GPT-5.3 Codex Spark pricing, context window and limits
GPT-5.3 Codex Spark costs $1.75 per million input tokens and $14 per million output tokens at OpenAI list price. It accepts up to 128,000 tokens of context and returns up to 32,000 tokens.
- Model id
gpt-5.3-codex-spark - Snapshot
What does GPT-5.3 Codex Spark cost?
| Input | $1.75 |
|---|---|
| Output | $14 |
| Cached input (read) | $0.175 |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can GPT-5.3 Codex Spark read and write?
| Context window | 128,000 |
|---|---|
| Max input | 100,000 |
| Max output | 32,000 |
What can GPT-5.3 Codex Spark do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text, image, pdf |
| Output | text |
What does a request to GPT-5.3 Codex Spark cost?
| A typical request: 1,000 tokens in, 500 out | $0.0088 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.032 |
| 1,000 typical requests | $8.75 |
| 1 million tokens in and 1 million out | $15.75 |
Input read from the provider's prompt cache costs $0.175 per million tokens instead of $1.75, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.0072 instead of $0.0088.
Among 49 OpenAI models with a published price, GPT-5.3 Codex Spark is the 18th cheapest by input price. Its context window is the 34th largest of 48. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call GPT-5.3 Codex Spark through DVARA?
Configure the openai provider in the DVARA LLM Gateway and send the model id gpt-5.3-codex-spark. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other OpenAI models are there?
- GPT-5.3 Codex$1.75 in · $14 out · 400K context
- GPT-5.4$2.5 in · $15 out · 1.05M context
- GPT-5.3 Chat (latest)$1.75 in · $14 out · 128K context
- GPT-5.4 mini$0.75 in · $4.5 out · 400K context
- GPT-5.2 Pro$21 in · $168 out · 400K context
- GPT-5.4 nano$0.2 in · $1.25 out · 400K context
- GPT-5.2 Chat$1.75 in · $14 out · 128K context
- GPT-5.4 Pro$30 in · $180 out · 1.05M context
- GPT-5.2$1.75 in · $14 out · 400K context
- GPT-5.5$5 in · $30 out · 1.05M context
- GPT-5.1$1.25 in · $10 out · 400K context
- GPT-5.5 Pro$30 in · $180 out · 1.05M context
Which models from other providers are similar to GPT-5.3 Codex Spark?
These are the closest in context window and input price, one per provider.
- Pixtral Large (25.02) (EU)Amazon Bedrock · $2 in · $6 out · 128K context
- Pixtral Large (latest)Mistral AI · $2 in · $6 out · 128K context
- Deep Research Max Preview (Apr-21-2026)Google Gemini · $2 in · $12 out · 131K context
- Qwen2.5-VL 72B InstructAlibaba Qwen · $2.294 in · $6.881 out · 131K context
- Command A PlusCohere · $2.5 in · $10 out · 128K context