91VIP is a non-profit API service providing access to various AI models including Codex, Claude Code, and Open Code, with specific unlimited-use groups.

Models
383 models
From
$0.073/M
Speed
301 tok/s
Updated
8/4/2026
Latency
0.00 s
Created At
3/13/2026
Recharge Rate
¥7.30 per $1 quota

Features

DrawingTaskData ExportCheck-in

Login Methods

GitHubLinuxDOPasskeyGoogle

API Endpoints

  • Endpoint 1Historical / Unverified
    https://91vip.futureppo.top
  • Main
    https://api.pie-xian.com/

    Main route

  • Endpoint 3
    https://edge.pie-xian.com/

    EdgeOne route may be more accessible in China

  • Overseas
    https://ao.pie-xian.com/

    Overseas

  • Endpoint 5Historical / Unverified
    https://api.pie-xian.com
  • Endpoint 6Historical / Unverified
    https://edge.pie-xian.com
  • Endpoint 7Historical / Unverified
    https://ao.pie-xian.com
  • Endpoint 8Historical / Unverified
    https://xn--wnu.xn--6qq80winj2x7b.com
  • Server Status
    https://status.eloina.cn

    Server status

  • Endpoint 10Historical / Unverified
    https://futureppo-fuck.me
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 91VIP

91VIP is a non-profit API service offering access to multiple AI models. It supports Codex, Claude Code, and Open Code models. The service includes specific groups with unlimited usage: Meituan series, OpenRouter group, NVIDIA group, and Cerebras group. It provides multiple endpoint routes including a direct connection and Cloudflare-accelerated alternatives. Integration tutorials are available for VS Code Copilot and Codex, with configuration examples for model setup. The service operates on a non-profit basis with no sponsorship channels or official communication groups.

Health Check

0%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 807 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

Model
Input ($/M)
Output ($/M)
$14.60/M$58.40/M
$14.60/M$58.40/M
agnes-2.0-flash无限制
$0.730/M$1.46/M
agnes-2.0-flashvip
$0.730/M$1.46/M
agnes-2.0-flashuser
$0.730/M$1.46/M
agnes-2.0-flashmodel
$0.730/M$1.46/M
agnes-2.0-flash91vip
$0.730/M$1.46/M
agnes-2.5-flash无限制
$0.730/M$2.19/M
agnes-2.5-flashvip
$0.730/M$2.19/M
agnes-2.5-flash91vip
$0.730/M$2.19/M
agnes-2.5-flashuser
$0.730/M$2.19/M
agnes-2.5-flashmodel
$0.730/M$2.19/M
agnes-image-2.0-flashvip
$0.073/request-
agnes-image-2.0-flash无限制
$0.073/request-
agnes-image-2.0-flash91vip
$0.073/request-
agnes-image-2.0-flashuser
$0.073/request-
agnes-image-2.0-flashmodel
$0.073/request-
agnes-image-2.1-flashvip
$0.073/request-
agnes-image-2.1-flash91vip
$0.073/request-
agnes-image-2.1-flashuser
$0.073/request-
agnes-image-2.1-flash无限制
$0.073/request-
agnes-image-2.1-flashmodel
$0.073/request-
agnes-video-v2.0user
$0.730/request-
agnes-video-v2.0model
$0.730/request-
agnes-video-v2.0vip
$0.730/request-

Showing 25 of 807 model rows

Recent Test Records

TimeModelSpeedLatency
Jul 17, 01:58 PM
grok-build-0.1
130.63 tok/s
12.87s
Apr 23, 05:35 PM
gemini-3.1-flash-lite-preview
120.44 tok/s
11.32s
Apr 23, 05:19 PM
qwen3.5-397b-a17b
28.63 tok/s
4.07s
Apr 23, 05:17 PM
qwen3.5-397b-a17b
16.20 tok/s
4.38s
Apr 23, 05:07 PM
qwen3.5-397b-a17b
16.28 tok/s
2.89s
Apr 23, 04:58 PM
qwen3.5-397b-a17b
21.60 tok/s
4.64s
Mar 30, 03:45 AM
MiniMax-M2.7
40.43 tok/s
9.73s
Mar 30, 02:58 AM
gpt-5.3-codex
35.36 tok/s
17.64s
Mar 29, 09:55 AM
llama3.1-8b
1910.78 tok/s
0.43s
Mar 13, 03:29 PM
openai/gpt-oss-safeguard-20b
869.93 tok/s
0.67s

Similar API Provider Alternatives to Compare

Compare 91VIP alternatives against 6 nearby API providers using 979 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
91VIP

91vip-futureppo-top

91VIP is a non-profit API service providing access to various AI models including Codex, Claude Code, and Open Code, with specific unlimited-use groups.

Current provider baseline3832$0.054/M301 tok/s0%
Dext API

ai-dext-top

Dext API is an OpenAI-compatible API relay offering access to 500+ LLM models at competitive prices, with multi-channel routing and broad model coverage.

  • Lower average pricing
  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
  • Same provider category
667219$0.017/M19 tok/s3130%
钠 API

naapi-cc

Na API (naapi.cc) is an OpenAI-compatible LLM API gateway with competitive pricing and stable access to 100+ models from OpenAI, Anthropic, Google, and more.

  • Lower average pricing
  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
5660$0.0031/M649 tok/s9960%
初叶🍂Furry API

ai-chuyel-top

A free, community-supported API service providing access to various AI models for developers and users.

  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
  • Same provider category
1,021152$18.00/M171 tok/s2420%
天絮 API

tianxu-api

Tianxu API provides an AI model relay service with multiple access points and stable connectivity.

  • Lower average pricing
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
7590$0.014/M93 tok/s9920%
速创API

suchuang

Suchuang API provides access to various AI models including text generation, image creation, and video generation through a unified API.

  • Lower average pricing
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
5100$0.0020/M74 tok/s9960%
星见雅 API

api-xinjianya-top

Xinjianya API is an OpenAI-compatible API relay at api.xinjianya.top. Service availability may be limited.

  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
  • Same provider category
498211N/A67 tok/s6910%

Announcements

default8/25/2026

Registration code fd560e973a4249569805c4d9f69387b3 activated today, 432 people

success8/23/2026

agnes-video-v2.0 has adapted to the new version's response format. Those who had issues before can now retry the request.

default8/15/2026

Registration code activated today: 5858274c3a984751bc30bda2fe5e5193

success8/15/2026

Launched a new public welfare gameplay, Word Yuan Loan, accessible from the top bar.

success8/12/2026

Launched mistral's glm-5.2-fast, very fast!

ongoing7/10/2026

GitHub now requires a minimum account age of six months.

warning6/30/2026

Due to disk failure, data cannot be recovered. Previously registered users need to re-register.

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.