Compute Comparison

flux-dev

image-generationopen-weights
flux-dev PRICING (PER IMAGE)
Price per image$0.025
View Black Forest Labs
Context Window
4K
tokens
00
flux-dev Latency P50
4.0s
time to first token
About flux-dev

flux-dev is a advanced-tier language model from Black Forest Labs. flux-dev is an open-weights model, meaning the weights are publicly available for self-hosting, fine-tuning, and deployment on your own infrastructure — not just through Black Forest Labs's API. The FLUX family is Black Forest Labs's model series for this capability tier.

flux-dev is priced at $0.025 per image. This is a image model billed per image rather than per token — token input/output pricing does not apply.

Its 4K-token context window is standard for this tier — adequate for most chat and completion tasks, but may require chunking for long-document workloads. Median latency (P50 time-to-first-token) is approximately 4000ms — better suited to batch or async workloads where latency is less critical.

flux-dev is best suited to image-generation, open-weights. It is a text-only model without vision or function calling support. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how flux-dev compares to similar models across these dimensions.

flux-dev sits in the advanced tier — strong general-purpose models balancing capability and cost, suitable for most production applications. As an open-weights model, flux-dev can be self-hosted on GPU compute (see the GPU rental comparison on this site) to eliminate per-token API costs entirely — the break-even point versus API pricing depends on your volume and the GPU hourly rate. When comparing flux-dev to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (0/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.

flux-dev Intelligence Score
0/100
0

Composite quality score based on reasoning, coding, and instruction-following benchmarks.

flux-dev Pricing vs Advanced Tier
CheapestThis modelMost expensive
$0.070Free$30.00

Input price vs 184 advanced models tracked. Avg: $1.38/1M.

flux-dev Capabilities
Vision / Images✗
Function Calling✗
Streaming✗
Prompt Caching✗
Reasoning / CoT✗
Open Weights✓
Computer Use✗
Web Search✗
flux-dev Full Specifications
Model IDflux-dev
ProviderBlack Forest Labs
Model FamilyFLUX
TierAdvanced
Context Window4,096 tokens (4K)
Max Output Tokens—
Input Price$0 / 1M tokens
Output Price$0 / 1M tokens
Cached Input PriceNot available
Throughput—
Latency (P50)4.0s
Intelligence Score0/100
LiveBench Score—
Cost per Task (LiveBench)—
Data Confidence—
HLE Score—
GPQA Diamond—
SWE-bench Score—
OSWorld Score—
BrowseComp Score—
Terminal-Bench Score—
AutoBench Score—
Parameters—
Vision SupportNo
Function CallingNo
StreamingNo
Reasoning ModelNo
Open WeightsYes
Data SourceStatic (verified)
Last Updated2026-07-01

Similar Models by Intelligence Score

flux-dev Frequently Asked Questions