GPT-5.2 Codex is described by OpenAI as its most intelligent coding model of its generation: an upgraded version of GPT-5.2 optimized for long-horizon, agentic coding tasks in Codex-style environments.
- Input
- text image $1.75/M
- Output
- text $14/M
- Cache read
- $0.875/M
- Context
- 400K
- vs GPT-4o
- ~65% cheaper
- Knowledge cutoff
- 2025-08
Price in context
Where the price sits among 60 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Tokens
| Context window (vendor spec) | 400,000 |
|---|---|
| Max output (vendor spec) | 128,000 |
| Knowledge cutoff | 2025-08 |
Prompt caching
| How it caches | automatic |
|---|---|
| Min prefix | 1,024 |
| Lifetime | 5-10m, up to 1h |
Thinking
| Vendor control | reasoning.effort |
|---|---|
| Accepted values | low · medium · high · xhigh |
| Can be turned off | No |
| Thinking behaviour | OpenAI publishes no default effort for this model. |
| Parameter | reasoning_effort |
| Values | minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies |
Model
| Modalities | text + image → text |
|---|
- DEPRECATED: shut down by OpenAI on 2026-07-23, with gpt-5.6-sol named as the substitute
- upstream returns HTTP 404. Was a GPT-5.2 variant optimized for long-running agentic coding in Codex environments
- 400k context
Use GPT-5.2 Codex in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="gpt-5.2-codex",
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "gpt-5.2-codex",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.2-codex",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "gpt-5.2-codex",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("gpt-5.2-codex")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About GPT-5.2 Codex
- It supports a 400K-token context window, 128K max output tokens, four reasoning-effort levels (low through xhigh), streaming, function calling, and structured outputs.
- The model is purpose-built for autonomous, extended development workflows rather than general chat.
- Within that 400K window the documented input ceiling is 272K tokens, and image input and prompt caching are supported, with an August 31, 2025 knowledge cutoff.
- OpenAI's model guidance points it at companies building interactive coding products and the full spectrum of coding tasks, calling it the coding-optimized variant of GPT-5.2 for agentic workflows in Codex or Codex-like environments; pricing matches GPT-5.2 token for token, and there is no none effort level here, unlike the general-purpose model that defaults to it.
- Upstream it is a Responses-API model with Chat Completions and Batch both listed as unsupported, and its tool list is narrower than the general-purpose GPT-5 models': function calling, web search, hosted shell, and skills, with no file search, code interpreter, image generation, or MCP.
- It ships as a single undated snapshot with no dated alias to pin a build against.
- A February 2026 changelog entry records an inference-stack optimization that made it roughly 40% faster with model weights unchanged.
- OpenAI marks it deprecated: its shutdown date of July 23, 2026 has now passed, and gpt-5.6-sol is named as the substitute.
- Synthorai routes GPT-5.2 Codex traffic through its OpenAI-compatible endpoint with no client changes required.
FAQ
Is the GPT-5.2 Codex API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $1.75/M input tokens, that credit alone covers roughly 71 requests of ~8K tokens against GPT-5.2 Codex.
What is GPT-5.2 Codex best at?
Most intelligent coding model of its generation; optimized for long-horizon agentic coding; four reasoning-effort levels, low through xhigh. See the About section for the full picture from the vendor's own release notes.
How much does GPT-5.2 Codex cost?
GPT-5.2 Codex costs $1.75 per million input tokens and $14 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.875/M.
Does GPT-5.2 Codex support prompt caching?
Yes, automatically: OpenAI-served prompts cache with no code changes. Cached input tokens bill at $0.875/M vs $1.75/M uncached; prompts need a 1,024-token stable prefix to cache (TTL 5-10m, up to 1h). Prompt caching guide →
How do I get access to GPT-5.2 Codex?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-5.2-codex", and you're done. One API key covers every model on the gateway.
What is GPT-5.2 Codex's knowledge cutoff?
GPT-5.2 Codex's knowledge cutoff is 2025-08, per the vendor's official documentation (as of 2026-07-24).
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.