GPT-5.3 Codex Spark
gpt-5.3-codex-spark
GPT-5.3 Codex Spark is a text model from OpenAI. The snapshot records a release date of 2026-02-05. Context window: 128K tokens. Maximum output: 32K tokens. Input: text, images, PDF. Output: text. Capabilities recorded: reasoning, tool calls.
Directory snapshot 2026-10-26 · Chinese dossier: 完整中文页
Official list price
CNY / 1M TOKENSOfficial list price in the directory snapshot: ¥11.7 input and ¥93.59 output per 1M tokens, in CNY. Relay prices below are what individual sites listed; they can be lower or higher, and they are not official prices.
Relay coverage
19 SITES19 sites in our public directory listed this model ID in the 2026-10-26 snapshot. Listed relay price range: ¥0.0525–¥22.5 per 1M input tokens. A listing means the model appeared on the site's public model list; it is not proof that the site serves the genuine model.
| Site | Domain | Relay price / 1M | Verification |
|---|---|---|---|
| MuskAI | api.muskapi.cc | ¥0.0525–¥0.105 | enterprise |
| 幻灵AI | api.huanling.icu | ¥0.0875 | — |
| 找模型 | api.zhaomoxing.com | ¥0.1225 | enterprise |
| Portdan AI | portdan.com | ¥0.175 | — |
| 云渡 | yundu.lol | ¥0.2–¥0.3 | personal |
| Luccc | api.luccc.uk | ¥0.2 | — |
| 模方 | api.modelscube.com | ¥0.2275–¥0.245 | personal |
| Volt | voltapi.ai | ¥0.2625–¥0.6125 | personal |
| Sunskii | api.sunskii.com | ¥0.2625–¥0.4375 | — |
| 池中鱼 | poolai.chat | ¥0.2975 | personal |
| 天枢 | tian-shu.net | ¥0.315–¥0.525 | personal |
| sidrune | sidrune.ai | ¥0.35–¥0.875 | personal |
| 溯光 | suguangapi.cc | ¥0.35–¥0.7 | personal |
| luchikey | sub2api.luchikey.com | ¥0.35–¥0.385 | enterprise |
| Token Nexus | api.aisz.mom | ¥0.35–¥0.6125 | — |
| 像素群岛 | api.shiyutv.cn | ¥0.875 | — |
| Cooper-API | cooper-api.com | ¥1.225–¥7.35 | — |
| 元初AI | ai.yuanc.icu | ¥1.75 | enterprise |
| Super API | superapi.buzz | ¥18–¥22.5 | — |
How to verify this model on a relay
THREE STEPS- Send a short request to the relay and read the
modelfield in the response. It must match the ID you sent; a different ID is a mapping, not necessarily a substitution. - Run the same prompt against a known-good endpoint and compare prompt-token counts. A large, repeatable gap points at a different tokenizer or a different backend.
- Run the seven checks. Billing, context retention, error shape, parameter compliance, tools, and streaming each produce evidence you can quote.
Same publisher
OpenAIQuestions
FAQWhat is the context window of GPT-5.3 Codex Spark?
The snapshot records 128,000 tokens.
How much does GPT-5.3 Codex Spark cost?
Official list price: ¥11.7 input / ¥93.59 output per 1M tokens in CNY, per the directory snapshot. 19 relay sites listed it at ¥0.0525–¥22.5 per 1M input tokens.
Is a relay really serving GPT-5.3 Codex Spark?
A model ID in a response is not proof. The seven-check detection compares tokenizer ratios, billing, error shape, parameter compliance, tools, and streaming against the advertised family. Run it on a key you can afford to spend, and treat one run as a spot check, not 24/7 monitoring.
Specifications and prices come from the 2026-10-26 public directory snapshot. We do not publish IQ scores or structured-output claims for models where we have no reliable data.