Newagiai offers a unified API platform for accessing various AI models. It supports text generation models like GPT-5.1, Claude Opus, and Gemini-3-Pro, image generation models such as Nano-Banana-2 and Doubao-Seedream, and video generation models including Sora 2, Veo 3.1, and Kling Omni-Video. The platform provides both official and reverse-engineered API formats, with features like asynchronous tasks and OSS storage preferences for image models. Use cases include chatbots, content creation, and multimedia generation.
Newagiai
api.newagiai.com
Provides API access to a wide range of AI models including text, image, and video generation from multiple providers.
- Models
- 1191 models
- From
- $0.0002/M
- Speed
- --
- Updated
- 6/8/2026
- Latency
- --
- Created At
- 8/13/2025
- Recharge Rate
- ¥1.00 per $1 quota
Features
DrawingTaskData Export
Login Methods
GitHub
API Endpoints
- Token Balance Query URL
https://usage.gptbest.vipNo interface
- Main Site
https://api.bltcy.aiHigh defense, with UI (CF cluster, fast overseas)
- United States
https://api.gptbest.vipNo interface, includes query details for agent resale
- Hong Kong Route
https://hk-api.gptbest.vipHigh defense, no interface, includes query details for agent resale
- Endpoint 5Historical / Unverified
https://api.newagiai.com
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 Newagiai
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 | $0.548/M | $2.74/M |
claude-opus-4-7-thinkingdefault | $0.685/M | $3.42/M |
claude-opus-4-7-thinkingcc优质 | $1.37/M | $6.85/M |
claude-opus-4-7-thinkingorigin | $5.00/M | $25.00/M |
claude-opus-4-7-thinkingclaude正价 | $5.48/M | $27.40/M |
claude-opus-5-thinkingcc | $0.548/M | $2.74/M |
claude-opus-5-thinkingdefault | $0.685/M | $3.42/M |
claude-opus-5-thinkingcc优质 | $1.37/M | $6.85/M |
claude-opus-5-thinkingclaude官 | $3.42/M | $17.12/M |
claude-opus-5-thinkingorigin | $5.00/M | $25.00/M |
claude-opus-5-thinkingclaude正价 | $5.48/M | $27.40/M |
claude-sonnet-5-thinkingcc | $0.219/M | $1.10/M |
claude-sonnet-5-thinkingdefault | $0.274/M | $1.37/M |
claude-sonnet-5-thinkingcc优质 | $0.548/M | $2.74/M |
claude-sonnet-5-thinkingclaude官 | $1.37/M | $6.85/M |
claude-sonnet-5-thinkingorigin | $2.00/M | $10.00/M |
claude-sonnet-5-thinkingclaude正价 | $2.19/M | $10.96/M |
fal-ai/*fal.ai-all | $0.466/request | - |
gemini-3.1-flash-image-512pxgemini-t3 | $0.040/request | - |
gemini-3.1-flash-image-512pxgemini优质 | $0.020/request | - |
gemini-3.1-flash-image-512pxorigin | $0.073/request | - |
gemini-3.5-flash-thinking-highgemini优质 | $0.411/M | $2.47/M |
gemini-3.5-flash-thinking-highgemini-t3 | $0.822/M | $4.93/M |
gemini-3.5-flash-thinking-highorigin | $1.50/M | $9.00/M |
gemini-3.5-flash-thinking-lowgemini优质 | $0.411/M | $2.47/M |
Showing 25 of 2577 model rows
Recent Test Records
No test records available
Similar API Provider Alternatives to Compare
Compare Newagiai alternatives against 6 nearby API providers using 3203 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| Newagiai newagiai Provides API access to a wide range of AI models including text, image, and video generation from multiple providers. | Current provider baseline | 1,191 | 6 | $0.0002/M | N/A | 0% |
| 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% |
| F2API api-f2api-com F2API is an enterprise AI gateway providing a unified OpenAI-compatible interface for accessing multiple large language models. |
| 1,262 | 0 | N/A | 272 tok/s | 9990% |
| 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% |
| Yun API api-zyai-online Yun API is a high-speed, stable, and high-concurrency API relay service based on official APIs, offering access to over 100 AI models including text, image, and video generation. |
| 431 | 0 | $0.00000342/M | 32 tok/s | 9930% |
| TommyLam API new-api-tommylam-me TommyLam API offers an OpenAI-compatible API gateway for accessing multiple AI models at competitive rates. |
| 231 | 100 | N/A | 61 tok/s | 9990% |
| LLMService llmservice LLMService provides API access to large language models for self-use applications. |
| 453 | 0 | N/A | 139 tok/s | 5160% |
Announcements
default6/2/2026
Dear users, If you need to issue a consumption invoice, please submit your invoice application and provide the required information as soon as possible to avoid delays caused by backlog.
warning5/30/2026
Dear users,
Hello! To better serve enterprise users, if you are an enterprise customer who previously recharged using a personal account and wish to continue using the service normally, please contact customer service to complete the process of converting your personal account to an enterprise account.
