Back to modelsChat
ChatOpenAI

GPT-5.4 Codex AI Chat Assistant

GPT-5.4 Codex is Rivya's highest-end Codex option for repo-scale reasoning, difficult debugging, technical planning, and tool-using engineering work. Use it when the task spans multiple files, systems, or investigation steps.

Input
Prompt + optional images
Output
AI Chat Assistant
Credits
Pay per use — credits based on usage
Best for
Repo-scale debugging and architecture review
Example output

Example output

Best for prelaunch checks, blocker review, and release handoff.

Responses

Try this model onlineSee Chat overview

Online trial

Use GPT-5.4 Codex

Input setup

Prepare this run

Estimated credits: 4+

Chat controls

Choose when Rivya can search the web, how much reasoning it should use, and whether to include model thoughts when the selected model supports them.

Web search

Allow supported models to pull live web results during the reply.

Reasoning

Use the model default, or request a stronger or lighter reasoning level when available.

Start a conversation to turn planning, prompting, and creative direction into one reusable thread.

Prompt starters

Start GPT-5.4 Codex with a proven prompt

Use a template already mapped to GPT-5.4 Codex when you want a stronger first run than a blank prompt.

chat thread

Assess release risk after adding 20 Prompt templates and updating media example audits.

Scope: prompt coverage and media governance copy. Blockers: none if prompts check, media audit, typecheck, and build pass. Warnings: temporary media remains until final approved storage replacement. Required checks: prompts check, media example audit, content models audit, typecheck, build, and page sampling. Owner decision: confirm final media storage before launch.

Chat Prompt

Recommended model: GPT-5.4 Codex

Codex Release Risk Chat

Convert a release summary into a risk checklist with blockers, checks, owner decisions, and launch notes.

chat thread

Need to rename a prompt field across source, admin view models, and tests without touching generated files.

Target pattern: explicit field access in prompt source and view models. Exclusions: generated files and unrelated locale content. Review sampling: one template, one admin page, one public detail page. Formatting: run scoped formatter after codemod. Rollback: commit codemod separately from manual copy edits.

Chat Prompt

Recommended model: GPT-5.4 Codex

Codemod Safety Plan Chat

Plan a codemod with target pattern, exclusions, review sampling, formatting, and rollback strategy.

chat thread

Reusable examples now come from reviewed template records, while the older catalog rows remain read-only during migration.

Producer: reviewed template records. Consumer: example aggregation and public cards. Compatibility window: older catalog rows remain read-only inventory. Validation: coverage checks and page sampling. Cleanup step: remove the old path only after final storage and page sampling pass.

Chat Prompt

Recommended model: GPT-5.4 Codex

Data Contract Migration Chat

Plan a data contract migration with producer, consumer, compatibility window, validation, and cleanup step.

chat thread

Prompt detail pages return 404 for newly added slugs because static params did not include them in the build.

Impact: new prompt pages are unavailable after deploy. Suspected scope: static route generation or missing content records. Safe patch: confirm templates are included in the release and rebuild. Verification: request one new English and Chinese prompt URL. Communication: content was added but pages need a rebuild; no user data is affected.

Chat Prompt

Recommended model: GPT-5.4 Codex

Production Hotfix Brief

Turn a production issue into a hotfix brief with impact, suspected scope, safe patch, verification, and communication.

Model proof

What GPT-5.4 Codex output looks like

Use the online trial above, then compare these example results to judge finish, rhythm, and task fit before you spend more credits in Studio.

View more examples
chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Chat preview for Codex release risk in Rivya.

Output

Best for prelaunch checks, blocker review, and release handoff.

Lead sample

Best for prelaunch checks, blocker review, and release handoff.

Chat preview for Codex release risk in Rivya.

Input

Prompt + optional images

What to notice

Chat preview for Codex release risk in Rivya.

Credits per use

Pay per use — credits based on usage

Why this model works

Why this model works

Higher-tier Codex reasoning and coding collaboration

Keeps the Responses project

Good for complex code, tool use, and multi-step technical work

Best-fit tasks

Best-fit tasks

Repo-scale debugging and architecture reviewImplementation plans that span multiple tools or filesHigh-stakes code review and regression huntingTechnical specs from existing systems or codebases

Model proof

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for Codemod Safety Plan Chat.

