GPT‑5.3‑Codex‑Spark
GPT-5.3-Codex-Spark is a new model optimized for real-time coding, capable of processing over 1000 tokens per second on ultra-low latency hardware. This model is a smaller version of GPT-5.3-Codex and represents the first milestone in a partnership with Cerebras.
openai.com
5 min
2/12/2026
GPT-5.3-Codex being routed to GPT-5.2
GPT-5.3-Codex is being routed to GPT-5.2 in Codex CLI version 0.99.0-alpha.10. The user is subscribed to ChatGPT Pro and is operating on a Darwin 25.2.0 arm64 arm platform using the Ghostt terminal emulator.
github.com
1 min
2/11/2026
GPT‑5.3‑Codex‑Spark
GPT-5.3-Codex-Spark is a new model optimized for real-time coding, capable of processing over 1000 tokens per second on ultra-low latency hardware. This model is a smaller version of GPT-5.3-Codex and represents the first milestone in a partnership with Cerebras.
openai.com
5 min
2/12/2026
GPT-5.3-Codex being routed to GPT-5.2
GPT-5.3-Codex is being routed to GPT-5.2 in Codex CLI version 0.99.0-alpha.10. The user is subscribed to ChatGPT Pro and is operating on a Darwin 25.2.0 arm64 arm platform using the Ghostt terminal emulator.
github.com
1 min
2/11/2026
GPT‑5.3‑Codex‑Spark
GPT-5.3-Codex-Spark is a new model optimized for real-time coding, capable of processing over 1000 tokens per second on ultra-low latency hardware. This model is a smaller version of GPT-5.3-Codex and represents the first milestone in a partnership with Cerebras.
openai.com
5 min
2/12/2026
GPT-5.3-Codex being routed to GPT-5.2
GPT-5.3-Codex is being routed to GPT-5.2 in Codex CLI version 0.99.0-alpha.10. The user is subscribed to ChatGPT Pro and is operating on a Darwin 25.2.0 arm64 arm platform using the Ghostt terminal emulator.
github.com
1 min
2/11/2026
No more articles to load