Primary endpoint
https://api.openmodel.ai
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.
OpenAI Claude Gemini Codex Grok DeepSeek Usage-based Stripe Alipay
Share this provider
Visit site →
Site link includes an invite code
OpenModel API proxy overview
Model, billing, payment, and verification summary.
- Platform type
- Built with Sub2API
- Model providers
- Billing
- Usage-based · Pricing public
- Price reference
- About 10% of official pricing, saving roughly 90% · Min top-up $5
- Payment and invoice
- Visa / Mastercard / American Express / Alipay / Google Pay / Stripe · No invoice note found
- Support
- Discord / Email
- Public check
- Domain 7y 11m 9d · 2026-08-08
- Traffic reference
- 271.21K/mo
Traffic estimate
Monthly visits
271.21K
2026/07
Supported models
AnthropicOpenAIGoogleSpaceXAIDeepSeekMoonshot
claude-fable-5claude-opus-5claude-sonnet-5claude-opus-4-8claude-opus-4-7claude-opus-4-6claude-sonnet-4-6claude-sonnet-4-5claude-haiku-4-5-20251001gpt-5.6-solgpt-5.6-terragpt-5.6-lunagpt-5.5gpt-5.4-progpt-5.4gpt-5.4-minigpt-5.3-codexcodex-auto-reviewgemini-3.6-flashgemini-3.5-flashgemini-3.5-flash-litegemini-3.1-pro-previewgemini-3-flash-previewgrok-4.5deepseek-v4-prodeepseek-v4-flashkimi-k3kimi-k2.7-codekimi-k2.6kimi-k2.5
ProvidersAnthropicOpenAIGoogleSpaceXAIDeepSeekMoonshot
Model price history
ModelInputOutput/ 1M tokens7D
API endpoints
Payment methods
Visa
Mastercard
American Express
Alipay
Google Pay
Stripe
Support channels
Who is OpenModel for?
Good fit for OpenModel
Development teams integrating multiple model providers
It supports OpenAI, Anthropic, and Gemini protocols while centralizing routing and failover in the gateway.
Teams that need per-project cost controls and usage auditing
API keys can have spending quotas, expiration dates, and reset periods, while the console shows usage and request details by key.
Users who prefer usage-based access without a monthly plan
The service charges by token with no monthly minimum, which suits projects with variable usage.
Not a fit for OpenModel
Users who need confirmed availability in mainland China
Mainland China is not on the current official supported-region list, so availability must be confirmed with OpenModel before use.
Workloads whose data must not reach third-party model providers
Request content is forwarded to the selected or routed upstream provider and is subject to that provider's policies.
Teams that require confirmed invoicing, a public status page, and a contractual SLA before procurement
Invoicing and an independent status page are not currently confirmed. The service-specific terms state an availability target, but plan coverage and contractual guarantees still need confirmation from OpenModel.
FAQ excerpts
Integration and operations
2
Why not call upstream model providers directly?
Direct integrations scatter routing logic, credentials, and operational visibility across clients. OpenModel centralizes them in one control plane.
Are request logs and usage analytics included?
Yes. Request logs, usage changes, and billing context are core gateway capabilities.
Suitable teams
1
Who is OpenModel primarily designed for?
It is primarily designed for teams already running real model traffic that need unified API access and clearer operations.
Protocols and authentication
1
Which API protocols and authentication methods are supported?
The same om-prefixed API key works with OpenAI Responses, Anthropic Messages, and Gemini-compatible endpoints. OpenAI uses Bearer authentication, while X-Api-Key and X-Goog-Api-Key are recommended for Anthropic and Gemini respectively.
Reliability and rate limits
1
What happens during rate limits or upstream failures?
The platform enforces RPM and TPM limits at both user and channel levels. If a channel hits its limit, the gateway may route the request to another available channel for the same model. The documentation recommends exponential backoff with jitter for 429 and 5xx errors.
Privacy and data
1
Does OpenModel store prompts and model responses?
The privacy policy says inputs and outputs are not stored persistently or used to train OpenModel's own models. Request metadata and API usage logs are retained for 180 days. Content is still forwarded to upstream model providers and remains subject to their policies.
Regional availability
1
Is OpenModel available in every country and region?
No. Service is limited to the countries and regions on the official supported list, and some services may have additional restrictions. Mainland China was not listed at the time of verification, so users in unlisted regions should confirm availability with support first.
Top-ups and refunds
1
Can a top-up be refunded?
A refund request can be submitted in the console; the requested amount is frozen during review and an administrator approves or rejects it. The terms also state that payments are generally non-refundable unless explicitly provided by the terms or required by law.
Domain record
- Domain created
- 2018-09-02
- Domain expires
- 2028-09-02
- Domain age
- 7y 11m 9d
Certificate record
- First issued
- 2026-07-11
- Current issuer
- WE1
- Valid until
- 2026-10-09
Similar providers
Providers matched by related search intent, model coverage, payment methods, and pricing signals.
RunAPI RunAPI provides multi-model AI API aggregation and smart routing with OpenAI, Anthropic, and Google-compatible interfaces, covering Claude, GPT, Gemini, Grok, and DeepSeek with Claude Code and Codex support, USD billing, card payments, and Alipay top-ups. About 7.4% of official pricing, saving roughly 93% Min top-up $5 Usage-based Visa GPT and Codex models start at about 7.4% of official pricing, Claude models at 60%, and Gemini models at 21%. Top-ups use USD with usage-based or per-request billing; comparisons use the codex group for GPT and Codex, default for Claude, and discounts for Gemini. The minimum top-up is $5, signup includes $0.10 credit, and credits do not expire. Open site 
TeamoRouter TeamoRouter is a multi-model API routing service for Claude Code, Codex, and Gemini CLI. It supports OpenAI-, Anthropic-, and Gemini-compatible APIs, usage-based USD billing, public live model pricing, and Alipay top-ups. About 10% of official pricing, saving roughly 90% Min top-up $5 Usage-based Visa GPT models start at about 10% of official pricing, Claude at about 16%, and Gemini at about 20%. Billing uses USD and tokens, with a $5 minimum top-up, no monthly fee or subscription, and non-expiring credits; model discounts adjust with upstream costs. 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 7% of official pricing, saving roughly 93% Min top-up $3 Usage-based USDT GPT models start at 7% of official pricing, Claude models at 20%, and Gemini models at 80%. 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.