Xiaodoubao API is a Chinese AI API relay platform hosted at api.linkapi.org. The public site describes it as a low-cost, stable, and high-concurrency API gateway for OpenAI, Claude, Gemini, Grok, Flux, and AI agent workflows, and its /v1/models endpoint returns a token-required new_api_error response.
小豆包API
api.linkapi.org
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.
- Models
- 1190 models
- From
- $0.0003/M
- Speed
- --
- Updated
- 6/8/2026
- Latency
- --
- Created At
- 12/17/2025
- Recharge Rate
- ¥1.50 per $1 quota
Features
DrawingTaskData Export
Login Methods
GitHub
API Endpoints
- Endpoint 1Historical / Unverified
https://api.linkapi.org
Claim this provider
Verify ownership to unlock provider management features:
- Edit provider name, content, and links
- Get featured with priority traffic and visibility boost
- Display a verified badge to build user trust
Leaderboard Rankings
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
About 小豆包API
Health Check
0%Recent availability
History (72 pts)
PastNow
API Benchmarks & Pricing
Compare 2577 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
claude-opus-4-7-thinkingcc | $0.822/M | $4.11/M |
claude-opus-4-7-thinkingdefault | $1.03/M | $5.14/M |
claude-opus-4-7-thinkingcc优质 | $2.05/M | $10.27/M |
claude-opus-4-7-thinkingorigin | $7.50/M | $37.50/M |
claude-opus-4-7-thinkingclaude正价 | $8.22/M | $41.10/M |
claude-opus-5-thinkingcc | $0.822/M | $4.11/M |
claude-opus-5-thinkingdefault | $1.03/M | $5.14/M |
claude-opus-5-thinkingcc优质 | $2.05/M | $10.27/M |
claude-opus-5-thinkingclaude官 | $5.14/M | $25.68/M |
claude-opus-5-thinkingorigin | $7.50/M | $37.50/M |
claude-opus-5-thinkingclaude正价 | $8.22/M | $41.10/M |
claude-sonnet-5-thinkingcc | $0.329/M | $1.64/M |
claude-sonnet-5-thinkingdefault | $0.411/M | $2.05/M |
claude-sonnet-5-thinkingcc优质 | $0.822/M | $4.11/M |
claude-sonnet-5-thinkingclaude官 | $2.05/M | $10.27/M |
claude-sonnet-5-thinkingorigin | $3.00/M | $15.00/M |
claude-sonnet-5-thinkingclaude正价 | $3.29/M | $16.44/M |
fal-ai/*fal.ai-all | $0.699/request | - |
gemini-3.1-flash-image-512pxorigin | $0.110/request | - |
gemini-3.1-flash-image-512pxgemini优质 | $0.030/request | - |
gemini-3.1-flash-image-512pxgemini-t3 | $0.060/request | - |
gemini-3.5-flash-thinking-highgemini优质 | $0.616/M | $3.70/M |
gemini-3.5-flash-thinking-highgemini-t3 | $1.23/M | $7.40/M |
gemini-3.5-flash-thinking-highorigin | $2.25/M | $13.50/M |
gemini-3.5-flash-thinking-lowgemini优质 | $0.616/M | $3.70/M |
Showing 25 of 2577 model rows
Recent Test Records
No test records available
Similar API Provider Alternatives to Compare
Compare 小豆包API alternatives against 6 nearby API providers using 3205 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| 小豆包API xiaodoubao-api 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. | Current provider baseline | 1,190 | 6 | $0.0003/M | N/A | 630% |
| 钱多多 API api2-aigcbest-top Provides AI-generated content APIs for various applications, including text and image generation. |
| 1,418 | 2 | $0.0025/M | 101 tok/s | 9940% |
| Koyeb AI Gateway new-api-koyeb-app An OpenAI-compatible API gateway deployed on Koyeb, providing access to multiple AI models. |
| 578 | 420 | N/A | 33 tok/s | 9960% |
| 艾可API aicanapi-com AicanAPI provides an enterprise-grade API management platform with high-performance architecture, security compliance, and cost optimization for business digital transformation. |
| 545 | 103 | N/A | 70 tok/s | 5870% |
| APIMart apimart APIMart is a pay-as-you-go, OpenAI-compatible AI API gateway operated by Hangzhou Huanzhi Network Technology Co., Ltd. It provides unified access to more than 500 third-party text, image, video, and audio models, with consolidated billing, multi-provider routing, and automatic failover. |
| 257 | 16 | $0.015/M | N/A | 9980% |
| 91VIP API hcg-pippi-top A unified API gateway providing access to multiple large language models and AI services with competitive pricing and stability. |
| 181 | 30 | $0.467/M | 148 tok/s | 9890% |
| 优质企业级中转API 始终坚持只做 Pro 号池、高品质 ,尊重安全隐私。 api-17nas-com 17NAS API provides an OpenAI-compatible API gateway at api.17nas.com for accessing multiple LLM models. |
| 41 | 38 | N/A | 36 tok/s | 2460% |
Announcements
success4/24/2026
Model launch: gpt-5.5, deepseek v4
success4/22/2026
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.
