SU8 Codes
All models
OpenAI

GPT-6-astra API

GPT-6-astra

gpt-6-astra
Lowest landed discount
98% off

Inside the SU500 plan on the Codex channel, the landed discount is 98% off.

Official input
$10 / 1M
Official output
$50 / 1M
Cache read
$1 / 1M
Cache write
$12.5 / 1M

About GPT-6-astra

GPT-6-astra

Tool calling
Supported, parallel
Web search
Supported
Prompt caching
Supported
Reasoning effort
none / low / medium / high / xhigh / max

Pay-as-you-go discounts by channel

The same model can run through different channels at different landed discounts. Shorter bars cost less.

ChannelFinal discountQuota multiplierBilling unit
Codex Lowest
92.5% off
0.5× USD / 1M
Codex-Pro
91% off
0.6× USD / 1M
Codex-Max
89.5% off
0.7× USD / 1M
Azure
5% off
6.384× USD / 1M

Cache hits are billed at the cache read price. Cache writes use the cache write price, and the Console usage detail shows the final cost breakdown.

Plans that include this model

On a plan, calls are deducted from the daily quota at the plan channel's discount.

PackageFinal discountChannelQuota multiplierBilling unit
SU500
98% off
Codex 0.15× USD / 1M
SU750
98% off
Codex 0.15× USD / 1M
SU1000
98% off
Codex 0.15× USD / 1M
Super Ultra
97.8% off
Codex 0.15× USD / 1M
Ultra
97.8% off
Codex 0.15× USD / 1M
Max
97.3% off
Codex 0.15× USD / 1M
Pro
96.9% off
Codex 0.15× USD / 1M
SU500
96% off
Codex-Pro 0.3× USD / 1M
SU750
96% off
Codex-Pro 0.3× USD / 1M
SU1000
96% off
Codex-Pro 0.3× USD / 1M
Super Ultra
95.7% off
Codex-Pro 0.3× USD / 1M
Ultra
95.6% off
Codex-Pro 0.3× USD / 1M
Max
94.7% off
Codex-Pro 0.3× USD / 1M
SU500
94.6% off
Codex-Max 0.4× USD / 1M
SU750
94.6% off
Codex-Max 0.4× USD / 1M
SU1000
94.6% off
Codex-Max 0.4× USD / 1M
Super Ultra
94.3% off
Codex-Max 0.4× USD / 1M
Ultra
94.2% off
Codex-Max 0.4× USD / 1M
Pro
93.9% off
Codex-Pro 0.3× USD / 1M
Max
93% off
Codex-Max 0.4× USD / 1M
Pro
91.9% off
Codex-Max 0.4× USD / 1M
SU500
8.8% off
Azure 6.84× USD / 1M
SU750
8.8% off
Azure 6.84× USD / 1M
SU1000
8.8% off
Azure 6.84× USD / 1M

Example call

curl https://www.su8.codes/v1/chat/completions \
  -H "Authorization: Bearer $SU8_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-6-astra",
       "messages": [{"role": "user", "content": "Hello"}]}'

Frequently asked questions

How much does the GPT-6-astra API cost?

OpenAI list price: Input $10/1M, Output $50/1M, Cache read $1/1M. On SU8 Codes, each channel has its own landed discount; the current pay-as-you-go and package discounts are in the channel and package tables on this page, refreshed live.

Which channels serve GPT-6-astra, and how do they differ?

4 channels serve this model: Codex-Max, Codex-Pro, Azure, Codex. Each channel has its own landed discount, shown in the table above. You can pick or change the channel for any API key in the console; the key and base URL stay the same.

How do I call GPT-6-astra?

Create an API key in the SU8 Codes console, point your client at this site's base URL, and use the model ID gpt-6-astra. The example call above has copy-ready cURL and Python code.

Can I use GPT-6-astra with Codex CLI?

Yes. In ~/.codex/config.toml, set the base URL to this site, add your SU8 API key, and set the model to gpt-6-astra. The Codex CLI tab in the example call above has the full config, and the integration docs walk through each step.

Integration guides

More from OpenAI

ModelOfficial inputOfficial outputLanded discount
GPT-5.6 Sol
gpt-5.6-sol
$4/ 1M $20/ 1M
92.5% offCodex
GPT-5.6 Terra
gpt-5.6-terra
$2/ 1M $12/ 1M
92.5% offCodex
GPT-5.6 Luna
gpt-5.6-luna
$0.6/ 1M $3.6/ 1M
5% offAzure
GPT-5.5
gpt-5.5
$5/ 1M $30/ 1M
92.5% offCodex
GPT-5.4 Mini
gpt-5.4-mini
$0.75/ 1M $4.5/ 1M
5% offAzure
gpt-image-2.6-sunburst
gpt-image-2.6-sunburst
$0.15/ image Per image
92.5% offCodex