Long context

Codex Auto Review API pricing

OpenAI's GPT series — broad general capability, wide ecosystem, and the native models behind Codex CLI.

Model IDcodex-auto-review

ChatStreamingTool callingVision

Get API Key Run your first request

Call summary

Input

$5.00$0.50/ 1M tokens

Cache write $0.50

Cache read $0.25

Output

$30.00$3.00/ 1M tokens

Context Window

1.05M

API Endpoints

Codex Auto Review API endpoints

One API key — call this model through any of the 2 endpoints below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model

Chat Completions reference

POST/v1/responsesResponses API · Native for Codex CLI

Responses API reference

Call Codex Auto Review from your code

The same API key works across all 2 endpoints below.

Endpoint

/v1/chat/completions

Model ID

codex-auto-review

Request example

bash

curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "codex-auto-review",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Get API Key

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Successful response share

96.42%

Success 2xx

96.42%

Rate limit 429

0.00%

Server 5xx

3.58%

TPS

98.38

tokens/s

Avg. time to first token

10.87 s

Avg. latency

13.08 s

Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.

Updated Oct 24, 2026, 8:12 PM UTC

More GPT models on Router One

15 other GPT models on the same gateway and API key — each page lists endpoints, posted price, and context window.

GPT-5.6 Sol$0.50 in / $4.00 out per 1M1.05M context GPT-5.6 Terra$0.25 in / $1.50 out per 1M1.05M context GPT-6.1 Sol$0.40 in / $2.00 out per 1M1.05M context GPT-6 Astra$2.00 in / $10.00 out per 1M1.05M context GPT-6 Sol$0.40 in / $2.00 out per 1M1.05M context GPT Image 2$0.50 per image GPT Image 2.5 Flare$0.50 per image GPT Image 2.5 Sunburst$0.50 per image

7 channel versions

GPT-5.5 · Azure$3.75 in / $22.50 out per 1M1.05M context GPT-5.6 Luna · Azure$0.15 in / $0.90 out per 1M1.05M context GPT-5.6 Sol · Azure$3.00 in / $15.00 out per 1M1.05M context GPT-5.6 Terra · Azure$1.50 in / $9.00 out per 1M1.05M context GPT-6.1 Sol · Azure$1.50 in / $7.50 out per 1M1.05M context GPT-6 Astra · Azure$7.50 in / $37.50 out per 1M1.05M context GPT-6 Sol · Azure$1.50 in / $7.50 out per 1M1.05M context

Codex Auto Review at a glance

Codex Auto Review (model ID codex-auto-review) is a GPT-series text model on Router One. Posted rate: $0.50 in / $3.00 out per 1M tokens (was $5.00 in / $30.00 out). No Router One subscription plan includes Codex Auto Review today; every call bills the wallet at its posted rate. Context window: 1.05M tokens. Endpoints: POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path).

Codex's Auto-review may request this ID: with approvals_reviewer = "auto_review" set, the reviewer subagent prefers codex-auto-review (per the openai/codex source, rust-v0.159.3, checked 2026-10-01). Router One lists it, so those review calls route and bill like any other request. It is listed for that reviewer; for your own application, choose a model from the catalog by name.

Codex Auto Review FAQ

What is codex-auto-review, and why does Codex request it?

How much does Codex Auto Review cost on Router One?

Codex Auto Review is billed per token on Router One: $0.50 in / $3.00 out per 1M tokens, pay as you go.

Is Codex Auto Review included in Router One subscriptions?

No Router One subscription plan includes Codex Auto Review today; every call bills the wallet at its posted rate.

Which endpoints serve Codex Auto Review?

Codex Auto Review is served on 2 endpoints — POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path). The same Router One API key works on each.

What is Codex Auto Review's context window?

Codex Auto Review accepts up to 1.05M tokens of context per request on Router One.

Start using Codex Auto Review

Create an API key and call Codex Auto Review on Router One — pay as you go, with per-request cost and latency visibility.

Get API Key Plans & pay-as-you-go pricing Compare models side by side Quickstart guide Codex CLI and the Responses API