success4/19/2026
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.
success4/16/2026
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.
success4/14/2026
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.
success4/8/2026
Seedance2.0 is now supported, only available for enterprise and self-use customers. Please contact customer service to access.
warning4/8/2026
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.
success2/5/2026
All models in the Qwen series have been aligned with official prices. Please note the model price adjustments.
warning2/3/2026
🛡️ 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.
warning12/24/2025
📌 Invoice Notice
Due to year-end account closure and company structure adjustment, invoicing is currently suspended.
- Invoices for December recharges: You can submit applications online first, will be deferred to January for issuance
- Invoice applications for recharges before December: Acceptance has ended
After invoicing resumes in January, we will process applications in the order of submission. Thank you for your understanding and cooperation 🙏
FAQ
After switching to GPT-4, why does it answer that it is not GPT-4 when asked?
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.
How can I determine if it is the GPT-4 model?
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.
Unable to log in?
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.
Why is there no output or token completion after a request?
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.
What does it mean when the API returns an error in the data?
For different data return codes, here are common error codes: Please refer to the tutorial documentation.
The backend balance is sufficient, but the API indicates insufficient balance.
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.
CDN origin fetch error occurs.
Please contact customer service to obtain the enterprise customer API address.
Indicates no available channels in the current group.
Please ensure the model name exactly matches the list and is case-sensitive.
What is the balance? How is it calculated?
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.
Why does it indicate insufficient balance when the account balance is sufficient?
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.
Token is invalid.
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.
Notes
- Health checks: Scope: the 72-hour chart and recent availability measure API connectivity only. Each bar summarizes one hour of checks. Targets: LMSpeed tries the configured health check URL and provider status URL first, then API endpoints derived from known API hosts and recent speed-test base URLs. A website host is considered only when it looks like an API endpoint. Probe steps: each candidate goes through DNS lookup, TCP connection, TLS handshake for HTTPS, and an HTTP HEAD request with redirects followed. Probing stops after the first reachable candidate. Reachable criteria: every required network step must succeed. An HTTP response below 500 is treated as reachable, including 401 because it confirms that an authenticated API endpoint responded, except for statuses classified as blocked. Blocked results: HTTP 403, 429, 521, 525, and 530, plus detected WAF or Cloudflare challenges, are shown as blocked and excluded from availability calculations because LMSpeed cannot determine whether the API itself is down. Model availability: when a dedicated test key is configured, LMSpeed sends an authenticated GET request to a derived /models endpoint and compares returned model IDs with this provider's listed models. These per-model results appear in Models & Pricing and are not included in the provider connectivity percentage. Timeouts: TCP connection, TLS handshake, HTTP connectivity, and model requests each use a 20-second timeout. A full run can take longer when several candidates are tried. Frequency: a background worker checks all providers every 5 minutes by default. The 72-hour chart combines those samples into hourly bars, and the schedule may be changed by the service operator. Limit: automated samples are not an SLA and do not guarantee account quota, every model, every region, or successful completion requests. Check the provider's own status page before making operational decisions.
- Domain Rating data is sourced from Ahrefs. It is a 0–100 backlink-based domain strength signal and does not measure API speed or reliability.
- Announcements and FAQ are read from this provider's NewAPI status snapshot when available. LMSpeed stores the original content and optional English translations from the provider status source, then shows the localized fields on this page.