Answer: Fast mode supports GPT-6.2 Astra and GPT-6.2 Sol, and can also be used with GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, GPT-6 Sol, and GPT-6 Luna. Status: Confirmed Entry: tool/codex/models/fast-mode-supported-models Revision: 2 Digest: sha256:7c932dd3ea0f6a50 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:47:11Z Last changed: 2026-11-18T13:28:57Z (Speed multiplier: — → 1.5 times) Last verified: 2026-11-20T13:34:49Z Next check: 2026-11-21T13:34:49Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Primary supported models | GPT-6.2 Astra and GPT-6.2 Sol | [1] | 2026-11-20 Additional supported models | GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, GPT-6 Sol, and GPT-6 Luna | [1] | 2026-11-20 Speed multiplier | 1.5 times | [1] | 2026-11-20 Sources: [1] OpenAI. "Speed". https://learn.chatgpt.com/docs/agent-configuration/speed.md Role: primary. Accessed: 2026-11-20T13:34:49Z Quote: "Fast mode supports GPT-6.2 Astra and GPT-6.2 Sol." (Supports: Primary supported models) Quote: "You can also use it with GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, GPT-6 Sol, and GPT-6 Luna." (Supports: Additional supported models) Quote: "On GPT-6.2 Astra and GPT-5.6, Fast generates tokens at about 1.5 times the speed of Standard." (Supports: Speed multiplier) Snapshot SHA-256: ea46b8409f45d012b23bf385f7f515e4c99785ccb852ce4b000dd26eb3d623ce (captured 2026-11-18T13:28:56Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-18T13:28:57Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T13:34:49Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:34:49Z Last attempt: 2026-11-20T13:34:49Z Notes and limitations: Extracted automatically from a single official source (section "Fast mode"). Related: https://latestn.com/tool/codex/models/gateway-recognized-model-names What model names does Codex recognize when routing through a gateway? https://latestn.com/tool/codex/models/max-vs-ultra-mode What is Ultra mode in Codex and when should I use Max or Ultra? https://latestn.com/tool/codex/models/recommended-models Which models are recommended for Codex and ChatGPT Work, and what is each model best at? https://latestn.com/tool/codex/models/choose-model-reasoning-effort How do I choose a model and reasoning effort for a Codex Security bulk scan? https://latestn.com/tool/codex/models/custom-model-providers How do I set up a custom model provider like Amazon Bedrock or Google Cloud Vertex AI in Codex? https://latestn.com/tool/codex/models/daybreak-model-ci How do I use an approved Daybreak model with Codex Security in CI? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-18T13:28:57Z | changed | Speed multiplier: — → 1.5 times | [1] 2026-11-18T13:28:57Z | changed | Additional supported models: — → GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, GPT-6 Sol, and GPT-6 Luna | [1] 2026-11-18T13:28:57Z | changed | Primary supported models: — → GPT-6.2 Astra and GPT-6.2 Sol | [1] 2026-11-18T13:28:57Z | changed | Credits and pay-as-you-go rate: 2x → — | [1] 2026-11-18T13:28:57Z | changed | Subscription limit rate: 2.5x → — | [1] 2026-11-18T13:28:57Z | changed | Speed increase for GPT-5.6: 1.5x → — | [1] 2026-11-18T13:28:57Z | changed | Supported models: GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, GPT-6 Sol, and GPT-6 Luna → — | [1] 2026-11-13T03:47:11Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/codex/models/fast-mode-supported-models/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/codex/models/fast-mode-supported-models POST: https://latestn.com/dispute/tool/codex/models/fast-mode-supported-models with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/codex/models/fast-mode-supported-models?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). Which models support Fast mode in Codex? Revision 2, last verified 2026-11-20T13:34:49Z. https://latestn.com/tool/codex/models/fast-mode-supported-models (accessed 2026-11-21T09:54:19Z). @misc{LatestN_tool_codex_models_fast_mode_supported_models_r2, title = {Which models support Fast mode in Codex?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/codex/models/fast-mode-supported-models}}, note = {Revision 2; digest sha256:7c932dd3ea0f6a50; last verified 2026-11-20T13:34:49Z; accessed 2026-11-21T09:54:19Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/codex/models/fast-mode-supported-models