Docs · Getting started
What TopxAI is
One base URL, 16 models on seven lines and prepaid USD credit. TopxAI does not store prompts or completions.
TopxAI is a model API service. Point an OpenAI- or Anthropic-compatible client at one base URL, pay from a prepaid USD balance, and the relay forwards each request to the model you named.
One endpoint
The base URL is https://api.topxai.xyz/v1. It serves OpenAI-style Chat Completions and Responses, Anthropic-style Messages, image generation and edits, video generation, and /v1/systemone for Jev. Keep your SDK; change the base URL and the key.
16 models on seven lines
- Claude:
claude-fable-5-2,claude-sonnet-5-5,claude-opus-5-5 - OpenAI:
gpt-6-astra,gpt-6.1-sol,gpt-6.1-terra,gpt-image-2.6-sunburst,gpt-image-2.6-flare - Grok:
grok-4.7,grok-imagine-video-1.5 - GLM (private deployment):
GLM-5.3-Abliterated,GLM-5.3-Flash-Abliterated - Kimi (private deployment):
kimi-k3.1-pro - DeepSeek (private deployment):
deepseek-flash-Abliterated,deepseek-flash-fast - Jev:
jev-1.14.0(jev-latestandjev-previeware its aliases, billed and answered as it)
Claude, OpenAI, Grok and Jev use the providers' own models. The GLM, Kimi and DeepSeek lines are served from private deployments, not the providers' own APIs. GLM-5.3-Abliterated, GLM-5.3-Flash-Abliterated and deepseek-flash-Abliterated have the refusal alignment removed and form the Abliterated group on the price list; deepseek-flash-fast is DeepSeek V4.1 Flash 1017 on standard weights, and Kimi K3.1 Pro is Moonshot's model. GLM-5.3-Abliterated accepts text only; the other four accept text and images.
Routes and prices
Every price is a fixed USD figure per model and route, listed under Models & pricing at https://api.topxai.xyz/#models. For Claude, OpenAI and Grok the shared pool is 50% of the provider's list price and the official line 90%. Jev costs $0.055 per million input tokens, output free; its costlier standby line, which answers only when the main line fails, bills $0.058. The GLM, Kimi and DeepSeek models have their own fixed private-deployment prices, the same at every hour; their model pages list them.
A key is pinned to one route, such as claude-shared, or set to Auto route, which picks the lowest-priced line that serves each request's model.
Text bills per million tokens with separate input, output and cache lanes; images per picture by size (1K, 2K or 4K); video per second by resolution (480p, 720p or 1080p). Once the input reaches 272,001 tokens on gpt-6-astra, gpt-6.1-sol or gpt-6.1-terra, or 200,000 tokens on grok-4.7, the whole request bills at long-context lanes: double the input price, higher output. Each request writes a usage-log row with model, route and charge.
Prepaid USD
Credit is added on the Wallet page in the Top up panel, by Card / local payment (on Waffo's hosted checkout) or USDT / USDC, between $10 and $10,000 per payment; an unpaid order expires after 60 minutes. Redeem a code takes a Redemption code; Gift cards sells one to keep or give away. Only your own requests spend the balance, and every deduction is listed.
Zero retention
Prompts, completions and uploaded files pass through TopxAI in memory and are never written to disk; bodies, headers and upstream error bodies are not stored. What is kept is metadata: token counts, model name, route, status, latency, timestamps, the API key identifier, request ids and the charge. The provider serving the request handles the content under its own terms and retention policy, which TopxAI does not control.
Support
The help button at the bottom right of the site, or support@topxai.xyz.
Related
- Create an API key and choose a route
- Connect your SDK
- Shared pool, official line and auto route
- Every model's price
- What TopxAI stores and what it never stores
Next: Create an API key and choose a route
Other languages: 简体中文