GPT-5.3 Codex is OpenAI's "most capable agentic coding model to date," succeeding GPT-5.2 Codex as the default engine for autonomous coding workflows.
- 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
Benchmarks
Vendor-published: Alibaba (Qwen) Anthropic ByteDance Google MiniMax Moonshot OpenAI Tencent Z.ai
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 |
|---|
- Described as the most capable agentic coding model to date
- 400k context
- reasoning effort low-xhigh
Use GPT-5.3 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-5.3-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-5.3-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-5.3-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-5.3-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-5.3-codex")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About GPT-5.3 Codex
- Tuned specifically for agentic coding in Codex environments, it retains the 400K-token context window and 128K max output of its predecessor at the same per-token pricing, with four reasoning-effort levels plus streaming, function calling, and structured outputs.
- Within that 400K window the documented input ceiling is 272K tokens.
- Effort accepts low, medium, high, and xhigh.
- There is no none level here, and OpenAI publishes no default, so treat the effort setting as something to pin explicitly rather than inherit.
- The tool list is deliberately narrow next to the general-purpose GPT-5 models: function calling, web search, hosted shell, and skills, with no file search, code interpreter, computer use, MCP, or image generation.
- Upstream it is a Responses-API model with no Chat Completions or Batch support, and it ships as a single undated snapshot rather than a dated one, so there is no pinned alias to hold a build steady.
- Documentation is thin by OpenAI's standards: the changelog entry announcing it says only that it was released to the Responses API, with no comparative notes against GPT-5.2 Codex.
- For agent frameworks already speaking the OpenAI protocol, Synthorai serves GPT-5.3 Codex on its compatible chat endpoint out of the box.
FAQ
Is the GPT-5.3 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-5.3 Codex.
What is GPT-5.3 Codex best at?
Most capable agentic coding model to date; retains 400K context at unchanged pricing; default engine for autonomous coding workflows. See the About section for the full picture from the vendor's own release notes.
How much does GPT-5.3 Codex cost?
GPT-5.3 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-5.3 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-5.3 Codex?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gpt-5.3-codex", and you're done. One API key covers every model on the gateway.
What is GPT-5.3 Codex's knowledge cutoff?
GPT-5.3 Codex's knowledge cutoff is 2025-08, per the vendor's official documentation (as of 2026-07-09).
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.