GPT-5.3 Codex (xhigh)
Intelligence
32.5
#95 of 520 models
Output speed
126.7 tok/s
Measured generation rate
Cost / index task
—
Measured evaluation workload
End-to-end latency
55ms
First answer 51ms
01 / Position
A model in the landscape
Compare this model with peers across intelligence, speed, cost, and individual evaluations.
02 / Evidence
Benchmark results
9 distinct evaluations grouped by topic. Explore cross-model charts or switch to the full results list.
03 / Operation
Speed, tokens & price
Prices are per million tokens; latency and task costs describe the captured evaluation rather than a universal provider guarantee.
Token pricing
- Input / 1M
- $1.75
- Output / 1M
- $14.00
- Cache read / 1M
- $0.175
- Cache write / 1M
- —
- Cache-hit discount
- 90%
Response & usage
- Output speed
- 126.7 tok/s
- First chunk
- 51ms
- First answer
- 51ms
- Output / task
- —
- Reasoning / task
- —
Evaluation workload
- Canonical input
- —
- Canonical output
- —
- Answer / task
- —
- Index time / task
- —
- Run cost
- —
By prompt type
| Prompt | Output speed | First chunk | First answer | End to end |
|---|---|---|---|---|
| Medium | 141.4 tok/s | 35ms | 35ms | 39ms |
| Long | 126.7 tok/s | 51ms | 51ms | 55ms |
| Hundred K | 147 tok/s | 36ms | 36ms | 39ms |
| Medium Parallel | 108.4 tok/s | 37ms | 37ms | 41ms |
04 / Access
License & availability
Recorded license
No license recorded
No direct license document is available in the captured record. Weight availability alone does not establish usage rights.
- Weight access
- Closed / unavailable
- Classification
- Proprietary
- Reasoning
- Yes
Routing and providers
- OpenRouter ID
- openai/gpt-5.3-codex
- Tokenizer
- GPT
- Instruct type
- —
- Captured endpoints
- 3
| Provider | Quantization | Context | tok/s |
|---|---|---|---|
| Azure | unknown | 400k | — |
| OpenAI | unknown | 400k | — |
| OpenAI | unknown | 400k | — |
05 / Audit
Underlying fields
Inspect the captured model and routing records. Artificial Analysis destination links are omitted.