EN ▾
Get API key

Quickstart: Text API for Your Vision API Pipeline

Integrate our uncensored text engine into your vision pipeline using the standard OpenAI-compatible interface. This guide covers authentication, chat completions, streaming, and constraints for processing high-context vision data.

Base URL
https://api.visionllmapi.com/v1
Model
uncensored
$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute

Base URL & Authentication

Start by setting your base URL to https://api.visionllmapi.com/v1. This endpoint is compatible with standard OpenAI SDKs and any OpenAI-compatible client. You need an API key to authenticate requests. Generate one on the Get API key page by signing up with just an email and password. No credit card is required to start, and you receive $0.50 in trial credit valid for 7 days. Claim this credit with one click on your API key page. Keep your key secure; you can regenerate it at any time, which immediately invalidates the previous key.

First Request

Send a POST request to /v1/chat/completions. Use the model ID uncensored. The API accepts text input and returns text output, making it ideal for post-processing vision pipeline data. You can include system prompts to define behavior, such as instructing the model to extract structured data from OCR results or write from text descriptions of image content without content filters interfering with creative or adult-use cases.

curl https://api.visionllmapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

The response will contain the generated text in the choices[0].message.content field. If the model refuses to answer due to the hard limit on sexual content involving minors, you will receive an error or empty content depending on the specific refusal handling.

Python SDK

Use the official OpenAI Python SDK to integrate easily. Set the base_url and api_key variables to point to our service. This approach works with any OpenAI-compatible client library. The SDK handles JSON serialization and deserialization, but you are responsible for handling the response structure in your application logic.

from openai import OpenAI

client = OpenAI(base_url="https://api.visionllmapi.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

This method is suitable for batch processing or when you need synchronous execution. For real-time applications, consider using streaming responses to reduce perceived latency.

Node SDK

For JavaScript environments, use the OpenAI Node.js SDK. Configure the baseURL and apiKey to match our API endpoint. This allows you to integrate the uncensored text engine directly into your web or server-side Node.js applications. The SDK provides a familiar interface for developers already using OpenAI services.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.visionllmapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Ensure you handle the response data appropriately, as the model may return large amounts of text depending on the context window used. There are no specific guarantees about retry behavior or JSON decoding beyond what the standard SDK documentation provides.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery. This is useful for vision pipelines where you want to display results incrementally. Each event contains a partial chunk of the response, allowing you to update the user interface as text is generated.

stream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Parse the SSE stream to extract the content tokens. This reduces the time to first token, which is critical for interactive applications. Remember that the total token count still counts against your usage limits.

Rate Limits & Constraints

Each API key is limited to 300 requests per minute. The maximum request body size is 8 MB. If you exceed the rate limit, you will receive a 429 error. If your account has no credit, you will receive a 402 error. If the key is invalid, you will receive a 401 error. The context window supports up to 100,000 tokens for prompt and completion combined. This large context window ensures your vision-to-text logic isn't bottlenecked by token limits. There is no SLA guarantee, and no SOC2 or HIPAA certifications are provided. The model is tuned for lawful adult use but blocks sexual content involving minors.

02

Questions and answers

Is this a multimodal API?

No. This is a text-only API. It does not accept images, audio, or video directly. You must process vision data into text first, then send the text to this API for post-processing, extraction, or generation.

How is pricing calculated?

Pricing is pay-as-you-go with prepaid credit. Input tokens cost $0.15 per 1M tokens, and output tokens cost $0.50 per 1M tokens. Credits do not expire, and there are no monthly subscription fees.

What is the context window size?

The context window is 100,000 tokens, covering both the input prompt and the generated completion. This allows for processing large documents or extensive vision pipeline data in a single request.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Base URLhttps://api.visionllmapi.com/v1

Get API key

Technical reference

The numbers below are the real limits of this API, not marketing. Compare them with what your app needs.

FeatureSupport
CompatibilityOpenAI Chat Completions schema; official openai SDKs work unchanged
Base URLhttps://api.visionllmapi.com/v1
EndpointsPOST /v1/chat/completions · GET /v1/models
Model IDuncensored
AuthenticationBearer token in the Authorization header
Tools / tool callsSupported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages
Max outputprompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap
StreamingSupported (stream: true), usage included at the end
Max context100,000 tokens (prompt + completion together)
Sampling parameterstemperature, top_p, stop, seed, presence_penalty, frequency_penalty
Structured outputresponse_format: {"type": "json_object"}
Rate limit300 requests per minute per key
Max body8 MB request body
Concurrency8 requests at the same time per key
Response headersX-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency
Paymentcrypto: USDT on TRON or USDC on Base, $20–$500, any whole sum
Trial credit$0.50 of credit valid 7 days, no card needed · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Volume bonus+5% on $50+, +10% on $100+, +15% on $200+
Priceinput $0.15 / 1M tokens, output $0.50 / 1M tokens
How you payprepaid credit, charged by real token usage; errors and refusals are free
Subscriptionpaid credit never expires, no subscription
Contentuncensored for adults; the only hard rule: no sexual content involving minors
Sign-insign in with Google or with e-mail + password
Key managementone active key per account; a new key replaces the old one

Errors and what to do

Every error is JSON with a type you can switch on. You are never charged for an error.

HTTPTypeWhat to do
400bad_requestinvalid JSON, empty messages, bad parameter, or a prompt longer than the window — fix and resend
401missing_key · invalid_key · key_revokedno key, wrong key, or a key replaced by a newer one
402no_creditbalance is empty — top up, requests resume at once
403content_blockedrefused by the content policy
404not_foundunknown endpoint
413request_too_largerequest body larger than 8 MB
429rate_limited · concurrencyover 300/min or 8 parallel — back off and retry
503upstream_busymodel busy — retry in a few seconds