A

api.gemai.cc

哈基米API站 offers a unified API gateway for large language models with competitive pricing and stable service.

Models
323 models
From
$0.060/M
Speed
119 tok/s
Updated
6/19/2026
Latency
0.00 s
Created At
1/8/2026
Recharge Rate
¥0.01 per $1 quota

Features

DrawingTaskData ExportCheck-in

API Endpoints

  • US Load Server
    https://api.gemai.cc
  • Asia-Pacific Route
    https://api2.gemai.cc

    Deployed in data centers across Asia, providing faster access for users in mainland China and neighboring countries

  • US Load Server
    https://api3.gemai.cc
  • Tool Site
    https://tool.gemai.cc
  • Global Accelerated Route
    https://api.gemapi.ai

    Global accelerated route. Non-streaming timeout of 100s

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 哈基米API站

哈基米API站 provides a unified API gateway for accessing various large language models. It supports endpoints for chat completions, responses, embeddings, reranking, image generation and editing, audio speech, transcription, and translation. Key models and providers include MoonshotAI, OpenAI, Grok, Zhipu, Volcengine, Cohere, Claude, Gemini, Suno, Minimax, Wenxin, Spark, Qingyan, DeepSeek, Qwen, Midjourney, AzureAI, Hunyuan, and Xinference, among over 30 others. Typical use cases involve integrating AI capabilities into applications through a single interface, with a focus on cost-effectiveness and reliability. The service requires users to replace the model base address with provided endpoints and obtain an API key via registration.

Health Check

100%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 322 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

Model
Input ($/M)
Output ($/M)
[官C]claude-fable-5default
$1.80/request-
[官C]claude-opus-4-8default
$1.80/request-
[官C]claude-opus-5default
$1.80/request-
[官逆B]gemini-3.6-flashdefault
$0.050/request-
[满血A]gemini-3.6-flashdefault
$0.050/request-
[满血B]gemini-3.6-flashdefault
$0.050/request-
[满血E]gemini-3.6-flashdefault
$0.050/request-
[满血F]gemini-3.6-flashdefault
$0.050/request-
[特价C]claude-opus-5default
$0.250/request-
[特价D]claude-opus-5default
$0.400/request-
[特价F]claude-opus-5default
$0.700/request-
[福利]gemini-3-flash-preview-searchingdefault
$0.010/request-
[限时福利]claude-opus-5-thinkingdefault
$0.100/request-
[限时福利]gemini-2.5-flashdefault
$0.010/request-
[限时福利]gemini-2.5-prodefault
$0.030/request-
[限时福利]gemini-2.5-pro-thinkingdefault
$0.030/request-
$0.100/request-
$6.00/M$30.00/M
$0.020/request-
[premium]gemini-3-pro-previewdefault
$12.00/M$72.00/M
[premium]gemini-3.5-flashdefault
$9.00/M$54.00/M
[官C]claude-opus-4-5default
$1.80/request-
[官C]claude-opus-4-6default
$1.80/request-
[官C]claude-opus-4-7default
$1.80/request-
[官C]claude-sonnet-4-5default
$0.650/request-

Showing 25 of 322 model rows

Free resources

Community-shared API keys and redeem codes associated with 哈基米API站.

Free redeem codes

1
View all
Redeem codeRedeem value / Remaining / totalRedemption requirementsShared by / date
V***$200.00· 9980/10000New users only · Invitation or referral required · Other · 只能QQ邮箱注册。新用户注册送200额度。Yizutt· Aug 12, 2026

Recent Test Records

TimeModelSpeedLatency
Jun 15, 12:05 PM
[福利]gemini-3-flash-preview
152.15 tok/s
7.53s
Apr 2, 03:10 AM
claude-opus-4-6
112.88 tok/s
2.19s
Apr 2, 03:08 AM
claude-sonnet-4-6
100.80 tok/s
2.05s
Apr 2, 03:05 AM
claude-sonnet-4-6
70.59 tok/s
1.61s
Jan 8, 02:18 AM
[官逆C]gemini-3-flash-preview
193.84 tok/s
5.57s
Jan 8, 02:14 AM
deepseek-v3.2
25.69 tok/s
10.23s

Similar API Provider Alternatives to Compare

Compare 哈基米API站 alternatives against 6 nearby API providers using 394 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
哈基米API站

api-gemai-cc

哈基米API站 offers a unified API gateway for large language models with competitive pricing and stable service.

