Flux 2 Klein 9B API
Higher quality image generation with enhanced detail.
Provider: Black Forest Labs | Model ID: flux-2-klein-9b | Context Window: Varies
On this model: image workload class, routed through Black Forest Labs infrastructure.
Pricing
₹2.26/image. Pay-as-you-go micro-metered billing. UPI and cards accepted with zero minimum commitment.
| Billing Unit | Price (INR) |
|---|---|
| image | ₹2.26/image |
Model Specifications
| Model Identifier | flux-2-klein-9b |
|---|---|
| Provider | Black Forest Labs |
| Category | image |
| Context Window | Varies |
| Output Pricing Tier | metered |
| API Protocol | OpenAI-compatible REST API (JSON) |
| Endpoint | https://api.luminoai.co.in/v1/chat/completions |
Why image cost is per output, not per token
Image models bill per generated image rather than per token, so cost scales with how many candidates you generate, not how long the prompt is. Generating four options to pick one is four times the cost of generating one. Decide how many candidates your workflow actually needs.
Good fit for image generation
- Product and marketing imagery generated on demand
- Concept exploration and rapid visual iteration
- Batch asset generation for catalogues and campaigns
- Workflows where a designer reviews and selects output
OpenAI-Compatible Integration
Drop into existing OpenAI SDK code by changing the base URL to https://api.luminoai.co.in/v1. The request shape below is the image generation pattern.
curl https://api.luminoai.co.in/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LUMINO_API_KEY" \
-d '{
"model": "flux-2-klein-9b",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "A studio product shot on a neutral background."}
]
}'Flux 2 Klein 9B API FAQ
How is Flux 2 Klein 9B priced?
Per generated image, not per token. See the pricing table above for the exact rate.
Can I control the output resolution?
Resolution and aspect ratio are request parameters. Check the model catalog entry for the supported sizes before wiring it into a pipeline.
How do I keep image generation cheap?
Generate fewer candidates per prompt, and review before regenerating rather than regenerating in a loop.
Explore all models in catalog | API Documentation | Test Flux 2 Klein 9B in Playground