PPromptoll
At-cost pricing

Token-based pricing, at our cost

Prices are our wholesale cost — just +5% to cover payment fees — below each provider's public rate card. Per 1M tokens. Pay with any credit card via Stripe.

Best value

🇨🇳 Chinese value models

Production-grade, 1/10 – 1/100 the cost of GPT-4o

ModelInput / 1MOutput / 1M
deepseek-v3.120% off · full

≈ gpt-4o quality at 1/10 the price

$0.22$0.88
deepseek-v4-flash20% off · full

DeepSeek ultra-cheap

$0.11$0.22
kimi-k2.5full model

Moonshot, long context

$0.60$2.99
kimi-k2.6full model

Kimi latest flagship

$0.95$3.99
sonarfull model

Perplexity real-time search

$0.25$0.25

🌎 Western frontier

Full access, no cross-border hassle

ModelInput / 1MOutput / 1M
gpt-5.5~10% off · full

OpenAI flagship

$4.46$26.78
gpt-4.1~10% off · full

OpenAI strong

$1.79$7.14
gpt-4o~10% off · full

OpenAI balanced

$2.23$8.93
claude-opus-4-7full model

Anthropic flagship

$4.99$74.81
claude-sonnet-4-6full model

Anthropic general

$2.99$14.96
claude-haiku-4-5-20251001full model

Anthropic budget

$1.00$4.99
gemini-2.5-profull model

Google flagship

$1.25$9.98
gemini-2.5-flashfull model

Google fast/cheap

$0.30$2.49
grok-4.3~10% off · full

xAI latest

$1.12$2.23

Every model is the provider's official full version (no distillation/quantization).20% / ~10% off= genuinely below list price,full model= official full model at our cost (≈ list price).

Image · Audio · Video

Billed at our cost price. Video is async (create → poll → download); polling and downloading are free.

🖼 Image

dall-e-3

1024² standard

$0.03570
dall-e-3-hd

1024² HD

$0.07140

🎙 Audio

whisper-1

speech-to-text

$0.00009 / sec
tts-1

text-to-speech

$0.01339 / 1k chars
tts-1-hd

HD TTS

$0.02678 / 1k chars

🎬 Video

sora-2

OpenAI 720p

$0.08925 / sec
veo-3.1-fast

Google fast

$0.14963 / sec
veo-3.1

Google flagship + audio

$0.39900 / sec
vidu2.0

Vidu value (estimated)

≈ $0.03544 / sec
viduq3-pro

Vidu Q3 flagship 1080p (estimated)

≈ $0.11340 / sec

Video is billed per generated second; seconds is 4 / 8 / 12. Rates marked "≈" (Vidu) are estimates, final billed cost. Full model list & examples in the docs.

No per-seat. No minimums. No markup.

Pay for forwarded traffic at our cost. Balance never expires.

Pay-as-you-go

No minimum

At-cost pricing

Top up any amount. Balance never expires. Full feature access.

Enterprise

Custom

Volume + SLA

Dedicated support, SSO, SLA guarantees.

FAQ

Are these the real, production Chinese models?+

Yes — DeepSeek v3.1, Qwen Plus, GLM 4.6, Kimi K2 are the same versions the labs deploy in their own consumer apps. No distillations, no fine-tunes.

How reliable is this?+

We run redundant contracts with multiple upstream providers. If a model goes down, requests failover transparently to an equivalent model (opt-in per tenant).

Do I need a Chinese entity, phone number, or visa?+

No. Sign up with any email. We handle provider-side compliance. Pay via Stripe in USD.

Can I still use GPT-4o / Claude / Gemini if I need them?+

Yes — same API. All models billed at our cost price (wholesale + 5%). Use the `model` parameter to pick, or set `model="auto"` and let our router choose the cheapest.

Data retention?+

Request bodies are forwarded, not persisted. Only anonymized metadata (token counts, model used, latency) is stored for billing and analytics.

How do I migrate from OpenAI?+

Change `base_url` in your OpenAI SDK to `https://promptoll.com/v1`. That's it. Your existing code keeps working. Switch `model` to a cheaper one when you're ready.