Current provider baseline3230$0.930/M119 tok/s9940%
KKSJ-AI

kksj-ai

An AI model aggregation API platform offering multi-model access with OpenAI-compatible interfaces at low cost.

  • Lower average pricing
  • Higher 30-day availability
  • More free-model options
2532$0.0025/M49 tok/s9990%
6655 翻译小站

translate-api-6655-pp-ua

6655 Translation Mini-Station is a translation-focused LLM API relay by LinuxDO user chriswilson, rate limited to 500 requests per 20 min. Offers DeepSeek, Gemini, GLM, Hunyuan, OpenAI, Qwen. Gemini is not allowed for translation use.

  • Lower average pricing
  • Higher 30-day availability
  • More free-model options
1523$0.171/MN/A9990%
DreamChatBot

dreamchatbot-top

DreamChatBot runs a New API-based gateway on dreamchatbot.top for unified access to multiple AI models through a single endpoint.

  • Lower average pricing
  • Higher 30-day availability
1300$0.0027/MN/A9980%
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.

  • Lower average pricing
  • More free-model options
1219$0.095/M51 tok/s0%
180txt API

180txt-cn

180txt API provides an OpenAI-compatible API relay for multiple AI models.

  • Lower average pricing
  • More free-model options
778$0.639/M42 tok/s9930%
TanAPI

tanapi

  • Faster measured speed
  • Higher 30-day availability
450$2.74/M342 tok/s9970%

Announcements

default8/9/2026

🎰 Sunday Lucky Night · Limited-time Lottery Event!

Hey everyone, extra perks tonight! The Sunday Lucky Night lottery will officially start at 21:00 tonight. A total of 1,000 prizes are up for grabs, with a top prize of 5,000 quota. Come try your luck!

⏰ Event time: August 9, 2026 (Sunday) 21:00 – 22:00, scheduled draw

🎁 Prize setup (1,000 total): 👑 Grand prize: 5,000 quota, 2 winners 🥈 Second prize: 2,000 quota, 10 winners 🥉 Third prize: 1,000 quota, 40 winners 🎉 Fourth prize: 200 quota, 352 winners 🍀 Fifth prize: 100 quota, 596 winners

🔗 How to participate: After the event starts, open the link below to join with one click https://tool.gemai.cc/lottery/lw_kbiha3u0gunx9

This event uses a seed commitment mechanism. The seed hash has been pre-disclosed on the event page. Results are verifiable and tamper-proof. Feel free to participate.

See you at 21:00 tonight! May luck be with you all! 🍀

default8/3/2026

[Recharge Discount Restored to Regular Price Notice]

Dear users,

The month-end welfare season "Quota Top-Up Pack" event, which was postponed due to the network failure from July 31 to August 2, has been extended to today.

Notice as follows:

  1. Event end time: Today (August 3) 24:00
  2. After 24:00, recharges will return to regular prices, and discount tiers will be removed simultaneously
  3. Orders placed during the event enjoy discounts; quota is valid long-term after arrival with no expiration date

If you still have recharge plans, please note the time. Compensation for consumption during the failure period has been fully distributed yesterday. You can check it in "Wallet Transactions".

Thank you for your understanding and patience during the failure. We will continue to optimize service stability.

Hajimi API Operations Team August 3, 2026

default8/2/2026

🎰 Sunday Lucky Night · Limited-time Lottery Event!

Hey everyone, extra perks tonight! The Sunday Lucky Night lottery will officially start at 21:00 tonight. A total of 1,000 prizes are up for grabs, with a top prize of 5,000 quota. Come try your luck!

