ModelsOpenAI
GPT-5.3-Codex
Context
tokens
Released
on OpenRouter
Token share
OpenRouter · Jun 18, 2026
Price per million tokens
Input $/MTok
OpenRouter · Aug 9, 2026
Output $/MTok
OpenRouter · Aug 9, 2026
Cache read $/MTok
OpenRouter
| Source | Tracked slug | In $/MTok | Out $/MTok | Cache read | Cache write | Context | Effective | Last Δ (in) |
|---|---|---|---|---|---|---|---|---|
| OpenRouter | openai/gpt-5.3-codex | $1.75 | $14.00 | $0.17 | — | 400K | Aug 9, 2026 | — |
| models.dev | opencode/gpt-5.3-codex | $1.75 | $14.00 | $0.17 | — | 400K | Aug 9, 2026 | 9.4% |
latest tracked price per source · Δ = most recent input-price move within that source
2 sources tracking
Input $/MTok
Output $/MTok
per-source step lines · $/MTok
history since Jul 8, 2026
Context & availability
| Provider | OpenAI |
|---|---|
| Context window | 400K tokens |
| Listed on OpenRouter | Feb 24, 2026 |
| Tracked price sources | OpenRouter · models.dev |
| OpenRouter slugs | openai/gpt-5.3-codex · openai/gpt-5.3-codex-20260224 |
source: OpenRouter model catalog + tracked price feeds
id: gpt-5-3-codex
Share of OpenRouter tokens
source: OpenRouter model rankings · share of tracked coding-token volume
0.2% on Jun 18, 2026
Benchmark results
| Benchmark | Configuration | Score | Date | Source |
|---|---|---|---|---|
no benchmark results attributed to GPT-5.3-Codex yet | ||||
scores as published by each benchmark; configurations differ — compare within a row's benchmark only
Similar models
| # | Model | Tokens/day | 7d Δ | Head-to-head |
|---|---|---|---|---|
| 1 | DeepSeek V4 FlashDeepSeek | 2.7T | 18.7% | vs GPT-5.3-Codex |
| 2 | Hy3Tencent | 1.3T | 11.6% | vs GPT-5.3-Codex |
| 5 | Nemotron 3 UltraNVIDIA | 733B | 106.3% | vs GPT-5.3-Codex |
| 7 | GLM 5.2Z.ai | 533B | 41% | vs GPT-5.3-Codex |
ranked by OpenRouter usage-rank proximity
snapshot Aug 20, 2026
GPT-5.3-Codex FAQ
- How much does GPT-5.3-Codex cost per token?
- GPT-5.3-Codex is priced at $1.75 per million input tokens and $14.00 per million output tokens, per OpenRouter as of Aug 9, 2026.
- What is GPT-5.3-Codex's context window?
- GPT-5.3-Codex supports a context window of up to 400K tokens, per OpenAI.
- How widely used is GPT-5.3-Codex?
- GPT-5.3-Codex accounts for about 0.2% of tracked OpenRouter coding-token volume as of Jun 18, 2026.
- What are the alternatives to GPT-5.3-Codex?
- By OpenRouter usage, comparable models include DeepSeek V4 Flash, Hy3, and Nemotron 3 Ultra. Side-by-side comparisons are linked in the alternatives table.
Track GPT-5.3-Codex
Email me when GPT-5.3-Codex's price moves or it gets deprecated.