Wholesale prices on frontier AI media — one key, pay-as-you-go
Image and video generation at posted, per-unit prices — gpt-image-2 from $0.01 / image, Veo 3.1 from $0.01875 / sec. Plus every top text and coding model on the same OpenAI-compatible key. No subscription, no minimums, cancel any time.
Get your API key → · See all prices · Live prices, latency & status
Works with your stack
One base URL, one key, OpenAI-compatible — swap models with a string, no re-platforming:
Text & coding: GPT-5.6 (Sol / Terra / Luna) · Claude Opus 4.8 · Claude Sonnet 5 · Gemini 3.1 Pro · Grok 4.5 · GPT-5.5 Image: gpt-image-2 · nano-banana-2 · seedream-4.5 · flux-kontext-max · firefly-image-5 · imagine-1.5 Video: Veo 3.1 (gemini-veo31) · runway-gen4-turbo · firefly-video · grok-video
Claude also supports the native Anthropic protocol and Claude Code; everything else is one OpenAI-compatible endpoint: https://byesu.com/v1.
Aisle 01 — Media (posted per-unit prices)
Media is billed per image or per second — real numbers, on the shelf. Failed image/video tasks are auto-refunded.
| Model | What it is | Price |
|---|---|---|
| gpt-image-2 | OpenAI image, text→image & edits | $0.01 / image |
| nano-banana-2 | Google Gemini image, up to 4K | $0.025 / image |
| flux-kontext-max | Flux, instruction edits (background swap) | $0.025 / image |
| seedream-4.5 | ByteDance, 2K/4K, Chinese text renders cleanly | $0.05 / image |
| Veo 3.1 (gemini-veo31) | Google text→video, Sora alternative | $0.01875 / sec |
| runway-gen4-turbo | Runway Gen-4 Turbo (needs first frame) | $0.025 / sec |
The video hook, spelled out: Google lists Veo 3.1 at about $0.40 / sec. On byesu it is $0.01875 / sec — so an 8-second clip is about $0.15, versus roughly $3.20 at Google's list rate. Same official model, billed per second, no subscription tier gate.
gpt-image-2 is a flat $0.01 / image; calling OpenAI directly the same model is token-billed (~$0.006–$0.21 per 1024×1024 image by quality), so per-image billing removes the math — one image, one fixed price. Full side-by-side with sources on the Image & Video API Pricing page.
Start generating → · Image API docs · Video API docs
Aisle 02 — Text & coding (pay-as-you-go, transparent)
Text and coding models are pay-as-you-go with transparent multipliers on the official upstream — no model downgrade:
- Per token, input 1× / output 5×, and cache hits as low as 0.1× — for long system prompts and long documents that read the same context repeatedly, cache hits meaningfully cut real cost.
- You pay a fraction of each provider's official list price; the console shows the actual billed price per request next to the official list price, live.
- One account covers text, image and video from a shared balance — image/video calls use a token created in the media / media-gen group, no separate account needed.
Text prices vary by group and are shown live (input / output / cache) on the Model Marketplace when you sign in. See Pricing & Billing for how the multipliers work.
How it works
- Connect your key — drop one base URL (
https://byesu.com/v1) + token into the SDK or client you already use. - Access every model — one endpoint fans out to text, image and video models; switch with a string.
- Pay as you go — text per token, image per image, video per second. No seats, no minimums, no monthly lock-in.
- See the real price — the console records your actual charge per request, compared live against the official list price.
Quick Start (3 steps) · Choosing a group · Media API
Why byesu vs OpenRouter and the proxies
- Text and media on one account — most gateways route text only; byesu covers Claude/GPT/Gemini/Grok plus image and video from the same shared balance (media models use a media-group token).
- Official upstream, no downgrade — official channels, not reverse-engineered or mirrored; model specs match the originals.
- Real media prices, posted — image from $0.01, video from $0.01875/sec, with auto-refund on failure — where most aggregators are thin.
- Cache hits as low as 0.1× — genuine savings for long-context, heavy usage.
- Six languages, local payment — docs in six languages; Alipay / USDT, invoices available.
See the full breakdown: byesu vs OpenRouter · Image & Video API pricing · Sora API alternative · Claude Opus 4.8 vs GPT-5.6 · GPT-5.6 vs Grok 4.5
FAQ
How much does the gpt-image-2 API cost on byesu?
A flat $0.01 per image, pay-as-you-go, no subscription or minimums. Calling OpenAI directly the model is token-billed (~$0.006–$0.21 per 1024×1024 image by quality).
What does the Veo 3.1 video API cost per second?
$0.01875 per second (gemini-veo31). Google lists Veo 3.1 at about $0.40/sec, so an 8-second clip is about $0.15 on byesu versus roughly $3.20 at Google list rate. Failed tasks are auto-refunded.
How is text and coding pricing handled?
Pay-as-you-go with transparent multipliers (input 1×, output 5×, cache hits as low as 0.1×) on the official upstream models with no quality downgrade. You pay a fraction of each provider's list price; the console shows the actual billed price per request.
Do I need a subscription or minimum commitment?
No. No subscriptions, contracts or minimums — top up a balance and pay per request (text per token, image per image, video per second).
How do I set up a token for image and video models?
Image and video models are only available under the media / media-gen group. Create a token in that group, otherwise you get a no available channel error. See Choosing a group.
Get started: Get your API key · Quick Start · Pricing & Billing · Image / Video
Media prices are per-unit and shown as of July 2026; the Model Marketplace is authoritative for live prices. Official list prices cited (OpenAI, Google) are for context and belong to their respective providers.