Claude Code Guide
Set up Flaq AI Claude models and explore Claude Code skills
Try Gemini 3.6 Flash API for image-to-text, visual Q&A, OCR, analysis, and streaming multimodal responses through Flaq AI's stable Google API access.
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
method: 'POST',
headers: {
Authorization: 'Bearer YOUR_API_KEY',
Accept: 'text/event-stream',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'gemini-3.6-flash-image-to-text',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Describe the image and extract any visible text.' },
{
type: 'image_url',
image_url: {
url: 'https://example.com/sample-image.jpg'
}
}
]
}
],
stream: true,
max_tokens: 2048
})
});
const reader = response.body.getReader();
const decoder = new TextDecoder();
let buffer = '';
let assistantText = '';
while (true) {
const { done, value } = await reader.read();
if (done) break;
buffer += decoder.decode(value, { stream: true });
const frames = buffer.split('\n\n');
buffer = frames.pop() || '';
for (const frame of frames) {
const lines = frame.split('\n').filter(Boolean);
let eventName = 'message';
const dataLines = [];
for (const line of lines) {
if (line.startsWith('event:')) {
eventName = line.slice(6).trim();
} else if (line.startsWith('data:')) {
dataLines.push(line.replace(/^data:\s*/, ''));
}
}
const raw = dataLines.join('\n').trim();
if (raw === '[DONE]') {
console.log('\nFinal text:', assistantText);
continue;
}
let payload;
try {
payload = JSON.parse(raw);
} catch {
continue;
}
if (eventName === 'error' || payload.error) {
const msg = payload.error?.message ?? payload.message ?? 'Chat request failed';
throw new Error(msg);
}
const delta = payload.choices?.[0]?.delta;
if (delta?.content) {
assistantText += delta.content;
console.log(assistantText);
}
}
}
import json
import requests
response = requests.post(
'https://api.flaq.ai/api/v1/chat/completions',
headers={
'Authorization': 'Bearer YOUR_API_KEY',
'Accept': 'text/event-stream',
'Content-Type': 'application/json',
},
json={
'model': 'gemini-3.6-flash-image-to-text',
'messages': [
{
'role': 'user',
'content': [
{'type': 'text', 'text': 'Describe the image and extract any visible text.'},
{
'type': 'image_url',
'image_url': {
'url': 'https://example.com/sample-image.jpg'
}
},
],
}
],
'stream': True,
'max_tokens': 2048,
},
stream=True,
)
response.raise_for_status()
event_name = 'message'
assistant_text = ''
for raw_line in response.iter_lines(decode_unicode=True):
if not raw_line:
event_name = 'message'
continue
if raw_line.startswith('event:'):
event_name = raw_line.replace('event:', '', 1).strip()
continue
if raw_line.startswith('data:'):
raw_data = raw_line.replace('data:', '', 1).strip()
if raw_data == '[DONE]':
print('\nFinal text:', assistant_text)
continue
payload = json.loads(raw_data)
if event_name == 'error' or payload.get('error'):
error = payload.get('error') or payload
raise RuntimeError(error.get('message', 'Chat request failed'))
choices = payload.get('choices') or []
if choices:
delta = choices[0].get('delta') or {}
content = delta.get('content')
if content:
assistant_text += content
print(content, end='', flush=True)
curl -N -X POST "https://api.flaq.ai/api/v1/chat/completions" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Accept: text/event-stream" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.6-flash-image-to-text",
"messages": [
{
"role": "user",
"content": [
{ "type": "text", "text": "Describe the image and extract any visible text." },
{
"type": "image_url",
"image_url": {
"url": "https://example.com/sample-image.jpg"
}
}
]
}
],
"stream": true,
"max_tokens": 2048
}'
| Parameters | Price | Original Price | Discount |
|---|
Gemini 3.6 Flash Image-to-Text API gives Flaq AI applications a focused path from visual input to useful text. Built on Google's multimodal Gemini 3.6 Flash model, the route combines an image with an instruction so teams can ask questions, extract observations, explain screenshots, and prepare visual content for downstream workflows. It keeps the integration deliberately narrow: a focused visual request produces text rather than generated media.
