Pricing & Billing
Byesu aggregates mainstream models through official upstreams — no model downgrade — with pay-as-you-go, transparent multipliers. Text per token, images per image, Claude cache hits as low as 0.1x.
Live prices & status
The Model Marketplace (sign-in required) shows each model's input / output / cache price for your group; the console records your actual charge per request; current availability and latency per route are on the status page. This page is October 2026 static data for search & quick reference — the Model Marketplace is authoritative for live prices.
How billing works
| Type | Billing | Notes |
|---|---|---|
| Text / coding | Per token (input + output) | tokens × model multiplier × group multiplier; Claude cache hits as low as 0.1x |
| Image | Per image | charged per image generated; nothing generated, nothing charged |
| Video | Per second | not available right now (no video models are on sale) |
With an auto-group token, you are billed at the rate of whichever group the request actually lands on — see Choosing a Group.
💬 Text / coding models
All callable via one OpenAI-compatible interface (Claude also supports the native Anthropic protocol and Claude Code):
| Model | Best for | Billing |
|---|---|---|
gpt-6.1-sol · gpt-5.6 (Sol / Terra / Luna) | OpenAI, general / coding, works with Codex | pay-as-you-go · transparent |
claude-opus-5-5 · claude-opus-4-8 | Anthropic, strongest reasoning | pay-as-you-go · transparent · cache 0.1x |
claude-sonnet-5-5 · claude-sonnet-5 | General / coding, works with Claude Code | pay-as-you-go · transparent · cache 0.1x |
claude-haiku-4-5 | Fast & light | pay-as-you-go · transparent · cache 0.1x |
gemini-3.8-flash-high | Google, long text / multimodal | pay-as-you-go · transparent |
grok-4.7 · grok-4.5 | xAI coding / agent model | pay-as-you-go · transparent |
glm-5.3 · kimi-k3 | Zhipu GLM / Moonshot Kimi | pay-as-you-go · transparent |
The full list of models on sale is in the quick-reference table at the bottom of Models. Text prices vary by group; the Model Marketplace shows them after you sign in.
🖼 Image models (per image)
| Model | About | Price |
|---|---|---|
| gpt-image-2 | OpenAI image, multi-reference | about $0.009 / image |
| gpt-image-2.5 | OpenAI image (newer generation) | about $0.009 / image |
| gemini-3.0-pro-image-ultra | Google image model · Gemini 3 Pro Image (Nano Banana Pro) | about $0.009 / image |
| gemini-nano-banana-2.1-ultra | Google image model · Nano Banana 2.1 | about $0.008 / image |
| gemini-3.1-flash-image-ultra | Google image model · Gemini 3.1 Flash Image (Nano Banana 2) | about $0.007 / image |
Image tokens need the
media / media-gengroup — see Choosing a Group. The live price is shown in the Generation Playground once you pick a model.
🎬 Video models
Not available right now — no video models are on sale at the moment. This section will be updated when they return.
Why the pricing is worth it
- Official upstreams, no downgrade — official channels, not reverse-engineered or mirrored; model specs match the originals.
- Transparent pricing — the console shows actual billed price vs official list price, live; no fuzzy multipliers.
- Cache hits 0.1x — Claude cache hits as low as 0.1x; real savings for long-context heavy usage.
- Public status — availability and latency of every route are public on the status page, measured from real requests.
- One interface, all models — text and image on one account and one API surface.
- Local payment — Alipay / USDT, invoices available.
FAQ
How does Byesu API billing work?
Text is billed per token (input + output × model & group multiplier); images per image. All prices show the actual billed price in the console, compared against the official list price.
How much do cache hits save?
For Claude models, cache hits are billed as low as 0.1x, matching official cache pricing. For repeated long-context reads, this significantly lowers real cost.
Am I charged if image generation fails?
No. Images are billed per image generated, so a failed generation is not charged.
How do I set up a token for image models?
Image models are only available under the media / media-gen group; create a token in that group. Text models work with the default auto group.
Where do I see the actual price?
After signing in, the Model Marketplace shows each model's actual billed price; the console records your actual charge per request. This page is October 2026 static data; the Marketplace is authoritative for live prices.
Compare & wholesale
- 🛒 Wholesale media API — posted per-unit image pricing, pay-as-you-go.
- 🖼 Image API pricing compared — the image models on sale here, side by side with official vendor list prices.
- ⚖️ byesu vs OpenRouter — AI API gateway comparison.
- 🧠 Claude Opus 4.8 vs GPT-5.6 · GPT-5.6 vs Grok 4.5
Get started: Quick Start (3 steps) · Models · Image generation · Status · Sign up