OPENAI MODEL GUIDE
Codex Auto Review API
An LLMFly AI route for automated code review. Its exact API ID is codex-auto-review; public vendor specifications are not inferred from the display name.
Choosing and integrating
Codex Auto Review API pricing breakdown
Codex Auto Review (codex-auto-review) is billed by token usage. Prices below are USD per 1M tokens. LLMFly AI rates already include the 0.3x group multiplier; do not apply it again. Provider reference prices are separate. These rates come from the site's Model Plaza snapshot; confirm live catalog and account rates before calling.
Example: a request with 10,000 uncached input tokens and 1,000 output tokens costs approximately $0.00096 in LLMFly AI token charges. This excludes cache writes, tools, retries, and other additional fees.
- Platform and provider prices use their own input-token tiers. Do not apply provider long-context multipliers to platform prices.
- Not listed does not mean free. Account for cache reads, cache writes, and uncached input in their respective billing categories.
- Token cost = tokens in each billing category × its price per million ÷ 1,000,000. Add tools and other charges separately.
| Price source | Input tokens per request | Input | Output | Cache write | Cache read | 1h cache write |
|---|---|---|---|---|---|---|
| LLMFly AI | 0 < tokens ≤ 272,000 | $0.06 | $0.36 | $0.075 | $0.006 | $0.075 |
| LLMFly AI | 272,000 < tokens | $0.12 | $0.54 | $0.15 | $0.012 | $0.15 |
| Provider reference | 0 < tokens ≤ 272,000 | $0.2 | $1.2 | $0.25 | $0.02 | $0.25 |
| Provider reference | 272,000 < tokens | $0.4 | $1.8 | $0.5 | $0.04 | $0.5 |
Pricing tiers and additional charges
OpenAI long-context tiers, caching, and tool charges depend on the exact model. The calculator evaluates LLMFly AI rates and vendor references separately and does not infer unlisted charges.
Codex Auto Review capabilities and workloads
An LLMFly AI route for automated code review. Its exact API ID is codex-auto-review; public vendor specifications are not inferred from the display name.
Automated review workflows with explicit acceptance criteria and human escalation.
- Use for repository or patch review only after validating the request shape and returned review format.
Limits to check before migration
- Do not treat this route name as an OpenAI product title or infer unsupported tools, context, or output limits.
Comparing Codex Auto Review with sibling models
Compare the exact API ID, vendor lifecycle, context, maximum output, tools, and thinking controls first. Then measure pass rate, latency, tokens, and total cost on the same tasks. The Codex Auto Review version or tier label alone does not prove better results.
Use the exact model ID when connecting
Set the model field to codex-auto-review; do not infer its spelling from the display name. Configure the API address and key using the access documentation; the snippet only shows the model field, not a complete request.
- Send a minimal text request and inspect the response and usage.
- Test streaming, tool calls, and structured output separately if your application needs them.
- Check retry behavior and spending limits before increasing traffic.
{
"model": "codex-auto-review"
}Vendor capability versus gateway access
Codex Auto Review's specifications above were checked in vendor documentation. No paid inference requests or account-route modality, tool, or beta-parameter tests were run in this review. Validate your application before launch; documentation review is not end-to-end compatibility certification.
Frequently asked questions
What should I put in the model field?
Use the exact ID codex-auto-review, not the display name.
How is the discount calculated?
The current 0.3x multiplier is applied to the base rate, giving 70% off the catalog's official reference. Amounts are shown per million tokens.
Do these prices include every possible fee?
Not necessarily. Check cache-write duration, tools, and other route charges separately. Use the full pricing table and actual usage records to reconcile a bill.
What are the context and output limits?
Vendor documentation lists Route-defined context and Not published maximum output; confirm gateway route limits separately.
Use the Codex Auto Review API
LLMFly AI provides this model. Use the exact ID codex-auto-review and confirm current account pricing in Model Plaza.