Multimodal Visual Understanding: Combine an image and natural-language instruction to create grounded visual descriptions, answers, and analyses.
Efficient Image Question Answering: Use the Flash model family for responsive visual tasks such as screenshot explanation, product-detail extraction, and image comparison.
Focused Visual Workflow: Keep each request centered on a focused image input, making the route straightforward to use in product features and review queues.
Documented Image Delivery: Send images through the configured Flaq AI request pattern that fits your application's upload and storage workflow.
Message-Based Context: Add system guidance, user intent, and conversational context around visual questions when the task needs clearer constraints.
Text-First Integration: Receive text suitable for display, review, routing, and automation without treating the endpoint as an image-generation service.
Input: A supported image paired with a prompt that specifies the question, description, extraction, or comparison task.
Output: Text responses grounded in the supplied image and the request context.
Image Delivery: Provide an image according to the configured Flaq AI request format.
Capabilities: Visual question answering, screenshot explanation, image summarization, detail extraction, and image-grounded content drafting.
UI and Product Review: Turn screenshots into interface descriptions, bug-report drafts, visual QA notes, or actionable design feedback.
Catalog Enrichment: Extract visible attributes and draft product descriptions for human-reviewed commerce and inventory workflows.
Customer Support Triage: Interpret screenshots and user-submitted images to suggest questions, responses, and routing decisions for support teams.
Accessibility Assistance: Produce draft image descriptions and visual summaries that editors can review and refine before publishing.
Document and Diagram Explanation: Help users understand charts, diagrams, slides, and visual references through clear generated text.
Note This route is configured for focused image input and text output. Review image-derived output before using it for safety-critical, legal, medical, financial, or compliance decisions.
Gemini 3.6 Flash Image-to-Text vs. Gemini 3.5 Flash Image-to-Text
Gemini 3.5 Flash provides a familiar option for
image-to-text tasks. Gemini 3.6 Flash is the newer model generation for teams that want an efficient multimodal API
with stronger reasoning and coding-adjacent planning support.
Gemini 3.6 Flash Image-to-Text vs. Gemini 3.7 Flash Image-to-Text
Gemini 3.7 Flash is the more recent Flash model
for complex agentic and multimodal workflows. Gemini 3.6 Flash offers a balanced visual-understanding route when a
focused image-to-text workflow is the priority.
Gemini 3.6 Flash Image-to-Text vs. Grok 4.6 Image-to-Text
Grok 4.6 is a useful xAI alternative for image-grounded
technical reasoning. Gemini 3.6 Flash provides Google's multimodal model family with a focused Flaq AI integration for
visual questions and content operations.
Gemini 3.6 Flash Image-to-Text vs. GPT 5.6 Terra Image-to-Text
GPT 5.6 Terra visual models support broad multimodal application
scenarios. Gemini 3.6 Flash is a strong choice to evaluate when teams need an efficient Gemini-based route for
screenshots, products, and image-grounded text output.
Gemini 3.6 Flash Image-to-Text vs. Claude Vision
Claude vision models can be well suited to document and
explanatory tasks. Gemini 3.6 Flash offers another production-ready API option for visual analysis with a clear
image-to-text boundary.
Set up Flaq AI Claude models and explore Claude Code skills

Set up Flaq AI GPT models and explore Codex skills
Use Flaq AI LLM models in Hermes Agent
Use GLM 5.2, Kimi K3, and DeepSeek v4 in ZCode
Run DeepSeek Harness with Flaq AI DeepSeek models
Connect AI agents to Flaq image and video generation tools
Use GPT 6 Astra and Claude Fable 5.1 in WorkBuddy