⏰ Event time: August 2, 2026 (Sunday) 21:00 – 22:00, scheduled draw

🎁 Prize setup (1,000 total): 👑 Grand prize: 5,000 quota, 2 winners 🥈 Second prize: 2,000 quota, 10 winners 🥉 Third prize: 1,000 quota, 40 winners 🎉 Fourth prize: 200 quota, 352 winners 🍀 Fifth prize: 100 quota, 596 winners

🔗 How to participate: After the event starts, open the link below to join with one click https://tool.gemai.cc/lottery/s4uljwmf7dhxvfzu

This event uses a seed commitment mechanism. The seed hash has been pre-disclosed on the event page. Results are verifiable and tamper-proof. Feel free to participate.

See you at 21:00 tonight! May luck be with you all! 🍀

default8/2/2026

[Compensation Credited Notice]

Dear users,

From 17:00 on July 31, 2026 to 17:00 on August 2, 2026, due to a network bandwidth failure in the data center, our site experienced service fluctuations and brief unavailability. We sincerely apologize for the inconvenience.

Compensation promised in the previous notice has now been fully distributed, ahead of the promised 72 hours:

  1. Scope: All consumption quota generated between 17:00 July 31 and 17:00 August 2 has been calculated and fully refunded;
  2. Form: Issued as bonus quota to your account, included in total balance, prioritized for consumption, with no usage restrictions;
  3. Inquiry: You can check the credit record in "Wallet Transactions" with type "Refund";
  4. The system has automatically issued it; no application needed. Amounts already auto-refunded during the period will not be reissued. If you believe the amount is incorrect after verification, please contact customer service for a case-by-case review.

The root cause has been identified, and reinforcement measures are in place. We will continue to optimize service stability. Thank you for your understanding and support.

Hajimi API Operations Team August 2, 2026

default8/2/2026

[Service Notice] Explanation and Compensation for Service Fluctuations from July 31 to August 2 Dear users,

Starting from 17:00 on July 31, due to abnormal traffic occupying the upstream network link of the data center, bandwidth resources were squeezed, causing some platform interfaces to experience slow responses and request timeouts. The technical team intervened immediately, completed link troubleshooting and service reinforcement. Services have gradually stabilized, and we are working with the data center to expand network capacity to prevent recurrence.

It is important to note: This was a resource issue at the network link level. Platform servers and data were not compromised. All user accounts, keys, and balance data security remain unaffected.

We sincerely apologize for the inconvenience caused by this fluctuation.

Compensation plan:

Scope: All consumption quota generated between 17:00 July 31, 2026 and 17:00 August 2, 2026; Method: Full refund to account balance, processed automatically by the system; no application needed; Crediting time: Expected to be completed in batches within 72 hours; records can be viewed in "Wallet Transactions";

If the refund amount does not match actual consumption, please contact customer service for verification.

Thank you for your understanding and support.

—— Operations Team August 2, 2026

default8/1/2026

[Service Anomaly Explanation and Recovery Notice]

Dear users, From the evening of August 1 to the early morning of August 2, some requests on our site experienced slow responses and occasional failures. Services have now returned to normal. We apologize to affected users.

Cause Mainly due to two latent issues from the early architecture: first, as call logs accumulated to hundreds of millions, database query efficiency gradually declined; second, some service nodes had abnormal latency in the network link to the database. The combination caused delayed billing settlement for some requests.

Impact on account quota Our billing uses a "pre-deduct, then settle" mechanism. During the anomaly, settlement of some requests was delayed, potentially causing temporary over-deduction of account quota. This quota will not be lost. The system is automatically refunding each amount. After refund, the balance will increase automatically. No need to contact customer service or take any action. If you confirm abnormal quota that has not been restored for a long time, please provide the corresponding request ID to customer service for separate investigation.

Completed actions

  1. Optimized database indexes, significantly improving query performance
  2. Fixed multiple defects in the settlement retry mechanism
  3. Adjusted connection pool and network-related configurations

Next steps We will continue to optimize network links and billing processes, and strengthen anomaly monitoring and alerts to minimize recurrence. We apologize again for the impact. Thank you for your understanding and support.

