Primary endpoint
https://llm.apixo.ai
APIXO is a multilingual AI API platform for image, video, audio, and text models, with public pricing for Claude, GPT, Gemini, Grok, and usage-based billing from a USD balance.
OpenAI Claude Gemini Grok Codex Usage-based Multimodal Multilingual Trial credit
Share this provider
APIXO API proxy overview
Model, billing, payment, and verification summary.
- Platform type
- Unknown
- Model providers
- Billing
- Usage-based · Pricing public
- Price reference
- About 31% off on average · Min top-up $10
- Payment and invoice
- Visa / Mastercard / American Express / WeChat Pay / Alipay / Google Pay / Stripe · Invoice support not documented
- Support
- Public check
- Domain 9m 18d · 2026-08-24
- Traffic reference
- 20.26K/mo
Traffic estimate
Monthly visits
20.26K
2026/07
Supported models
AnthropicOpenAIGoogleSpaceXAI
claude-opus-4-8claude-opus-4-7claude-opus-4-6claude-opus-4-5-20251101claude-sonnet-4-6claude-sonnet-4-5-20250929claude-haiku-4-5-20251001gpt-5.6-solgpt-5.6-terragpt-5.6-lunagpt-5.5gpt-5.4gpt-5.4-minigpt-5.3-codexgpt-5.2-codexgpt-5.2gpt-5-minigpt-image-2gemini-3.6-flashgemini-3.5-flashgemini-3.1-pro-previewgemini-3-flash-previewgemini-2.5-progrok-4.5grok-image
ProvidersAnthropicOpenAIGoogleSpaceXAI
Model price history
ModelInputOutput/ 1M tokens7D
API endpoints
Primary endpoint
https://llm.apixo.ai/v1
Payment methods
Visa
Mastercard
American Express
WeChat Pay
Alipay
Google Pay
Stripe
Support channels
Emailsu***t@ap***.ai
Who is APIXO for?
Good fit for APIXO
Developers who need text and media models in one platform
The public catalog covers LLM, image, video, and audio models under one account balance.
Users who want to validate real API calls with a small top-up
Signup includes $0.50 credit, billing is usage-based, top-ups start at $10, and balances do not expire.
Not a fit for APIXO
Teams that require CNY settlement or mainland China invoices
Public prices and the minimum top-up are shown in USD, and invoice support has not been verified.
Buyers who need a long operating history before adoption
The domain was registered in November 2025, so the observable third-party traffic history remains short.
FAQ excerpts
Integration and authentication
3
When should I use the Generation API, Chat API, or APIXO MCP?
Use the asynchronous Generation API for image, video, audio, and utility models; use the Chat API for Claude, OpenAI Responses, and Gemini-compatible calls; use MCP to discover model schemas or generate integration code in tools such as Cursor, Claude Code, and Codex.
Can I use the official Claude, OpenAI, and Gemini SDKs?
Yes. Keep the official request format and replace the API key and base URL: Claude and Gemini use https://llm.apixo.ai, while OpenAI Responses uses https://llm.apixo.ai/v1. Switch models by changing only the model ID.
How is the APIXO API key sent with each API format?
The Generation API and OpenAI Responses use Authorization: Bearer; Claude uses x-api-key plus anthropic-version: 2023-06-01 for raw HTTP; Gemini uses x-goog-api-key. Keep the API key in server-side environment variables.
Tasks and routing
2
How do generation tasks return results, and should I poll or use webhooks?
The Generation API returns a taskId first; development and low-volume integrations can poll every 3–5 seconds, while production services can use an HTTPS webhook. The webhook must return HTTP 200 within 30 seconds, failed deliveries are retried up to three times, and result URLs expire after 24 hours.
What is the difference between Auto, Value, and Official routing?
Routing is configured per API key. Auto tries lower-cost Value routes first and fails over to Official when availability or health issues occur; Value prioritizes lower-cost partner routes; Official uses official or officially authorized routes. Switching does not require a new key or code changes.
Streaming and troubleshooting
2
Does the Chat API support streaming for Claude, OpenAI, and Gemini?
Yes. APIXO preserves each compatible API's SSE format. Set stream: true for Claude and OpenAI Responses; use :streamGenerateContent?alt=sse for Gemini, and keep the parser expected by the original provider format.
