FlexAI · Pricing Plans
Flexai Plans
Flexai Plans is the pricing profile for FlexAI on the APIs.io network — every figure transcribed verbatim from the provider’s own pricing page on 2026-10-28.
It defines 12 plans, including Qwen3.6-35B-A3B (serverless) — $0.100; GPT-OSS 20B (serverless) — $0.020; BGE-M3 (embeddings) — $0.010, and 9 more.
The page prices API or platform usage directly, priced per call; the service is delivered as managed plus licensed.
Tagged areas include Company, Artificial Intelligence, Machine Learning, Inference, and LLM.
12 Plans
Prices the API
Basis: per call
Delivered: managed + licensed
Transcribed from the provider's pricing page on 2026-10-28 — flex.ai/pricing.
View Source
CompanyArtificial IntelligenceMachine LearningInferenceLLMOpenAI-CompatibleGPU ComputeEmbeddingsFine-TuningAgents
Compare with the market: Artificial Intelligence pricing
Plans
Qwen3.6-35B-A3B (serverless)
per-use
$0.100 per input $/M tokens
Overage: Output $0.950 /M; cached input $0.0150 /M; 256K context
GPT-OSS 20B (serverless)
per-use
$0.020 per input $/M tokens
Overage: Output $0.100 /M; cached input $0.0030 /M; 128K context
BGE-M3 (embeddings)
per-use
$0.010 per input $/M tokens
FLUX.1 [schnell] (image)
per-use
$0.0005 per per image
Whisper Large V3 Turbo
per-use
$0.0002 / min per per minute
Kokoro-82M (TTS)
per-use
$0.99 / M chars per per million characters
MiniMax-H3 (video)
per-use
$4.8 / min of video per per minute of video
Dedicated B200
per-use
$6.25 /hr per GPU-hour
Overage: Contact sales for Custom package rates.
Dedicated H200
per-use
$3.15 /hr per GPU-hour
Dedicated H100
per-use
$2.10 /hr per GPU-hour
Dedicated A100
per-use
$1.80 /hr per GPU-hour
Custom: AI Factory & Enterprise
none
Custom pricing on your workload. Talk to us.
Includes: VPC, on-prem, air-gapped. Dedicated CSM. Geo redundancy. 99.9%
Sources
Work with this as data
Every plan here is available over the APIs.io API and to AI agents over MCP.