Skip to content
ORYNX

GPT-5.5 Compact

ReasoningCompactionOpenAI

Context compaction for GPT-5.5 sessions in older Codex CLI versions.

Input
$1.25
per 1M tokens
Output
$7.50
per 1M tokens
Context window
1.05M
tokens
Max output
128K
tokens

Pricing

Prices are in USD per 1M tokens. Cached input is billed at the cache read price.

Input
$1.25/ 1M
Output
$7.50/ 1M
Cache read
$0.125/ 1M

Use it from code

Older Codex CLI versions call this model by themselves when they compact a long session. It is billed only through /v1/responses/compact, so don't set it as your main model.

OpenAI Responses
curl https://api.orynx.dev/v1/responses/compact \
  -H "Authorization: Bearer $ORYNX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": [{"role": "user", "content": "Explain what an API gateway does in one sentence."}]
  }'

More from GPT

GPT-6 AstraDynamic pricing
gpt-6-astra

OpenAI's flagship for demanding end-to-end work and deep reasoning.

Input
$3.00/ 1M
Output
$15.00/ 1M
OpenAI ResponsesOpenAI Chat1.05M ctx
GPT-5.6 SolDynamic pricing
gpt-5.6-sol

Flagship of the GPT-5.6 series for complex reasoning and coding.

Input
$1.20/ 1M
Output
$6.00/ 1M
OpenAI ResponsesOpenAI Chat1.05M ctx
GPT-5.6 TerraDynamic pricing
gpt-5.6-terra

Balanced GPT-5.6 model between Sol and Luna.

Input
$0.60/ 1M
Output
$3.60/ 1M
OpenAI ResponsesOpenAI Chat1.05M ctx