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

Models
759 models
From
$0.014/M
Speed
93 tok/s
Updated
8/20/2026
Latency
0.00 s
Created At
8/13/2025
Recharge Rate
¥50.00 per $1 quota

Features

DrawingTaskData ExportCheck-in

Login Methods

GitHubLinuxDOPasskey天絮网盘Microsoft

API Endpoints

  • Endpoint 1Historical / Unverified
    https://tx.x.ahne.cn
  • Endpoint 2Historical / Unverified
    https://chat-api.tx648.cn
  • Tunnel Route
    https://chat-api4.087654.xyz/

    Main site

  • Endpoint 4Historical / Unverified
    https://chat-api4.087654.xyz
  • HK Node 1
    https://chat-api4-3.087654.xyz

    HK-CF, better than the main FRP address

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 天絮 API

天絮 API is a unified gateway for accessing various large language models (LLMs) and AI services. It offers standardized API endpoints compatible with multiple providers, allowing users to switch between different models by changing the base URL.

Key capabilities:

  • Chat completions (/v1/chat/completions, /v1/responses, /v1/messages)
  • Model management (/v1beta/models)
  • Embeddings (/v1/embeddings)
  • Reranking (/v1/rerank)
  • Image generation and editing (/v1/images/generations, /v1/images/edits, /v1/images/variations)
  • Audio processing (/v1/audio/speech, /v1/audio/transcriptions, /v1/audio/translations)

Supported providers include: MoonshotAI, OpenAI, Grok, Zhipu, Volcengine, Cohere, Claude, Gemini, Suno, Minimax, Wenxin, Spark, Qingyan, DeepSeek, Qwen, Midjourney, AzureAI, Hunyuan, Xinference, and others.

Notable features: No subscription required, pay-as-you-go pricing model. The service emphasizes better pricing and stability compared to direct provider access.

Typical use cases: Developers and businesses needing unified access to multiple AI models without managing separate API integrations.

Health Check

99%Recent availability
History (72 pts)
PastNow

API Benchmarks & Pricing

Compare 442 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

Model
Input ($/M)
Output ($/M)
$2.00/M$2.00/M
Qwen/Qwen-Image-Editdefault
$535.71/M$535.71/M
Qwen/Qwen-Image-Edit-2509default
$535.71/M$535.71/M
Qwen/Qwen3-VL-Reranker-8Bdefault
$535.71/M$535.71/M
Tongyi-MAI/Z-Imagedefault
$535.71/M$535.71/M
Tongyi-MAI/Z-Image-Turbodefault
$535.71/M$535.71/M
Wan-AI/Wan2.2-I2V-A14Bdefault
$535.71/M$535.71/M
$535.71/M$535.71/M
kimi-k3default
$21.43/M$107.14/M
$7.14/M$42.86/M
$17.86/M$107.14/M
$35.71/M$214.29/M
grok-4.5default
$14.29/M$42.86/M
$14.29/M$71.43/M
$6.64/M$21.43/M
$5.29/M$25.00/M
$21.43/M$128.57/M
$535.71/M$535.71/M
@cf/meta/llama-3.2-11b-vision-instruct
--
@cf/meta/llama-4-scout-17b-16e-instruct
--
@cf/mistralai/mistral-small-3.1-24b-instruct
--
aqa
--
ascend-tribe/pangu-pro-moe
--
babbage-002
--
baidu/ERNIE-4.5-300B-A47B
--

Showing 25 of 442 model rows

Recent Test Records

TimeModelSpeedLatency
May 2, 11:20 AM
LongCat-Flash-Lite
61.40 tok/s
7.78s
May 2, 11:18 AM
LongCat-Flash-Chat
118.05 tok/s
5.70s
May 2, 11:17 AM
LongCat-Flash-Chat
100.90 tok/s
6.67s
May 2, 11:16 AM
wbot-2
88.62 tok/s
1.72s
May 2, 11:15 AM
wbot-2-code
51.75 tok/s
1.77s
May 2, 11:13 AM
gpt-5.4
46.34 tok/s
3.29s
May 2, 11:11 AM
deepseek-v4-pro
48.13 tok/s
4.11s
May 2, 11:10 AM
deepseek-v4-flash
49.02 tok/s
2.64s
May 2, 11:08 AM
gpt-5.5
60.91 tok/s
5.31s
Sep 20, 10:07 AM
gemini-2.0-flash-001
108.11 tok/s
2.70s

Similar API Provider Alternatives to Compare

Compare 天絮 API alternatives against 6 nearby API providers using 1370 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

ProviderWhy compareModelsFreeAvg priceSpeed30d uptime
天絮 API

tianxu-api

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

Current provider baseline7590$0.014/M93 tok/s9910%
初叶🍂Furry API

ai-chuyel-top

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

  • Faster measured speed
  • More free-model options
  • Broader model coverage
  • Same provider category
1,021152$18.00/M171 tok/s2350%
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
  • Same provider category
5660$0.0031/M649 tok/s9960%
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
  • Same provider category
3359$0.095/M138 tok/s9960%
VSLLM

vsllm-com

VSLLM runs a New API-powered AI gateway on vsllm.com for aggregated model access through a single endpoint.

  • Faster measured speed
  • Higher 30-day availability
  • More free-model options
  • Same provider category
2092$0.056/M174 tok/s9960%
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
  • Same provider category
5100$0.0020/M74 tok/s9960%
小水管 API

edge-pieixan-icu

Pie-Xian (小水管) provides an OpenAI-compatible API relay with multiple endpoints including api.pie-xian.com and edge nodes.

  • Faster measured speed
  • More free-model options
  • Same provider category
4952$0.054/M260 tok/s9900%

Announcements

success8/22/2026

If the light mode is hard to read, try dark mode — it works well in practice.

warning5/3/2026

Users who haven't verified by joining the group will be limited to RPM=2.

Join the group for verification~

warning2/24/2026

Be sure to click the top right corner to view notifications (announcement cannot fit here).

success8/14/2025

API site is back online, everyone.

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.