Plan a codemod with target pattern, exclusions, review sampling, formatting, and rollback strategy.

Conversation preview for Codemod Safety Plan Chat.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for Data Contract Migration Chat.

Plan a data contract migration with producer, consumer, compatibility window, validation, and cleanup step.

Conversation preview for Data Contract Migration Chat.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for the Production Hotfix Brief prompt.

Turn a production issue into a hotfix brief with impact, suspected scope, safe patch, verification, and communication.

Conversation preview for the Production Hotfix Brief prompt.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for Test Fixture Cleanup Chat.

Clean up test fixtures by identifying what they prove, stale fields, shared helpers, and safe deletion order.

Conversation preview for Test Fixture Cleanup Chat.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for Technical Debt Priority Chat.

Rank technical debt items by user impact, failure risk, migration pressure, and verification cost.

Conversation preview for Technical Debt Priority Chat.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for Codemod Safety Plan Chat.

Plan a codemod with target pattern, exclusions, review sampling, formatting, and rollback strategy.

Conversation preview for Codemod Safety Plan Chat.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for Data Contract Migration Chat.

Plan a data contract migration with producer, consumer, compatibility window, validation, and cleanup step.

Conversation preview for Data Contract Migration Chat.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for the Production Hotfix Brief prompt.

Turn a production issue into a hotfix brief with impact, suspected scope, safe patch, verification, and communication.

Conversation preview for the Production Hotfix Brief prompt.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for Test Fixture Cleanup Chat.

Clean up test fixtures by identifying what they prove, stale fields, shared helpers, and safe deletion order.

Conversation preview for Test Fixture Cleanup Chat.

chat thread

Ask Rivya to handle more complex code generation, technical analysis, tool collaboration, or responses project tasks.

Conversation preview for Technical Debt Priority Chat.

Rank technical debt items by user impact, failure risk, migration pressure, and verification cost.

Conversation preview for Technical Debt Priority Chat.

Decision fit

When this model is the right choice

Decision fit

Fit signals

Higher-tier Codex reasoning and coding collaboration
Keeps the Responses project
Good for complex code, tool use, and multi-step technical work
Supports vision input with a larger output budget
A stronger follow-up option after GPT-5.3 Codex

Best-fit tasks

Use it when the task looks like this

Repo-scale debugging and architecture reviewImplementation plans that span multiple tools or filesHigh-stakes code review and regression huntingTechnical specs from existing systems or codebasesAgent-style engineering projects with longer reasoning chains

Quiet facts

Inputs, output, and credits to confirm

Provider

OpenAI

Category

Chat

Capabilities

Responses

Credit model

Pay per use — credits based on usage

Input path

Prompt + optional images

Prompt setup

Up to 20,000 chars

Developer access

Available via API

Call GPT-5.4 Codex from Public API v1 after checking the model fields, reference media rules, and credit behavior.

Open API referenceOpen debugger
FAQ

GPT-5.4 Codex FAQ

Compare alternatives

Other models to consider next

Chat

GPT-5.5

OpenAI's advanced GPT chat model on Rivya for complex reasoning, image-aware analysis, research synthesis, and structured writing when the brief needs more room.

Why consider it

Consider it when the credit note fits your next run: Pay per use - credits based on usage.

InputPrompt + optional images
CreditsPay per use - credits based on usage
Best forResearch synthesis across long or messy source packets
See details
Chat

GPT-5.4

OpenAI's higher-end AI chat model on Rivya, with stronger structured input handling, reasoning control, and tool-oriented conversation projects for more complex analysis and writing tasks.

Why consider it

Consider it for this task fit: Long strategic briefs and decision memos.

InputPrompt + optional images
CreditsPay per use — credits based on usage
Best forLong strategic briefs and decision memos
See details
Chat

GPT-5.3 Codex

OpenAI's latest and most capable Codex model on Rivya. It combines state-of-the-art code generation with deeper agentic reasoning for the most demanding development projects.

Why consider it

Consider it for this task fit: Hard debugging in large codebases.

InputPrompt + optional images
CreditsPay per use — credits based on usage
Best forHard debugging in large codebases
See details