AI Models API
A flat monthly price for API access to three models — qwen3.8 for chat, code and documents, qwen-image for image generation and editing, and gemma-4 for writing and drafting. Unlimited tokens on every plan; plans differ by speed: requests per minute, concurrency, tokens per hour and request size.
Choose plan
Mini
For trying the API, hobby scripts and light personal use.
-
Req / minute
5 -
Concurrent
1 -
Tokens / hour
500k
- Unlimited tokens — no monthly cap
- Up to 3 images / hour
- Requests up to 32k tokens
- All three models
- OpenAI-compatible endpoint
Starter
For personal projects, scripts and small bots.
-
Req / minute
20 -
Concurrent
1 -
Tokens / hour
2M
- Unlimited tokens — no monthly cap
- Up to 10 images / hour
- Requests up to 128k tokens
- All three models
- OpenAI-compatible endpoint
Pro
For a team that works with AI all day.
-
Req / minute
60 -
Concurrent
4 -
Tokens / hour
6M
- Unlimited tokens — no monthly cap
- Up to 30 images / hour
- Requests up to 256k tokens
- All three models
- Embeddings: nemotron-embed-8b
- OpenAI-compatible endpoint
Scale
For automations, agents and heavy workloads.
-
Req / minute
120 -
Concurrent
8 -
Tokens / hour
12M
- Unlimited tokens — no monthly cap
- Up to 60 images / hour
- Requests up to the model’s context window
- All three models
- Embeddings: nemotron-embed-8b
- OpenAI-compatible endpoint
Billed monthly in US dollars through PayPal. No commitment, cancel any time.
Three models, in every plan
All three run behind one OpenAI-compatible endpoint — switch models by changing the model name.
qwen3.8
qwen3.8-flash-next Fast general-purpose model and the default choice for chat, summaries, drafting, translation, code and pulling data out of documents and emails. It takes the full request size your plan allows, so long documents and large codebases belong here.
qwen-image
qwen-image Generates images from a text prompt on /v1/images/generations and edits images you already have on /v1/images/edits: banners, product shots and campaign visuals. Your plan sets the pace: up to 3 images an hour on Mini, 10 on Starter, 30 on Pro and 60 on Scale.
gemma-4
gemma-4-26b Google’s open-weight Gemma 4 (Apache 2.0): a second general-purpose model for writing, drafting, replies and translation. Requests up to 32k tokens, prompt and answer together, on every plan.
Pro and Scale also include embeddings for search and RAG on /v1/embeddings: nemotron-embed-8b for documents and nemotron-embed-8b-query for questions.
Plan, key, paste. A few minutes.
-
Choose a plan
Pick Mini, Starter, Pro or Scale on reeva.me and pay with PayPal. Your account is created and your first key is issued as soon as the payment clears.
-
Create more keys
Give each tool its own key, with a name and an optional expiry. Up to 10 keys; revoke any one of them on its own.
-
Paste it into your tool
Base URL and key — in Python, curl, opencode or Cline. The same code you wrote for OpenAI.
from openai import OpenAI
client = OpenAI(
base_url="https://api.reeva.me/v1",
api_key="<your API key>",
)
# chat: qwen3.8-flash-next · gemma-4-26b — images: qwen-image
reply = client.chat.completions.create(
model="qwen3.8-flash-next",
messages=[{"role": "user", "content": "Hello!"}],
)Works with any tool that speaks the OpenAI API: opencode, Continue, Aider, Cline, the OpenAI SDKs and curl.
AI Models API — frequently asked questions
Which models does the AI Models API include?
Every plan includes three models: qwen3.8 for chat, summaries, drafting, code and long documents, qwen-image for image generation and editing, and gemma-4 for writing and drafting. Plans differ only in how hard you can use them: requests per minute, how many requests run at once, tokens and images per hour, and the largest single request — 32k tokens on Mini, 128k on Starter, 256k on Pro (Scale: no plan limit, only the model’s context window). gemma-4 is the exception: up to 32k tokens per request on every plan. gpt-oss-20b has been retired, and requests that name it are refused: use qwen3.8-flash-next for code and agents, and gemma-4-26b for writing and drafting.
Does the API create embeddings?
Yes, on Pro and Scale; Mini and Starter do not include them. Send POST /v1/embeddings in the OpenAI format to nvidia’s Nemotron-3-Embed-8B, which has two ids, and you need both: nemotron-embed-8b for the documents you store and nemotron-embed-8b-query for the questions you search with. Each input is embedded up to 4,096 tokens, and longer text is cut without an error, so split long documents into chunks first. Embedding tokens count toward your hourly token budget.
Will the tools I already use work?
Yes, if they speak the OpenAI API. Set the base URL to https://api.reeva.me/v1 and the API key to your key, then choose a model by name — qwen3.8-flash-next, qwen-image or gemma-4-26b. opencode, Continue, Aider, Cline, the OpenAI SDKs and curl all work this way, without code changes.
Are the tokens really unlimited?
Yes. There is no monthly token cap and no per-token billing — the price is flat. What a plan sets is speed: requests per minute, concurrent requests and tokens per hour (500k on Mini, 2M on Starter, 6M on Pro and 12M on Scale). A request larger than your plan allows is refused before it runs, with HTTP 400. The hourly budget is a rolling window: the request that takes you over it still completes, the next one is refused with HTTP 429, and the budget frees up as your earlier requests age past one hour.
How much does it cost?
Mini is $5 per month, Starter is $29 per month, Pro is $59 per month and Scale is $119 per month — a flat price with no per-token billing. Enterprise pricing is custom.
How do I get an API key?
Choose a plan on reeva.me/ai-api and pay with PayPal. Your account is created and your first key is issued as soon as the payment clears. In the control panel you can create up to 10 keys, give each one a name and an optional expiry, and revoke any key on its own — a revoked key gets HTTP 401.
Can I cancel anytime?
Yes. Plans are billed monthly through PayPal with no commitment, and you can cancel in the control panel at any time. Your key keeps working until the period you have paid for ends.
What happens when I hit a rate limit?
Requests over the per-minute limit or the limit on requests at once are refused with HTTP 429, not queued. Over the per-minute limit, retry within a minute. Over the limit on requests at once, retry as soon as one of your own requests finishes. The OpenAI SDKs retry on their own.
What if I need higher limits?
The Enterprise option offers a dedicated instance, custom rate limits, an SLA and contractual privacy terms. Contact us to discuss your workload.
The AI Models API is provided and billed through reeva.me. linux-hosting.co.il is not affiliated with, endorsed by, or sponsored by the makers of the models and tools named on this page (such as Qwen, Google’s Gemma, OpenAI or nvidia). All product names, logos, and brands are the property of their respective owners and are used here only for identification.
