Claude Code Guide
Set up Flaq AI Claude models and explore Claude Code skills
Try Gemini 3.7 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-3.7-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-3.7-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-3.7-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 3.7 Flash Image-to-Text API connects Flaq AI applications to Google's latest Flash model for fast, capable visual understanding. Send a focused image input with a clear instruction to produce text that describes, explains, extracts, or analyzes visual content. The route pairs Gemini 3.7 Flash's multimodal and reasoning strengths with a deliberately focused Flaq AI input boundary, making it well suited to responsive product features and review workflows.
Advanced Visual Reasoning: Turn image-grounded questions into clear text responses that reflect the supplied visual context and task instruction.
Cost-Effective Multimodal Workflow: Use a very affordable Flash configuration for visual-analysis features that need capable text output at scale.
Focused Image Request: Keep each interaction centered on a visual input and a specific goal, which helps applications produce clearer, more reviewable outputs.
Documented Image Delivery: Send image input through the configured Flaq AI API request pattern.
Message Context Support: Combine the visual request with structured system, user, and assistant messages when the task needs instructions, criteria, or follow-up context.
Responsive API Integration: Select streaming or complete response delivery to fit interactive assistants, asynchronous review jobs, and internal tools.
Input: A supported image with a natural-language prompt that defines the requested description, question, extraction, or analysis.
Output: Text responses for user-facing experiences, human review, content workflows, and downstream automation.
Image Delivery: Use the configured Flaq AI request format for the image input.
Capabilities: Image-grounded question answering, screenshot interpretation, visual detail extraction, image summarization, and content drafting.
Visual Product Experiences: Add image questions, visual search assistance, and contextual explanations to user-facing applications.
Design and QA Review: Generate first-pass notes from UI screenshots, product imagery, diagrams, and visual feedback for human review.
Support Workflows: Help agents interpret customer images and screenshots, identify useful details, and prepare response or escalation drafts.
Commerce and Catalog Operations: Extract visible attributes, draft descriptions, and support editorial review of product imagery.
Accessibility and Content Workflows: Create reviewable draft descriptions and visual summaries to help editorial teams prepare accessible content.
Note The current Flaq AI route is designed for focused image input and text output. Do not use generated analysis as the sole basis for high-impact decisions; retain appropriate human review and source verification.
Gemini 3.7 Flash Image-to-Text vs. Gemini 3.6 Flash Image-to-Text
Gemini 3.6 Flash offers a balanced multimodal
route for image questions and operations. Gemini 3.7 Flash is the newer Flash model to evaluate when the visual task
also benefits from more advanced multi-step reasoning.
Gemini 3.7 Flash Image-to-Text vs. Grok 4.6 Image-to-Text
Grok 4.6 is an xAI option for image-grounded technical
reasoning. Gemini 3.7 Flash provides a highly cost-effective Google model route for visual questions, screenshots, and
text-first product features.
Gemini 3.7 Flash Image-to-Text vs. GPT 5.6 Terra Image-to-Text
GPT 5.6 Terra visual models support broad multimodal applications.
Gemini 3.7 Flash is a compelling alternative when teams want an efficient Flash model for focused image analysis and
generated text.
Gemini 3.7 Flash Image-to-Text vs. Claude Vision
Claude vision models can be a strong choice for explanatory and
document-oriented tasks. Gemini 3.7 Flash offers a responsive visual-understanding API for teams evaluating
cost-effective multimodal workflows.
Gemini 3.7 Flash Image-to-Text vs. Gemini 3.7 Flash Text-to-Text
Text-to-Text is optimized for prompts with no
visual input. Image-to-Text is the better route when the answer must be grounded in a supplied image as well as
written instructions.
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