Connect to Standard Thinking.

1. Create an API key

Open the console and create a key for your project. Copy the secret when it is shown and store it securely.

export STANDARD_API_KEY="YOUR_STANDARD_API_KEY"

2. Configure your client

Set the Standard Thinking base URL and load your API key from a server-side environment variable.

https://api.standardthinking.ai/v1

3. Check model access

Use GET /v1/models to find the model IDs available to your project. Compare commercial access requirements in the model catalog.

/v1/models

curl https://api.standardthinking.ai/v1/models \
  -H "Authorization: Bearer $STANDARD_API_KEY"

4. Send and read a response

Choose an example below and use a model enabled for your workspace. The JavaScript and Python examples display the streamed text; curl displays the raw streaming events. These examples use deepseek-v4-1-flash.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.STANDARD_API_KEY,
  baseURL: "https://api.standardthinking.ai/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-1-flash",
  messages: [{ role: "user", content: "Explain this architecture." }],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}

Authentication

Authenticate every request with a project API key in the Authorization header.

Authorization: Bearer $STANDARD_API_KEY

Chat completions

/v1/chat/completions

Send a conversation to a supported model. Check its supported inputs and parameters before making a request. Set stream to true for incremental server-sent events.

Request parameters

Response

Cached-input billing and the usage fields that report it differ by provider; how prompt caching is billed on open-model APIs compares them.

Streaming

Streaming responses use server-sent events. Each event carries a partial delta, followed by a final [DONE] marker.

data: {"choices":[{"delta":{"content":"Standard Thinking"}}]}

data: {"choices":[{"delta":{"content":" is ready."}}]}

data: [DONE]

Models

/v1/models

List the models available to your project. For commercial access and pricing, see the model catalog and API rates.

Rate limits

Check the request and token limits that apply to your project and model. Use the documented response headers when handling a limit. Your workspace limits are managed in the console.

Error codes

Use the status code, error details, and request ID to investigate a failed request.

Coding Plan limits and peak-time priority

Every plan includes Kimi K3, GLM-5.3, and DeepSeek V4.1 Flash. Prices are per developer, per month.

Peak-time restrictions apply to every plan, including $200. Requests may slow, queue, or time out. Priority is $200 → $100 → $50. An uncapped usage allowance does not guarantee processing speed or concurrency.

Tools that speak OpenAI chat completions connect with the base URL above. Codex CLI speaks only the Responses API: run a proxy that accepts POST /v1/responses, forwards chat completions with streaming and tool calls intact, and returns usage, then point a model_providers entry in ~/.codex/config.toml at it with wire_api = "responses". Claude Code speaks the Anthropic Messages API; ask about your workflow for setup.

Exact allowances and request and concurrency limits are confirmed before activation. Ask about tool support and setup or compare Coding Plan pricing. The vocabulary of allowances, windows, and priority is defined in capacity and plan terms.

If the first request fails

• Key not accepted: check that the key is valid and loaded in the environment where the request runs.
• Model unavailable: check the model ID and your workspace’s access to that model.
• Request limit reached: follow the documented retry timing for the applicable request or token limit.

For help, contact technical support with the request ID and error details. Do not include your API key.

Review streaming and error handling, compare models, and check API rates before connecting your application.