fal API Models — Pricing & Benchmarks
39 models available · fal
Last refreshed 2026-10-23. Next refresh: weekly.
fal API hosts 39 AI models in this catalog. The lowest listed input price is HeyGen Voice Turbo at $4.00/1M input tokens. LLM Reference compares these models across all 124 providers.
| Model | Input (per 1M) | Output (per 1M) | Context | |
|---|---|---|---|---|
| HeyGen Voice Turbo | $4.00 | — | — | |
| HeyGen Voice | $30.00 | — | — | |
| Eleven Flash v2.5 | — | — | — | |
| FIBO 2.0 | — | — | — | |
| FIBO 2.0 Edit | — | — | — | |
| FLUX 3 Max | — | — | — | |
| FLUX.1 [dev] | — | — | — | |
| FLUX.1 [schnell] | — | — | — | |
| FLUX.1 Kontext [pro] | — | — | — | |
| FLUX.1.1 [pro] | — | — | — | |
| FLUX.1.1 [pro] Ultra | — | — | — | |
| FLUX.2 | — | — | — | |
| GPT Image 1.5 | — | — | — | |
| GPT Image 2 | — | — | — | |
| Grok Imagine Image | — | — | — | |
| Grok Imagine Image Quality | — | — | — | |
| Grok Imagine Video | — | — | — | |
| Grok Imagine Video 1.5 Preview | — | — | — | |
| HeyGen Video | — | — | — | |
| Ideogram 4.0 | — | — | — | |
| Ideogram Vector 1.0 | — | — | — | |
| Kling | — | — | — | |
| Kling 4.0 | — | — | — | |
| Krea 3 | — | — | — | |
| Krea 3 Ultra | — | — | — | |
| LingBot-World-V2-14B-Causal-Fast | — | — | — | |
| Mirelo SFX 2.0 | — | — | — | |
| MOSS-Image SFT | — | — | — | |
| OmniHuman 2.0 | — | — | — | |
| Qwen Image | — | — | — | |
| Recraft V4 | — | — | — | |
| Seedream 4.5 | — | — | — | |
| Seedream 5.0 Flash | — | — | — | |
| Seedream 5.0 Lite | — | — | — | |
| Seedream 5.0 Pro | — | — | — | |
| Veo 3.1 | — | — | — | |
| Veo 3.1 Fast | — | — | — | |
| Veo 3.1 Lite | — | — | — | |
| Z-Image | — | — | — |
Where else to run this
Ideogram Vector 1.0 on fal API
Provider setup and pricing
HeyGen Voice Turbo on fal API
Provider setup and pricing
MOSS-Image SFT on fal API
Provider setup and pricing
Ideogram Vector 1.0 on Ideogram API
Alternative host
HeyGen Voice Turbo on OpenRouter
Alternative host
MOSS-Image SFT on MOSI API Platform
Alternative host
Pricing Overview
Cheapest$4.00/1M
Most expensive$30.00/1M
About fal API
fal serves asynchronous and real-time model APIs on its infrastructure with queue handling, automatic scaling, SDK and HTTP access, and model-specific output-based billing. Its public catalog includes first-party and partner-hosted endpoints across image, video, audio, vision, and 3D generation; model cards expose the applicable schema, pricing, and license information.
Full provider profile →