Hajimi API Site August 2, 2026

default7/31/2026

All recharge quotas that were not credited in this update have now been fully credited.

default7/31/2026

[Notice on Grayscale Update of API Key Function Optimization]

Dear users,

Over the past two days, we have focused on optimizing the security, stability, and user experience of API Keys. Related features will gradually enter grayscale updates soon.

This update mainly includes:

  • Optimized API Key security protection and quota mechanism to reduce risks from abnormal calls and key leaks;
  • Enhanced request frequency, concurrency, and quota control; clearer prompts will be provided when limits are exceeded;
  • Requests blocked by security policies will not incur charges;
  • Added Key usage source viewing feature, allowing you to view recent IPs, clients, success and failure counts, etc., to help detect abnormal calls;
  • Optimized compatibility for new Key creation, rotation, and historical Keys to reduce impact during grayscale updates;
  • Improved risk alerts and operation records for easy review of Key changes.

This grayscale update will not actively modify existing Key configurations or quotas. During the upgrade, a very small number of users may experience brief page refresh delays, data display delays, or call fluctuations. Retrying or refreshing the page should resolve them.

If abnormal calls are detected, please pause or rotate the relevant Key promptly, and provide the request time and request ID when reporting. Do not send full Keys to anyone.

Thank you for your continued rational supervision and constructive feedback. We will keep improving the platform's security, stability, and user experience!

Hajimi API Site Management Team July 31, 2026

default7/31/2026

📣 [Hajimi API Site] Month-End Welfare Season · Limited-Time Quota Top-Up Pack Preview!

Dear friends, month-end is here! Whether you're a developer rushing project milestones or a chat enthusiast enjoying daily conversations and AI creation, the site-wide limited-time "Quota Top-Up Pack" offers discounts tonight!

⏰ Event time: Starts promptly at 20:00 tonight, ends at 24:00 on August 1

🎁 Top-up special tiers: 🏷️ 0.96 yuan = 200 quota 🏷️ 9.6 yuan = 2000 quota 🏷️ 92 yuan = 20000 quota 🏷️ 900 yuan = 200000 quota

💡 Set your alarm early! Recharge discounts go live at 8 PM tonight. Enjoy!

default7/22/2026

Limited-time benefit: Claude temporarily restored, back online!

default7/22/2026

Limited-time benefit: Claude risk control, all series removed.

default7/17/2026

Newly launched kimi-k3 pay-per-use model, synced with Pro site.

default7/13/2026

[Notice on Grayscale Update of System Optimization Content]

Dear users, To continuously improve the platform experience, we plan to start a grayscale update of the optimization content proposed last week today (July 13) at 10:00 AM.

During the upgrade, a very small number of users may experience brief page refresh delays or call fluctuations. Refreshing the page should restore normal operation. Thank you for your rational supervision and constructive feedback. We will continue to provide better and more stable technical services!

Hajimi API Site Management Team July 13, 2026

default7/8/2026

[Notice on System Maintenance Completion and New UI Launch]

Dear users, The platform security upgrade has been successfully completed, and the new UI is now live! After the upgrade, some accounts may need to log in again. If you encounter a "404 Page Not Found" error, simply click the "Return to Home" button on the page. If the page layout is messy, try a hard refresh (Ctrl+F5) or clear your browser cache. Thank you for your cooperation!

Hajimi API Site Management Team July 8, 2026

default7/8/2026

[Notice on Temporary System Maintenance and Security Upgrade]

Dear users, To improve system stability, the platform will undergo a bottom-layer security upgrade starting today (July 8) at 20:00 to fix billing logic anomalies in the upstream open-source system. The upgrade uses grayscale release. During the period, a very small number of users may experience brief call fluctuations or background refresh delays. After the upgrade, the system will review and correct abnormal account quotas. Thank you for your understanding and cooperation!

Hajimi API Site Management Team

July 8, 2026

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.