FLUX 1 Schnell
flux-1-schnell-fp8Pricing
List prices at Fireworks AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.00035 | $0.00035 |
What it costs a month
At Fireworks AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$0.13
- RAG over documents2,000 requests a day, 8K in / 0.6K out$0.18
- Coding agent1,000 requests a day, 40K in / 2K out$0.44
- Overnight batch20,000 requests a day, 4K in / 0.4K out$0.92
Where to run it
3 hosts serve FLUX 1 Schnell. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Fireworks AIInference flux-1-schnell-fp8 | $0.00035 / $0.00035 | flux-1-schnell-fp8 | |
NscaleInference FLUX.1-schnell | - | FLUX.1-schnell | |
falInference schnell | - | schnell |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Fireworks AI | |||||||
| Alias flux-1-schnell | $0.10 / $0.10 +28471% vs headline | flux-1-schnell | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Images
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Fireworks AI.
Smaller Black Forest Labs models
No cheaper Black Forest Labs model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
No cheaper open-weight match.
Call it
Using Fireworks AI's API.
from litellm import completion
response = completion(
model="fireworks_ai/flux-1-schnell-fp8",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does FLUX 1 Schnell cost?
On Fireworks AI, FLUX 1 Schnell costs $0.00035 per million input tokens and $0.00035 per million output tokens.
Which APIs offer FLUX 1 Schnell?
FLUX 1 Schnell runs on 3 APIs: Fireworks AI, Nscale and fal.
What is FLUX 1 Schnell's context window?
4K tokens, with up to 4K tokens in one reply.
Is FLUX 1 Schnell being retired?
No retirement date is scheduled for it on any API we track.
What is FLUX 1 Schnell's API model id?
Use flux-1-schnell-fp8 with Fireworks AI. Other hosts use their own ids: FLUX.1-schnell on Nscale, schnell on fal.
Sources
Raw catalog entry for flux-1-schnell-fp8 on Fireworks AI
{
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 3.5e-10,
"output_cost_per_token": 3.5e-10,
"litellm_provider": "fireworks_ai",
"mode": "image_generation"
}