If you have any questions, feel free to contact customer service. Thank you for your understanding and cooperation!
default5/11/2026
Dear users,
Due to limited technical and operational resources at this stage, the platform can no longer sustain the continuously growing business scale and customer demand. After comprehensive evaluation, the company has decided to gradually adjust its current business direction, focusing on enterprise-level service cooperation in the future.
To ensure the quality of existing services and the stable operation of the platform, personal recharges and new open access features will be closed from today, and no new personal user business will be added in the future.
Existing users' recharged balances and activated services will continue to function normally, and the platform will continue to ensure the stable operation of current services. If special circumstances require negotiation, please contact platform customer service.
Further adjustments will be communicated through announcements.
Thank you for your continued support and understanding.
warning5/9/2026
The platform has temporarily closed new user registration to control site traffic and maintain stable operations, avoiding unnecessary external interference. This is not a scam or shutdown as rumored online. Additionally, we solemnly promise: even if there are future business adjustments or shutdown plans, all user account balances will be fully refunded normally, ensuring every user's rights. We will never run away with funds or harm user interests. Currently, all existing users' features work normally, and data assets are safe and controllable. Please do not believe false rumors, do not spread them. We operate steadily, and all official notices are authoritative.
success4/8/2026
Seedance2.0 is now supported, only available for enterprise and personal use customers. Please contact customer service to access.
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 conversations.
🤖 Smart Filtering: The system has enabled keyword interception and semantic recognition to automatically filter inappropriate content.
🔨 Violation Handling: Depending on the severity, 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 for legal accountability.
✅ 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 restructuring, invoicing is currently suspended.
- Invoices for December recharges: You can submit applications online first, will be postponed to January for issuance
- Invoice applications for recharges before December: No longer accepted
After invoicing resumes in January, we will process applications in the order they were submitted. Thank you for your understanding and cooperation 🙏
default12/17/2025
🔔 Invoice Reminder Notice Dear users,
Due to upcoming structural adjustments and company business registration changes, financial invoicing will be processed centrally.
👉 Please submit invoice applications for the last three months before December 25. After this date, invoices for orders in this period cannot be issued.
If you have unclaimed orders, please contact our staff as soon as possible. Thank you for your understanding and cooperation.
success12/4/2025
Support for the latest image generation model doubao-seedream-4-5-251128 has been added.
success12/2/2025
The world's first unified multimodal video model [Kling Video O1 Model] is now available
🌟 Model Highlights
- Multimodal video generation: Supports input of any content to generate videos that meet requirements.
- Multimodal input: Supports unified creation and editing, meeting various input forms.
- Video consistency solution: Ensures consistency during video generation through powerful technology.
- More creativity: Strong combination capabilities help users achieve more creative ideas.
- Controllable generation time: Flexible generation time, 3-10 seconds for free narrative.
💰 Pricing Details
Kling Omni-Video V1 High Quality Edition
- With reference video and video generation: Duration calculated by rounding, 1.2 per second
- Without reference video and video generation: Duration calculated by rounding, 0.8 per second
warning10/29/2025
Jimeng 4 image generation model: due to official adjustments, the price has increased to 0.14 per use. Hailuo video: to maintain stability, the price has increased. Effective from 2025.10.29 23:59:59
success10/4/2025
Due to adjustments in Doubao discounts, Jimeng 4 image generation has temporarily returned to its original price.
success9/27/2025
Support for Wanxiang's latest video model wan 2.5 has been added; all image generation models now support asynchronous tasks. Please refer to the API documentation.
ongoing8/19/2025
MiniMax Hailuo video model - now supports the full range of Hailuo official API video models.
success8/19/2025
Support for Kling - video sound effects, text-to-sound effects, multi-image reference video generation, multimodal video editing, multi-image reference image generation, and image expansion features has been added.
success8/5/2025
Support for Qianwen's latest image generation model qwen-image has been added, compatible with chat and Dalle interfaces.
success7/29/2025
Support for Zhipu AI's new GLM-4.5 series models has been added. Click to view.
warning7/28/2025
The domestic special pricing group will increase prices today at 12:00, adding more models and vendors.
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 for testing: 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 on your own, please contact customer service for immediate assistance.
Why is there no output or token completion after the request?
There are several possibilities: 1. The output was about to start, but the client disconnected. 2. It's a tools call or function call. 3. OpenAI directly returns [Done], usually due to policy or safety-related refusal to answer, which should be judged based on the returned finish_reason or content.
What does it mean when the API interface returns error data?
For different data return codes, here are common error codes: Please refer to the tutorial documentation.
The backend has sufficient quota, but using the API indicates insufficient quota.
Please confirm that the token created in the backend has been allocated quota and expiration time, which can generally be set to unlimited. Also, quota is not entered as an amount; 500,000 quota equals 1 USD, and you can fill in as needed.
CDN origin fetch error occurs.
Please contact customer service to obtain the enterprise customer interface address.
Indicates that there are no available channels in the current group.
Please ensure the model name exactly matches the list and is case-sensitive.
What is quota? How is it calculated?
Quota = 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. In non-streaming mode, the official interface returns the total tokens consumed, but note that the multipliers for prompt and completion are different.
Why does it indicate insufficient quota when the account quota is sufficient?
Please check if your token quota is sufficient; this is separate from the account quota. Token quota 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.