	Peak (01:00–04:00, 06:00–10:00 UTC)	¥2.25	¥0.075	¥6.75	1M
DeepSeek V4.1 Flash`deepseek-v4.1-flash`Alias: `deepseek-flash`	Off-peak (all other hours)	¥0.8	¥0.016	¥3.2	1M
	Peak (01:00–04:00, 06:00–10:00 UTC)	¥1.6	¥0.032	¥6.4	1M
DeepSeek V4 Flash Vision Exp`deepseek-v4-flash-vision-exp`	Off-peak (all other hours)	¥0.98	¥0.0196	¥3.92	1M
	Peak (01:00–04:00, 06:00–10:00 UTC)	¥1.96	¥0.0392	¥7.84	1M
GLM-5.3 Flash`glm-5.3-flash`	Standard	¥0.6	¥0.1725	¥2.1	1M
Qwen3.8 Max`qwen3.8-max`	Standard	¥9	¥1.125	¥27	991K
DeepSeek V4.1 Flash 260910`deepseek-v4-1-flash-260910`Alias: `deepseek-v4.1-flash-260910`	Off-peak (all other hours)	¥0.9	¥0.018	¥3.6	1M
	Peak (01:00–04:00, 06:00–10:00 UTC)	¥1.8	¥0.036	¥7.2	1M
GLM-5.3`glm-5.3`Alias: `GLM-5.3`	Standard	¥6	¥1.5	¥21	1.024M
Kimi K3`kimi/kimi-k3`Alias: `kimi-k3`	Standard	¥16	¥1.6	¥80	1.048576M
GLM-5.2`ZHIPU/GLM-5.2`Alias: `glm-5.2`	Standard	¥6	¥1.5	¥21	1M
Qwen3.8 Flash`qwen3.8-flash`	Standard	¥0.64	¥0.08	¥2.16	1M
Qwen3.8 27B`qwen3.8-27b`	Standard	¥2.4	¥0.48	¥9.6	1M
Qwen3.8 2.4T A95B`qwen3.8-2.4t-a95b`	Standard	¥9.6	¥1.2	¥28.8	1M
Qwen3.7 Max`qwen3.7-max`	Standard	¥9.6	¥1.92	¥28.8	991K
Qwen3.6 Plus`qwen3.6-plus`	Input ≤ 256K	¥1.6	Input rate	¥9.6	1M
Qwen3.6 Plus`qwen3.6-plus`	Input > 256K	¥6.4	Input rate	¥38.4	1M
Qwen3.7 Plus`qwen3.7-plus`	Input ≤ 256K	¥1.6	¥0.32	¥6.4	1M
Qwen3.7 Plus`qwen3.7-plus`	Input > 256K	¥4.8	¥0.96	¥19.2	1M

Image model pricing

Image models are billed per generated image. Qwen Image also charges for reference images; Z-Image Turbo uses the higher output rate when prompt enhancement is enabled.

Image model	Input / image	Output / image	Enhanced output / image
Qwen Image 3.0 Pro`qwen-image-3.0-pro`	¥0.016	¥0.2	—
Qwen Image 3.0`qwen-image-3.0`	¥0.016	¥0.144	—
Wan 2.7 Image Pro`wan2.7-image-pro`	¥0	¥0.4	—
Wan 2.7 Image`wan2.7-image`	¥0	¥0.16	—
Z-Image Turbo`z-image-turbo`	¥0	¥0.08	¥0.16

Prices are in CNY per 1M tokens. Plus tiers use input-token count; DeepSeek V4 models use the request start time. View full Batch and explicit-cache pricing

A machine-readable catalog is also available at: GET https://api.kimiseek.app/v1/models

DeepSeek V4 Flash examples

These examples use the canonical ID deepseek-v4-flash-0731; the shorter alias deepseek-v4-flash is also accepted. Both protocols use the same KimiSeek API key.

Shell · OpenAI-compatible

curl https://api.kimiseek.app/v1/chat/completions \
  -H "Authorization: Bearer $KIMISEEK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash-0731",
    "messages": [{"role":"user","content":"Hello"}]
  }'

Shell · Anthropic Messages

curl https://api.kimiseek.app/v1/messages \
  -H "x-api-key: $KIMISEEK_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash-0731",
    "max_tokens": 1024,
    "messages": [{"role":"user","content":"Hello"}]
  }'

Image generation API

Call image models with /v1/images/generations. Set image to HTTPS references or image data URLs when editing.

Shell · Images API

curl https://api.kimiseek.app/v1/images/generations \
  -H "Authorization: Bearer $KIMISEEK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-3.0-pro",
    "prompt": "A red panda reading under a cedar tree",
    "size": "1024x1024",
    "n": 1
  }'

Use the official OpenAI SDK

Change only model to switch providers. Each request is routed to the upstream configured for that model.

TypeScript · OpenAI SDK

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.KIMISEEK_API_KEY,
  baseURL: "https://api.kimiseek.app/v1",
});

const response = await client.chat.completions.create({
  model: "qwen3.7-plus",
  messages: [{ role: "user", content: "Analyze this code" }],
});

Claude Code and Codex

Configure with CC Switch

Use the CC Switch interface to add KimiSeek as a provider for Codex and Claude Code separately.

Create or copy a KimiSeek API key in the dashboard first. Open API key management
Open CC Switch, select Codex or Claude Code, and add a custom provider, or edit an existing one.
Enter the provider details below. Website and notes are optional and can be left blank.
Provider name
kimiseek
API Key
Your own KimiSeek API key (starting with ks-)
Default model
glm-5.3-flash
The screenshots use glm-5.3-flash. You can also copy an available model ID from the catalog above.
Enter the API request address (Base URL) shown below for your client. Leave the Full URL switch off.
Click Save, enable KimiSeek in that client's provider list, then restart the client. Configure and enable each client separately if you use both.

Codex

The Codex Base URL must include the /v1 suffix.

API request address · Base URL

https://api.kimiseek.app/v1

CC Switch · Codex · https://api.kimiseek.app/v1 — Codex · Configuration screenshot (click for full size)

Claude Code

The Claude Code Base URL must not include the /v1 suffix.

API request address · Base URL

https://api.kimiseek.app/

CC Switch · Claude Code · https://api.kimiseek.app/ — Claude Code · Configuration screenshot (click for full size)

Claude Code uses the Anthropic Messages compatibility endpoint.

Shell · Claude Code

export ANTHROPIC_BASE_URL="https://api.kimiseek.app"
export ANTHROPIC_AUTH_TOKEN="ks-your-key"
export ANTHROPIC_MODEL="deepseek-v4-pro-0813"

claude

Codex uses the Responses API and reads KIMISEEK_API_KEY from the environment.

TOML · Codex

model = "qwen3.7-max"
model_provider = "kimiseek"

[model_providers.kimiseek]
name = "KimiSeek"
base_url = "https://api.kimiseek.app/v1"
env_key = "KIMISEEK_API_KEY"
wire_api = "responses"

Gemini protocol

generateContent and streamGenerateContent are supported; pass the key with x-goog-api-key.

Streaming

Set stream: true for standard SSE. Generated usage is settled when the stream completes or is interrupted.

Error codes

400Invalid request or model name401Invalid API key or exhausted quota402Insufficient CNY balance503Model channel unavailable

CNY billing

Input, cached input and output tokens are multiplied by their rates and settled entirely in CNY.