One API key, ~60 leading text models (GPT, Claude, Gemini, DeepSeek, Grok, Qwen and more), OpenAI-compatible. Pay only for what you use.
Subscribe on RapidAPI (free tier, no card to start), copy your key, and make your first call — one base_url, OpenAI-compatible, zero migration.
Get your free API key on RapidAPI →
X-RapidAPI-Key from the Endpoints tab.curl https://modelis-auto-chat.p.rapidapi.com/v1/chat/completions -H "X-RapidAPI-Key: YOUR_KEY" -H "X-RapidAPI-Host: modelis-auto-chat.p.rapidapi.com" -H "Content-Type: application/json" -d '{"model":"modelis-auto","messages":[{"role":"user","content":"Hello"}]}'modelis-auto picks the right model for each request at a flat, predictable price.Authorization: Bearer drop-in with one command, no code changes:npx modelis-openai
# then point Aider / Cline / Continue / any OpenAI SDK at:
# base_url = http://127.0.0.1:8787/v1
# api_key = your RapidAPI key, model = modelis-autoBuy a prepaid credit pack with your card — no RapidAPI account needed. You'll get a redemption code by email, apply it under Wallet in your console, then call the API with Authorization: Bearer at https://modelishub.com/v1.
Secure card checkout by Gumroad. Codes are emailed after payment (usually within a few hours). Bulk or a custom amount? Email support@modelishub.com.
中国大陆用户可直接用支付宝 / 微信购买充值码（经爱发电收款），无需境外银行卡，支付宝/微信即可付款。收到兑换码后，在 console 的「钱包 → 兑换」输入即到账，然后用 Authorization: Bearer 调 https://modelishub.com/v1。⚠️ 下单时务必在「留言/备注」填写你的 Modelis 注册邮箱，付款后我们会尽快把充值兑换码发给你。
各档到账额度以商品页标注为准（例：¥72 到账 2,600,000 credits，可用于全部模型）。
支付宝/微信扫码即付，付款后我们会尽快把兑换码发给你（记得查垃圾箱）。没收到码？发邮件到 support@modelishub.com，人工补发。
按月订阅（每月固定额度 + 专属权益，适合稳定集成）：入门 ¥59/月（3× 并发额度 · 客服优先响应）· 专业 ¥168/月（同权益 · 更大额度）· 团队 ¥468/月（6× 并发 + 专属高速通道，高峰期请求不拥堵）。在爱发电订阅 →
Authorization: Bearer on modelishub.com/v1; a RapidAPI key works only on p.rapidapi.com. Don't mix them.Usage is billed per token at each model's published rate — you are charged only for the input and output tokens you actually consume. Live per-model rates are shown in your dashboard before and during use. No hidden fees; one balance works across every model.
One endpoint, one key. You choose how the model is selected — and the pricing that comes with it. Switch any time by changing the model string.
Call modelis-auto and Modelis picks the best model for each request within a quality tier you set, billed at one predictable flat per-token rate — simple requests aren't over-billed on a frontier model, and hard ones aren't sent to a weak one.
modelis-auto — balanced default (same as :standard)modelis-auto:basic / :standard / :premium — pick the tier:high for the tier's top model (no surcharge) or :low for its cheapestKnow exactly which model you want? Name it — e.g. modelis-auto:claude-sonnet-4-6 or modelis-auto:gpt-5.5. You get that exact model on every request, billed per token at its own transparent rate.
modelis-auto:<model> — always that model, pay for what it actually costsSame base URL and key for both modes. Your dashboard shows the exact rates and which model handled each request.
| Model | Use case |
|---|---|
| claude-opus-4-8 / claude-sonnet-4-6 | Reasoning, coding, long context |
| gpt-5.5 / gpt-5.1-codex | General assistant, coding, tools |
| gemini-3.1-pro / gemini-3.5-flash | Multimodal input, fast chat |
| deepseek-v4 / grok-4.3 / qwen3.7 / glm-5.2 | Cost-efficient open & frontier models |
| modelis-auto[:basic|:standard|:premium] | Auto-pick the right model per task at a flat tier price |
Modelis is a text LLM API gateway. We do not offer image or video generation.
Call any model below by its exact name — one OpenAI-compatible base_url, same key. Grouped by provider; 42 flagship models across 11 labs shown.
| Provider | Models |
|---|---|
| OpenAI | gpt-5.2-codex gpt-5.2-pro gpt-5.3-chat-latest gpt-5.3-codex gpt-5.4 gpt-5.4-pro gpt-5.5 gpt-5.5-pro |
| Anthropic | claude-fable-5 claude-opus-4-8 claude-sonnet-4-6 claude-sonnet-5 |
gemini-2.5-flash gemini-2.5-flash-lite gemini-2.5-pro gemini-3-flash-preview gemini-3-pro-preview gemini-3.1-pro-preview | |
| xAI | grok-4-1-fast-non-reasoning grok-4-1-fast-reasoning grok-4-fast-reasoning grok-4.5 grok-code-fast-1 grok-latest |
| DeepSeek | DeepSeek-V4-Flash deepseek-v4-pro |
| Qwen | Qwen3-VL-32B-Instruct Qwen3.5-397B-A17B Qwen3.6-35B-A3B qwen3.7-max qwen3.7-plus |
| Zhipu | GLM-4.5V GLM-5 GLM-5.1 glm-5.2 |
| Moonshot | Kimi-K2.6 |
| Mistral | codestral-2508 mistral-large-2512 mistral-medium-3.1 |
| MiniMax | MiniMax-M2.5 |
| Meta | llama-4-maverick llama-4-scout |
Modelis routes to 95+ available models in total; the catalog above highlights the current-generation flagships most builders should reach for. Specialist, regional, and open models are also available and may vary by plan. Text LLMs only — no image or video generation.
Questions? support@modelishub.com