Which LLM Gateway errors are safe to retry?
Use exponential backoff only for transient 429, 500, 502, and 504 failures, for example after 1, 2, and 4 seconds before stopping or handing off to a queue. Do not blindly retry 400, 401, or 403 responses, invalid models or request parameters, missing protocol headers, or requests that already produced a successful streamed response.
MCP integration
1
What does APIXO MCP require, and what can it do?
It requires Node.js 20+, npm 9+, and an APIXO API key, runs through npx -y @apixo/mcp-server, and connects to stdio MCP clients such as Cursor, Claude Code, and Codex. A healthy install can list models, inspect schemas, submit generation tasks, check task status, and read the account balance.
Domain record
- Domain created
- 2025-11-06
- Domain expires
- 2027-11-06
- Domain age
- 9m 18d
Certificate record
- First issued
- 2026-06-30
- Current issuer
- WE1
- Valid until
- 2026-09-28
Similar providers
Providers matched by related search intent, model coverage, payment methods, and pricing signals.
MuskAI MuskAI is a multi-model API proxy for AI coding and application workloads. It provides OpenAI- and Anthropic-compatible access for Claude Code, Codex, Gemini CLI, and models from Claude, GPT, Gemini, Grok, and more, with token-based billing. About 82% off on average Min top-up ¥10 Subscription plan USDT Claude averages 7.4% of official pricing, as low as 7.4% of official pricing; GPT averages 3.2% of official pricing, as low as 1.8% of official pricing; Gemini averages 8.3% of official pricing, as low as 8.3% of official pricing; Grok averages 2.8% of official pricing, as low as 2.8% of official pricing; DeepSeek averages 43.7% of official pricing, as low as 43.6% of official pricing; Kimi averages 42.7% of official pricing, as low as 42.7% of official pricing. Usage is billed by token, top-ups start at CNY 10, and subscriptions are also available. The current lowest price comes from the Codex promotional group and may change. Open site 
OpenModel OpenModel is a multi-model API proxy compatible with OpenAI Responses, Anthropic Messages, and Gemini APIs, with unified API keys, failover, request logs, usage analytics, and public model pricing. About 36% off on average Min top-up $5 Usage-based Visa Claude averages 46.1% of official pricing, as low as 40% of official pricing; GPT averages 30.7% of official pricing, as low as 10% of official pricing; Gemini averages 80% of official pricing, as low as 50% of official pricing; Grok averages 95% of official pricing, as low as 95% of official pricing; DeepSeek averages 52.5% of official pricing, as low as 25% of official pricing; Kimi averages 80% of official pricing, as low as 80% of official pricing. Usage is billed per 1M tokens with no monthly minimum; top-ups start at $5. Open site 
OmniaKey OmniaKey is a multi-model API gateway for coding agents, with OpenAI, Anthropic, and Gemini protocols for Claude Code, Codex CLI, and Gemini CLI. About 38% off on average Min top-up $3 Usage-based USDT Claude averages 24.7% of official pricing, as low as 24% of official pricing; GPT averages 14.5% of official pricing, as low as 7% of official pricing; Gemini averages 80% of official pricing, as low as 80% of official pricing; Grok averages 1.6x official pricing, as low as 1.6x official pricing; DeepSeek averages 33% of official pricing, as low as 33% of official pricing. Usage is billed per token in USD per 1M tokens, with no subscriptions or account tiers, and balances do not expire. Stripe top-ups start at $3 and USDT top-ups at $15. Open site Next steps to compare
Continue with the path that matches your next step.
Compare low-cost OpenAI-compatible optionsUse this path when price, minimum top-up, and payment method are your first filters.Find OpenAI-compatible proxy providersUse this comparison when you need GPT or OpenAI-style API access through a proxy.Compare Claude API proxy optionsUse this path when Claude model coverage is the main reason you are checking providers.Find proxy options for CodexUse this when you want to connect Codex to an OpenAI-compatible endpoint.Compare services like OpenRouterUse this when you want a multi-model API gateway or an OpenRouter alternative.Browse the full AI API directoryUse this when you want to compare providers across models, pricing, and payment methods.