SU8 Codes

Enterprise model gateway
Up to 92.5% off

Stack monthly plans and pay-as-you-go pricing to fit your usage.

Pick a model12
View all 33 models
curl https://www.su8.codes/v1/chat/completions \
  -H "Authorization: Bearer $SU8_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-6.1-sol",
       "messages": [{"role": "user", "content": "Hello"}]}'
Pay as you go via Codex Per 1M input $2 $0.149 92.5% off
Works inside these tools
  • Codex
  • Claude Code
  • GitHub Copilot
  • Cursor
  • Windsurf
  • Gemini CLI
  • Codex VS Code
  • Claude Code VS Code

What you control after you connect

Pick your channel, check every call, keep the protocol your tool already speaks, and handle payment and invoices yourself.

Switch a key's channel, not your code

You choose each API key's channels and can change them in the console at any time, while the key and base URL stay the same.

How to switch channels

Every call is on record

Time to first token, latency, output speed, token breakdown, and cost are listed for every call from the last 30 days.

Four protocols, one key

Chat Completions, Messages, Responses, and Gemini endpoints all work, and when your tool and the channel use different protocols we convert between them so streaming and tool calls keep working.

Pay with Stripe, get invoices

Check out with Stripe, then generate a Stripe Invoice in the console or apply for a Chinese tax invoice.

Monthly plans and pay as you go,
use either or both

Daily users save with a plan; variable usage pays as it goes. Keep both, and balance takes over once the day's plan quota runs out.

Monthly plan

For steady daily usage
$42.47from / 30 days
  • A daily quota, with unused quota carried over
  • Quota and RPM stack across plans
  • Some models cost less on a plan, e.g. GPT-5.6 Sol: 92.5% off pay as you go via Codex, 97.8% off on Super Ultra via Codex
Choose a plan

Pay as you go

For trials, variable usage, or bursts
Up to 92.5% offBalance never expires
  • Every enabled model is available, priced from official rates
  • Per-request billing details in real time
Top up balance
Use bothEligible requests use the plan rate; once the day's plan quota is used, the next request switches to balance without interruption.

Plans

Prices cover one validity period; daily quota is measured at official prices. Unused quota carries over.

Pro

$42.47/ 30 days
About $1.42 / day
Daily quota$7
RPM
100
Models
24
OpenAI Moonshot Zhipu DeepSeek Excludes Anthropic
Buy Pro

Max

Recommended
$52.01/ 30 days
About $1.73 / day
Daily quota$10
RPM
150
Models
24
OpenAI Moonshot Zhipu DeepSeek Excludes Anthropic
Buy Max

Ultra

Recommended
$108.35/ 30 days
About $3.61 / day
Daily quota$25
RPM
200
Models
31
OpenAI Anthropic Moonshot Zhipu DeepSeek All providers
Buy Ultra

Super Ultra

Recommended
$212.02/ 30 days
About $7.07 / day
Daily quota$50
RPM
300
Models
31
OpenAI Anthropic Moonshot Zhipu DeepSeek All providers
Buy Super Ultra
More plans: SU500, SU750, SU1000. View all 7 plans

Popular models

Prices are official list prices. Landed discount is what you pay through the cheapest channel; shorter bars cost less.

ModelOfficial inputOfficial outputLanded discount
GPT-6.1 Sol
gpt-6.1-sol
$2/ 1M $10/ 1M
92.5% offCodex
GPT-5.6 Sol
gpt-5.6-sol
$4/ 1M $20/ 1M
92.5% offCodex
GPT-6-astra
gpt-6-astra
$10/ 1M $50/ 1M
92.5% offCodex
GPT-6-sol
gpt-6-sol
$2/ 1M $10/ 1M
92.5% offCodex
Claude Opus 5.5
claude-opus-5-5
$4/ 1M $20/ 1M
77.6% offClaude
GPT-5.6 Terra
gpt-5.6-terra
$2/ 1M $12/ 1M
92.5% offCodex

FAQ

What does landed discount mean?

It is how much less than the official price you pay. 92.5% off means you pay 7.5% of the official price. Channels differ; the model detail page lists each channel.

Not when the key allows using balance after the plan quota: the next request is charged to balance, and you only see an insufficient quota error when balance is also empty. Plan quota resets daily at 00:00 Beijing time.

Two things: set the Base URL to https://www.su8.codes/v1 and use a key created in the console. OpenAI SDK, Anthropic SDK, Codex, and Claude Code all work directly.

Edit the key under API keys in the console, pick another channel in the Channels step, and save. Within 15 seconds new requests use the new channel; the key and base URL stay the same. Landed discounts can differ by channel and plans cover only some channels, so compare on the model detail page before you switch.

Usage in the console lists time to first token, latency, output speed, token breakdown, and cost for every call, covering the last 30 days.

Yes. Daily quota and RPM add up across plans; buying the same plan again extends its validity.

Two kinds. A Stripe Invoice has no service fee: generate and download one for a paid plan or top-up order under Billing > Orders in the console, except plan orders bought with platform invoicing. For a Chinese tax invoice, choose platform invoicing when you buy a plan or apply later for existing orders; it carries a 5% service fee and a minimum invoice amount of ¥300.

Start pay as you go, upgrade to a plan as you grow

Balance never expires and works with every enabled model.