MMKG is an API provider offering access to various AI models through a platform that includes a model marketplace for pricing and usage details. Key features include account management via QQ chat integration, a community-driven environment with official QQ groups for support and discussion, and a commitment to prohibiting NSFW content generation to comply with legal standards. The platform operates as a free service, with registration periodically limited to manage server load and ensure stability. It supports typical use cases such as AI model experimentation and integration into applications, emphasizing accessibility and community engagement without specific details on models, latency, or pricing.
api.mmkg.cloud
MMKG provides an API platform for accessing AI models, including a model marketplace and community features, with a focus on free and accessible services.
- Models
- 31 models
- From
- --
- Speed
- 98 tok/s
- Updated
- 6/8/2026
- Latency
- 0.00 s
- Created At
- 3/30/2026
- Recharge Rate
- ¥5.00 per $1 quota
Features
TaskData ExportCheck-in
Login Methods
Passkey
API Endpoints
- Official Website
https://api.mmkg.cloudMain site
- Endpoint 2Historical / Unverified
https://mmkg.cloud - Endpoint 3Historical / Unverified
https://api3.mmkg.cloud
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 MMKG
Health Check
99%Recent availability
History (72 pts)
PastNow
API Benchmarks & Pricing
Compare 31 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
Cerebra-1-glm-4.7普通猫猫 | $5.00/request |
Kiro-3-claude-sonnet-4-6普通猫猫 | $15.00/request |
Kiro-3-claude-sonnet-5普通猫猫 | $15.00/request |
Kiro-5-claude-opus-4-6普通猫猫 | $25.00/request |
Kiro-5-claude-opus-4-7普通猫猫 | $25.00/request |
Kiro-5-claude-opus-4-8普通猫猫 | $25.00/request |
官方-0.5-gpt-oss-120b普通猫猫 | $2.50/request |
官方-0.5-gpt-oss-20b普通猫猫 | $2.50/request |
官方-1-deepseek-v4-flash普通猫猫 | $5.00/request |
官方-1-gemini-2.5-flash-lite普通猫猫 | $5.00/request |
官方-1-gpt-4o-mini普通猫猫 | $5.00/request |
官方-1-gpt-5.4-mini普通猫猫 | $5.00/request |
官方-1-grok-4.20普通猫猫 | $5.00/request |
官方-2-gemini-2.5-flash普通猫猫 | $10.00/request |
官方-2-gemini-3-flash-preview普通猫猫 | $10.00/request |
官方-2-gemini-3.1-flash-lite-preview普通猫猫 | $10.00/request |
官方-2-grok-4.3普通猫猫 | $10.00/request |
官方-2-grok-4.3-深度思考普通猫猫 | $10.00/request |
官方-2-grok-4.5普通猫猫 | $10.00/request |
官方-2-grok-build普通猫猫 | $10.00/request |
官方-2.5-gpt-5.4普通猫猫 | $12.50/request |
官方-2.5-gpt-5.5普通猫猫 | $12.50/request |
官方-3-deepseek-v4-pro普通猫猫 | $15.00/request |
官方-3-grok-imagine普通猫猫 | $15.00/request |
特惠-0.5-deepseek-v4-flash普通猫猫 | $2.50/request |
Showing 25 of 31 model rows
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Mar 30, 02:43 AM | 0.5-兼容-官转-kimi-2.5 | 98.18 tok/s | 4.75s |
Similar API Provider Alternatives to Compare
Compare MMKG alternatives against 6 nearby API providers using 187 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| MMKG api-mmkg-cloud MMKG provides an API platform for accessing AI models, including a model marketplace and community features, with a focus on free and accessible services. | Current provider baseline | 31 | 0 | N/A | 98 tok/s | 9980% |
| 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% |
| ChooseC API ipv4-beta-lm-studio ChooseC API is a unified AI model aggregation gateway supporting 260+ mainstream models including Claude, GPT, Qwen, DeepSeek, Kimi, and GLM with OpenAI, Claude, and Gemini compatibility. |
| 335 | 9 | $0.095/M | 138 tok/s | 9950% |
| 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% |
| LLMService llmservice LLMService provides API access to large language models for self-use applications. |
| 449 | 0 | N/A | 139 tok/s | 4760% |
| Kterna api-kterna-xyz Kterna (api.kterna.xyz) is an OpenAI-compatible LLM API relay aggregating multiple providers including OpenAI, Anthropic Claude, Google Gemini, MoonshotAI, DeepSeek, Qwen, Grok, Zhipu, Volcengine, MiniMax, Hunyuan, Midjourney and Suno. Offers chat completions, embeddings, rerank, image and audio endpoints with no subscription required. |
| 230 | 124 | N/A | N/A | 0% |
| ChooseC API ipv4-beta-kxcym-top-3001 ChooseC API is an OpenAI-compatible relay service hosted at ipv4-beta.kxcym.top, providing access to multiple AI models through standardized endpoints. |
| 122 | 9 | $0.095/M | 51 tok/s | 0% |
Announcements
default7/8/2026
📢 MMKG Public Welfare Site · Inactive User Cleanup Notice
Dear users: To ensure fair allocation of public welfare resources and stable server operation, we will clean up a batch of long-term inactive accounts on July 15, 2026.
Cleanup Time
July 15, 2026
Cleanup Scope
Inactive accounts that have not logged in for a long time and have no usage records.
How to Keep Your Account
Before July 15, simply log in once and use the service normally, and you will automatically be considered an active user, unaffected by this cleanup.
success7/8/2026
📢 MMKG · Restart Trial Operation Notice
Dear users:
MMKG has now restarted and entered the trial operation phase. 🎉
To ensure service stability, we have made the following temporary adjustments during the trial period:
- 🚫 New user registration is temporarily closed
- 🚫 Daily check-in is temporarily closed
Existing accounts are unaffected and can log in and use normally. Once the system stabilizes, we will restore registration and check-in functions as soon as possible. Thank you for your understanding and patience.
Public welfare is not easy; may the stars accompany you ✨
—— MMKG Team
ongoing10/26/2025
Important Reminder:
To receive official notifications in a timely manner, handle related issues, and avoid accidental bans due to violations, please all users join the official communication groups as soon as possible:
Group 1: 1042266308 (Full)
Group 2: 1065341718 (Recommended)
Thank you for your understanding and cooperation!
FAQ
What is the API endpoint for your website?
Our API endpoint (Endpoint / Base URL) is `https://api.mmkg.cloud`. Depending on the client or software you use, the format you fill in may have slight differences. To ensure optimal compatibility, we **strongly recommend using the following complete address**: > **`https://api.mmkg.cloud/v1`** --- **Why is `/v1` sometimes needed?** The standard OpenAI API path includes a version number, for example `/v1/chat/completions`. * **Some clients** will automatically append the `/v1` path after the domain you fill in. For such clients, you only need to fill in `https://api.mmkg.cloud`. * **Other clients** require you to provide the complete base path including `/v1`; they do not add it automatically. **Summary and Recommendation:** To avoid confusion and connection failures, please directly copy and use **`https://api.mmkg.cloud/v1`**. This address is compatible with almost all software that supports the OpenAI protocol. If you encounter issues, try using the version without `/v1`.
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.