Currently, there are eight models, model selection, and pricing categories. For detailed prices, please refer to the Model Plaza. Includes complete inspection steps, practical verification, and error handling.

Current models and prices

Please check the specific price, availability status, and call name of the modelModel Square。 Applications should also use their own call key requests /v1/models, subject to actual returns and key restrictions.

Currently open models

The above is the open list from this document compilation and does not guarantee permanent future availability. When the model is upgraded, upstream resources or changes in the site's access scope, the current page and actual response shall prevail.

How to start choosing

You can use it for the first time you want to connect gpt-6-luna Complete short text requests, then compare output, time, and consumption with other models based on your actual tasks. You don't guarantee the quality of each task just by model name, nor do you assume that expensive models will always suit your scenario.

How to read prices

• Input: The text you submit is in the necessary conversational context.
• Cache input: the portion that meets the model and upstream cache rules is priced according to the corresponding category; You can't guarantee the cache will hit every time.
• Output: Measurement of model-generated content.
• Long context: Use the price for the corresponding upper and lower document slots.

1 Word Knife (1 DK) = the amount of tokens used in the selected commercial API reference price, worth $1. Its full English name is Doken. Each model's input, output, cache, and long upload and lower document positions are generated DK according to the published reference unit price and quantity, with no duplicate counting; 1 DK does not have a fixed number of tokens.

Currently, the site calculates the RMB value of the user's purchased balance at a recharge price of 0.30 yuan/DK; this is not the platform's exact subscription cost. Platform costs cover exactly the same batch of tokens, with additional USDs allocated according to Codex subscription bills and actual usage, then converted to local currency at a specified exchange rate; See details for detailsDoken explains in three steps。 User grouping multipliers are unified at 1; cache and long context pricing categories are not special user multipliers.

Interfaces and functional range

Plain text requests for Chat Completions and Responses are currently available. The appearance of model names on the plaza or homepage presentation does not mean that tools, networking, images, audio, video, and other functions are now available. See you at the full boundaryUsage rules。

Checklist before practical use

1. Prepare your own account and access keys, and do not use others' shared credentials.
2. Records client versions, systems, and models to be used for easy reproduction during troubleshooting.
3. Save the original configuration or screenshot, hide keys, verification codes, and private content.
4. Confirm that testing may consume a small amount of DK, starting with a single sentence and a single request.
5. Review the current model plaza and status page before deciding whether to enable more features.

Detailed investigation: narrow down the scope of the problem in order

First, confirm that the account is complete, the key is valid, and the DK balance is sufficient, then verify the protocol, address, and model. Make a minimum text request using the same key; Only after it succeeds does it restore attachments, tools, or automatically retry each item. After saving the client configuration, reopen the session to avoid using the previous vendor in the old session.

How to confirm that this section has been learned

Don't just check the "Configuration saved successfully" prompt. You should be able to clearly state the current Base URL, key usage, chosen model, and request protocol, and be able to verify your operation results on the corresponding console. The client-side tutorial uses a single actual plain text response and corresponding logs as the initial completion standard; Account tutorials are based on comprehensive security information; The billing tutorial uses the correspondence between principal, channel fees, and DK as the standard.

If an error occurs, record the occurrence time, HTTP status, content of the anonymized error, and the actual expected result. Do not screenshot the entire page key, and do not give the password or verification code to others. For 401, authentication should be resolved first; for 400, parameters should be resolved first; for 429, intensive retries should be stopped; for 404, request paths and upstream verification should be verified; recharging cannot resolve all errors.

A small task suitable for practice

Complete the minimum steps in this section in your own testing environment, recording in text "how you originally set it, which item you modified, and what results you saw." Do not treat production data, real payments, or irrecoverable commands as exercises. If you encounter features beyond what this section offers, first check the corresponding protocol tutorial before considering adding features; Changing only one configuration at a time makes it easy to judge which step leads to errors.

The next step is the boundary of the version

Return to the full learning map · Streamlined API site configuration · Real-time status of this site。

The tutorial was compiled on October 9, 2026. The specific interface and capabilities may vary depending on the client and upstream versions; The configuration guidelines do not mean that all client versions have passed the test. For balance payments, QQ / Alipay login, and open channels, please refer to the actual page page; Compression interfaces: Previously, upstream 404 and raw image channels were not available, so don't assume configuration files can be automatically removed.