Xiaodoubao API is a Chinese AI API relay platform hosted at api.linkapi.org, advertising low-cost and high-concurrency access to OpenAI, Claude, Gemini, Grok, Flux, and agent workflows.
小豆包API offers 1042 LLM API models.
API pricing per token ranges from $0.0000 to $71.92/M (input).
https://api.linkapi.org| Model | Audit | Input ($/M) | Output ($/M) |
|---|---|---|---|
| — | Free | Free | |
| — | Free | Free | |
| — | Free | Free | |
| — | Free | Free | |
| — | Free | Free | |
| — | Free | Free | |
| — | $0.0000 | $0.0000 | |
| — | $0.0000 | $0.0000 | |
| — | $0.0000 | $0.0000 | |
| — | $0.0000 | $0.0000 |
api.newagiai.com
Provides API access to a wide range of AI models including text, image, and video generation from multiple providers.
api.bltcy.cn
柏拉图AI (api.bltcy.cn) is a multi-dimensional API integration platform providing access to over 600 AI models, serving as an alternate endpoint.
api.holdai.top
毫秒API provides a stable, high-bandwidth API forwarding service for OpenAI-compatible models, including GPT, Claude, and Midjourney, with global server deployment and transparent pricing.
api2.aigcbest.top
Provides AI-generated content APIs for various applications, including text and image generation.
api.gpt.ge
Provides access to over 500 AI models via OpenAI protocol with pay-as-you-go pricing, fast response times, and transparent billing.
api.aaai.vip
API provider for AI services accessible via dedicated endpoints.
Model launch: gpt-5.5, deepseek v4
Price adjustment notice for banana pro & banana 2 models 4K, 512px: Due to significant price differences in 4K, 512px model consumption, prices will be proportionally adjusted on the 23rd at 23:59.
gpt-image-2 has been launched, reverse-engineered from gpt plus; official grayscale release in progress, manually filtering available accounts, higher cost; official may downgrade to image-1.5, use with caution if concerned.
Due to severe official risk control by Gemini, the default group has essentially no availability. It is recommended to switch to other groups; for users with high stability needs, please use the gemini-t3 group or origin group first.
Price adjustment notice for aws claude and gemini premium groups due to long-term risk control instability: gemini premium group multiplier 1.5 -> 2 (banana pro price unchanged), aws claude group multiplier 2 -> 3, effective today at 12:00.
Seedance2.0 is now supported, only available for enterprise and self-use customers. Please contact customer service to access.
Due to strengthened risk control and sharply rising costs, prices for aws-claude and openai official premium groups will increase. Please pay attention to price changes.
All models in the Qwen series have been aligned with official prices. Please note the model price adjustments.
🛡️ Community Safety and Compliance Management Announcement
To maintain a healthy and positive platform environment, we have fully upgraded the content compliance review mechanism:
🚫 Creation Red Line: Strictly prohibited to use the platform (including tavern tools) to generate vulgar, pornographic, or illegal dialogues.
🤖 Intelligent Filtering: The system has enabled keyword interception and semantic recognition to automatically filter inappropriate content.
🔨 Violation Handling: Depending on the severity of the violation, we will take measures such as warnings, temporary bans, or permanent account suspensions.
⚖️ Legal Bottom Line: For malicious illegal activities, the platform will preserve evidence and cooperate with relevant departments to pursue legal responsibility.
✅ Thank you for your cooperation. Let's jointly safeguard this free and orderly creative space.
Due to year-end account closure and company structure adjustment, invoicing is currently suspended.
After invoicing resumes in January, we will process applications in the order of submission. Thank you for your understanding and cooperation 🙏
First, if you ask GPT-4: Are you GPT-4? It will most likely answer: I am OpenAI's GPT-3 model, and there is no GPT-4 yet. This is because the GPT-4 available for API calls has training data only up to September 2021. Once a model is trained, it does not automatically update its knowledge without retraining, similar to asking someone in 2021 what they ate for their first meal in 2023—the answer would be incorrect.
You can use the following logical question to test: Question: What is the relationship between Lu Xun and Zhou Shuren? GPT-3.5: Lu Xun and Zhou Shuren are two different people. GPT-4: Lu Xun and Zhou Shuren are the same person.
Please ensure the username is entered correctly; do not use an email address. Use the username you registered with. If you encounter login issues that you cannot resolve, contact customer service for immediate assistance.
Possible reasons: 1. The client disconnected just before output. 2. Tools call or function call. 3. OpenAI directly returns [Done], usually due to policy or safety-related refusal to answer; check the returned finish_reason or content for details.
For different data return codes, here are common error codes: Please refer to the tutorial documentation.
Please confirm that the token created in the backend has been allocated a balance and expiration time, which can generally be set to unlimited. Also, the balance is not in monetary units; 500,000 credits = 1 USD, and you can set it as needed.
Please contact customer service to obtain the enterprise customer API address.
Please ensure the model name exactly matches the list and is case-sensitive.
Balance = Group multiplier * Model multiplier * (Prompt tokens + Completion tokens * Completion multiplier). The completion multiplier is fixed at 1.33 for GPT-3.5 and 2 for GPT-4, consistent with the official API. In non-streaming mode, the official API returns the total tokens consumed, but note that the consumption multipliers for prompts and completions are different.
Please check if your token balance is sufficient; this is separate from the account balance. The token balance is only for users to set the maximum usage, and users can set it freely.
This issue usually occurs due to: 1. Incorrect address; it's not our address. 2. The token is not correctly set in the program. 3. The token has expired; please generate a new one.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
