Chat & coding
Streaming, tool calls and long context for assistants, agents and coding tools — Cursor, Cline, Claude Code and any MCP client.
apistore.cloudLog inGet API keyDeepSeek, Seedream and Seedance through one OpenAI-compatible API. Change the base URL, keep your code, and pay only for what you use.
from openai import OpenAI
client = OpenAI(base_url="https://api.apistore.cloud/v1", api_key="sk-...")
stream = client.chat.completions.create(
model="deepseek-v4-1-flash",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="")The same API key and base URL for text, images and video. Click a model to try it in the playground; full price list on the pricing page.
Streaming, tool calls and long context for assistants, agents and coding tools — Cursor, Cline, Claude Code and any MCP client.
Text-to-image and image editing through the images endpoint; results come back as links ready to use.
Text, image and video-to-video with reference files, 480p to 4K, priced per second of output. Start a job, poll it, download the result from our storage.
Pictures and videos from the official pages of BytePlus, the maker of these models.





No sales call and no contract. Sign up, create a key and send a request.
Email or Google. Verify your address and claim 2M free tokens.
Create an API key, set a daily spending cap if you like, and add credit by card.
Point your OpenAI SDK, LangChain, MCP client or the apistore CLI at our base URL. No other code changes.
Works with the OpenAI SDKs, LangChain, Cursor, Cline and MCP clients, or from the terminal with the apistore CLI. Chat with streaming and tool calls, plus image and video generation, on the same key.
If a provider is slow or down, your request moves to another one automatically. Failed requests are not charged, and finished jobs are billed on what was actually made.
Top up by card. Every request shows its tokens and cost; set a daily cap on each key.
English, Spanish, Portuguese and Vietnamese. Prices in US$, top-ups by card from US$20, and your working hours fall in DeepSeek's off-peak window, so you pay the lower rate all workday.
Something else? Write to support@apistore.cloud.
Yes. The chat, images and video endpoints follow the OpenAI request and response format. Point the official OpenAI SDK for Python or Node.js, LangChain, Cursor, Cline or any MCP client at our base URL with your apistore API key and keep the rest of your code.
Pay as you go from a prepaid balance: per million tokens for chat models, per image for image models and per second of output for video. There is no subscription and no monthly minimum, and failed requests are never charged. Every model and price is on the pricing page.
Top up by card in US dollars. Prices are shown in US dollars and your balance does not expire.
Chat and coding models such as DeepSeek, image models and video models such as Seedance, served from several providers. If one provider is slow or down, your request moves to another one automatically. The current list is on the pricing page and at /v1/models.
No. Requests and responses pass through in transit only; we keep token counts and cost for billing. Generated images and videos are stored for download for a limited time.
Pay only for what you use. Every request shows its tokens and cost in your dashboard.