fal.ai

Functions 4.6/10

Custom deployments on a GPU fleet from $1.89/hr for H100 (16 vCPU, 200GB RAM, 1TB SSD); Serverless model APIs billed per output (~$0.025/image, $0.05-$0.40/video-sec) or per-second

fal.ai scores 4.6/10 for free value in Functions. The main constraint: Paid — From $1.89/hr for H100 (Compute); per-output for Serverless. Custom deployments on a GPU fleet from $1.89/hr for H100 (16 vCPU, 200GB RAM, 1TB SSD); Serverless model APIs billed per output (~$0.025/image, $0.05-$0.40/video-sec) or per-second fallback.

Category Functions Kind Paid plan

Free value score

4.6 / 10

Show the math

Overall 4.6/10

value = 4.6/100

weighted_components_v1

Invocation value 1/10

value = 0.01 ×

fixed_log_v1

Runtime fit 8.2/10

value = 8.2/100

policy_score_v1

Deploy friction 8/10

value = 8/100

policy_score_v1

Key metrics

H100 $1.89/hr

per-output

What you get

Paid — From $1.89/hr for H100 (Compute); per-output for Serverless. Custom deployments on a GPU fleet from $1.89/hr for H100 (16 vCPU, 200GB RAM, 1TB SSD); Serverless model APIs billed per output (~$0.025/image, $0.05-$0.40/video-sec) or per-second fallback.

H100 from $1.89/hr is among the cheapest H100 rates on a managed inference platform; per-output pricing gives exact cost-per-result for media gen.

Gotchas

No gotchas documented yet. Contribute one if you know a constraint we missed.

Sources

"Deploy your own app on our competitively priced GPU fleet, as low as $1.89/hr for H100"
https://fal.ai/pricing
"H100s, H200s, B200s starting at $1.89. Pay only for what you use. Choose per-output pricing for Serverless, or hourly GPU pricing with Compute."
https://fal.ai/

paid value serverless-functions

Open service ← All Functions

Alternatives

Same category · similar quota

BasetenBaseten · paid · Paid plan

4.6

Per-minute, idle-excluded billing on dedicated replicas; A100 80GB ~$4/hr, H100 MIG ~$0.0625/min, H100 80GB ~$6.50/hr (also $9.984/hr SXM tier). Autoscaling model deployments.

A100 ~$4/hr

Checked 26d ago

Paid only

CerebriumCerebrium · paid · Paid plan

4.6

Pay-per-second GPU/CPU: T4 $0.000164/s, L4 $0.000222/s, A10 $0.000306/s, A100 80GB $0.000583/s (~$2.10/hr), H100 $0.000944/s (~$3.40/hr), B200 $0.00167/s; CPU $0.00000655/vCPU/s.

A100 $.58k/sT4 $164u/s

Checked 26d ago

Paid only

Cloudflare Containers GPU note / R2Cloudflare Containers GPU note / R2 · paid · Paid plan

4.6

$5/mo unlocks Workers + Containers + Durable Objects + R2 ($0.015/GB-month standard, Class A $4.50/M, Class B $0.36/M) with no egress fees.

$0 egress$5/moR2 $.015/GB

Checked 26d ago

Low/no egressEmbeddingsPaid only