The Short Version
Update (September 23, 2026): This article covers the April launch. GPT-5.5 and GPT-5.5 Pro are no longer in Teamday's model picker. Choose a current OpenAI model such as GPT-6 Astra, Sol, or Luna in the model guide. OpenAI says GPT-5.5 will retire from Codex with ChatGPT sign-in on October 14; that retirement does not apply to the API.
On April 23, 2026, OpenAI announced GPT-5.5 — codename Spud — and rolled it out to ChatGPT Plus, Pro, Business, and Enterprise users the same day. API access followed on April 24.
GPT-5.5 is the first OpenAI model that unifies text, image, audio, and video in a single architecture. No more stitching together GPT-5 + Whisper + Sora behind your agent. One model handles all modalities end-to-end.
At launch, GPT-5.5 was offered through Teamday's Codex harness.
Model Card
| Field | Value |
|---|---|
| Provider | OpenAI |
| Model ID | gpt-5.5 (and gpt-5.5-pro) |
| Codename | Spud |
| Released | April 23, 2026 (API: Apr 24) |
| Modalities | Text, image, audio, video — in and out |
| Context window | 400,000 tokens |
| Tool use | Native, parallel, computer use, browser |
| Harness in TeamDay | Codex |
| Best for | Multimodal missions, agentic computer use, knowledge work |
What OpenAI Claims
The launch positioned GPT-5.5 as a step toward an "AI super app." Concrete capability claims:
- Agentic coding — strongest gains over GPT-5 here
- Computer use — operates software, fills forms, moves across tools until a task is finished
- Knowledge work — researching online, analyzing data, creating documents and spreadsheets
- Early scientific research — reading papers, replicating analyses, drafting follow-ups
- Native multimodal — process and generate text, image, audio, and video in one call
The unified architecture is the part that changes how you build agents. With GPT-5, a "watch this video and summarize what was decided" task meant routing through a separate audio model. With GPT-5.5, it's one call.
How It Compares
| Model | Released | Strength | Context |
|---|---|---|---|
| GPT-5.5 | Apr 23, 2026 | Unified multimodal, computer use | 400K |
| GPT-5.5 Pro | Apr 23, 2026 | + extended reasoning | 400K |
| Claude Opus 4.7 | Apr 16, 2026 | Long-horizon coding, verification | 1M |
| Gemini 3.1 Pro | Feb 19, 2026 | ARC-AGI-2 reasoning | 2M |
Opus 4.7 still leads on long-horizon coding and the largest context. GPT-5.5 leads on mixed-modality work: any mission that touches video, audio, screenshots, or "use this software" steps.
Teamday Setup: Then and Now
How it's wired
The Codex harness runs Teamday's supported OpenAI models. The available choices change as models are released or retired; check the current picker or model guide.
1. Switch any agent to the Codex harness
Open the agent's settings, choose Codex, then select a model currently shown in the picker. GPT-5.5 and GPT-5.5 Pro are no longer offered there.
2. Mix harnesses on one mission
A common pattern now: a Claude Code agent owns the planning and code review; a Codex agent owns the execution and computer-use steps; a Gemini CLI agent handles the giant-context document review. Configure per-step harnesses in Mission Templates → Steps.
3. Historical video and audio example
The original launch example used GPT-5.5 to process a customer call and draft a follow-up. For a new mission, choose a model currently supported by Teamday and check its media input capabilities before assigning that work.
4. Bring your own OpenAI key
Connect an OpenAI API key in AI providers to use supported API models under your own OpenAI account and rate limits.
When Not to Reach for GPT-5.5
- Pure long-context coding — Opus 4.7's 1M context and verification behavior still win on multi-hour engineering missions.
- Cheapest-per-token batch work — Sonnet 4.6 and Gemini 3.1 Pro are both cheaper for high-volume content loops.
- Pure image or video generation — pair GPT-5.5 as the planner with gpt-image-2 or Seedance 2.0 as the executor.
TL;DR
GPT-5.5 was a notable April 2026 launch. For work in Teamday today, choose from the current OpenAI model options in the Codex harness.