Models
192 models
From
--
Speed
59 tok/s
Updated
9/5/2026
Latency
0.00 s
Created At
7/22/2026

Billing

Payment methods

AlipayUSDTWeChat PayCredit cardApple PayGoogle Pay

Billing types

Usage-basedSubscription
Refunds
Supported
Invoicing
Supported

API Endpoints

  • Endpoint 1
    ai.furry.vg
Claim this provider
SVerified by Steve

Leaderboard Rankings

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

About S3AI API

S3AI API is an all-in-one API Router for developers, teams, and users worldwide. International users are welcome. Through a unified interface, the platform brings together Claude, Codex, Gemini, Grok, MiniMax, Mistral, DeepSeek, Zhipu, and leading image-generation models.

The platform supports multiple service routes for the same model, allowing users to choose the most suitable speed, pricing, caching capabilities, and tool-calling support for each task. The default group includes Meshy, AzureTTS, UnrealSpeech, NanoBanana, and a broad range of Chinese models, supporting text, code, vision, speech, and image workflows.

S3AI API offers comprehensive coverage of Chinese models, including self-hosted Chinese models. It also provides No Data Retention models for users who prioritize data privacy and compliance. The site offers more than 65 free models for testing, development, and everyday use.

S3AI API supports multiple payment methods, including Google Pay, Apple Pay, Mastercard/Visa, WeChat Pay, Alipay, Monero, and USDT, making payments convenient for users in different countries and regions.

To use the relevant free capabilities, an account must maintain a minimum balance of 0.01 credits. Users can unlock access by inviting two people through their personal referral link and linking a Telegram account. Alternatively, spending 15 credits will unlock the relevant capabilities automatically.

S3AI API also provides exclusive text-to-3D, image-to-3D, and texture-generation APIs, along with Blender workflow support. Text or images can be converted into deliverable GLB assets, making the platform suitable for rapid prototyping, content creation, and 3D asset production.

One entry point connecting multiple models, payment methods, and creative workflows.

Health Check

99%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 192 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

Model
Model availability
claude-fable-5
99%
qwen3.8-max
99%
moonshotai/kimi-k3
99%
muse-spark-1.2-contributor
99%
agnes-2.0-flash
99%
agnes-2.5-flash
99%
agnes-image-2.0-flash
99%
agnes-image-2.1-flash
99%
deepseek-v4-pro-0813
99%
gemini-3.1-flash-image
99%
glm-5
99%
glm-5.1
99%
google/diffusiongemma-26b-a4b-it
99%
gpt-image-2-1k
99%
grok-4.20-0309-non-reasoning
99%
grok-4.20-0309-reasoning
99%
grok-4.3
99%
grok-4.6
99%
grok-build-0.1
99%
grok-imagine-image
99%
hy3
99%
Kimi-K2.5
99%
meta/llama-3.2-11b-vision-instruct
99%
meta/llama-3.2-90b-vision-instruct
99%
meta/llama-guard-4-12b
99%

Showing 25 of 192 model rows

Free resources

Community-shared API keys and redeem codes associated with S3AI API.

Free API keys

2
View all
API key / StatusAPI URLModelsSubmitted

sk-BrP***mwzI

Available
https://ai.furry.vg/v1openai/gpt-5.6-luna · Kwai-Kolors/Kolors · +4qweasdzxc2024· Aug 25, 2026

sk-fB3***cvx2

Unavailable
https://ai.furry.vgModels pendingbba321· Jul 23, 2026

Free redeem codes

1
View all
Redeem codeRedeem value / Remaining / totalRedemption requirementsShared by / date
ht***zl$0.10· 97/99New users onlyai coder· Sep 5, 2026

Recent Test Records

TimeModelSpeedLatency
Aug 30, 09:15 AM
openai/gpt-5.6-luna
45.58 tok/s
1.79s
Aug 25, 09:21 PM
Kimi-K2.6-free
115.85 tok/s
18.26s
Aug 25, 09:21 PM
MiniMax-M2.7-free
67.62 tok/s
0.83s
Aug 25, 09:21 PM
deepseek-v4-flash-0731-free
48.26 tok/s
0.83s
Aug 25, 09:21 PM
mimo-v2.5
64.98 tok/s
4.32s
Aug 25, 09:21 PM
openai/gpt-5.6-luna
52.98 tok/s
2.12s
Jul 24, 04:46 AM
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
24.51 tok/s
16.55s
Jul 23, 03:46 AM
openai/gpt-5.6-terra
50.07 tok/s
3.05s

Similar API Provider Alternatives to Compare

Compare S3AI API alternatives against 6 nearby API providers using 428 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
S3AI API

s3ai-api

Current provider baseline1920N/A59 tok/s9770%
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.

  • Faster measured speed
  • Higher 30-day availability
  • More free-model options
  • Broader model coverage
  • Same provider category
3359$0.095/M138 tok/s9960%
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.

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
1,0780$0.0031/M649 tok/s9960%
天絮 API

tianxu-api

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

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
7590$0.014/M93 tok/s9910%
OpenRouter

openrouter

A unified API interface providing access to over 300 models from 60+ providers, including OpenAI, Anthropic, and Google.

  • Faster measured speed
  • Higher 30-day availability
  • Broader model coverage
  • Same provider category
5930N/A85 tok/s9990%
速创API

suchuang

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

  • Faster measured speed
  • 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.

  • Faster measured speed
  • More free-model options
  • Broader model coverage
  • Same provider category
498211N/A67 tok/s7090%

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.