Black Forest Labs: FLUX.1 [dev]
flux-1-dev- Price
- From $0.025
- Context
- 4K
- Max output
- 4K
- Modalities
- Image
About FLUX.1 [dev]
FLUX.1 [dev] is Black Forest Labs' open-weight text-to-image model, a 12 billion parameter rectified flow transformer trained with guidance distillation. Black Forest Labs describes its output quality as second only to FLUX.1 [pro], with prompt following comparable to closed models. It generates from text only and ships under a non-commercial licence for the weights.
Where it works well
- It is a 12 billion parameter rectified flow transformer, so the same architecture behind the FLUX.1 [pro] line is available as open weights.
- Guidance distillation makes generation cheaper to run than a standard diffusion model of similar quality.
- Black Forest Labs says its prompt following matches closed-source competitors, which suits detailed multi-element prompts.
When to choose another model
- It only turns text into images; there is no reference-image input, so editing an existing picture needs a Kontext or FLUX.2 model.
- The released weights carry a non-commercial licence, so check Black Forest Labs' terms before building a commercial product on self-hosted copies.
- Black Forest Labs ranks it below FLUX.1 [pro], so final-quality hero images may justify a pro-tier model.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Text to imageTokenLab endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "operation": "text-to-image", "model": "flux-1-dev", "prompt": "A minimalist product photo of matte black headphones on a soft blue background." }'
Parameters
Text to image
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
async | Not provided | Not provided | Not provided |
operation | Not provided | Not provided | Not provided |
prompt | Not provided | Not provided | Not provided |
resolution | Not provided | Not provided | Model-specific resolution values and the default are not yet verified for this public operation. |
Task-capable image contract; `async: true` is accepted when the public status mode is `inline_or_task`.
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Text to image
per image- Official price
- $0.025
- Verified price
- —
- Discount
- —
| Official priceper image | Verified priceper image | Discount | |
|---|---|---|---|
| Text to image | $0.025 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open FLUX.1 [dev] in Console with a prompt ready to edit or send.
Help me create an image with flux-1-dev using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.
Use cases
Best for- Text to Image
Concept art and moodboards
Generate many text-driven variations of a scene, character, or environment to explore a visual direction before committing to a final render.
Open-model benchmarking
Use it as a known open-weight baseline when comparing how newer image models handle composition, text, and anatomy on your own prompts.
Blog and editorial illustration
Produce a quick header illustration from a one-line description when no reference photo exists.
Prompt examples
A watercolor map of a fictional harbor town at dawn, boats at anchor, hand-lettered labels in the margins.
Studio photograph of a ceramic teapot on a walnut table, soft window light from the left, shallow depth of field.
Isometric cutaway of a small bakery, three floors, warm lighting, flat illustration style.
FAQ
What is FLUX.1 [dev]?
It is Black Forest Labs' open-weight text-to-image model with 12 billion parameters, built as a rectified flow transformer and trained with guidance distillation. It sits just below FLUX.1 [pro] in the maker's own quality ranking and is meant for research, personal and creative use.
Can FLUX.1 [dev] edit an existing image?
No. This model takes a text prompt and returns a new image. For editing with a reference picture, use FLUX.1 Kontext or one of the FLUX.2 models, which accept input images alongside the instruction.
Is FLUX.1 [dev] allowed for commercial use?
The open weights are released under the FLUX.1 [dev] Non-Commercial License, which permits personal and scientific use. Using generated images through a hosted API is a separate matter governed by the provider's terms, so read both before shipping a commercial product.
How does FLUX.1 [dev] differ from FLUX.1 [pro]?
FLUX.1 [dev] is the open-weight, guidance-distilled model; FLUX.1 [pro] is the maker's top-tier closed model. Black Forest Labs says [dev] is second only to [pro] in output quality, so [pro] and later versions are the choice when you need the best fidelity.
How much does FLUX.1 [dev] cost?
On TokenLab, FLUX.1 [dev] costs $0.025 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should FLUX.1 [dev] use?
Use https://api.tokenlab.sh/v1/images/generations for FLUX.1 [dev]. The request example below shows the matching code shape.
Which operations does FLUX.1 [dev] support?
FLUX.1 [dev] supports Text to image. Select an operation above to see its endpoint and request example.
Compare FLUX.1 [dev]
Guides that use FLUX.1 [dev]
Sources
Reviewed Oct 2, 2026
More from Black Forest Labs