openai
OpenAI: GPT-5.4
openai/gpt-5.4
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
Specifications
- Model ID
- openai/gpt-5.4
- Canonical ID
- openai/gpt-5.4-20260305
- Creator
- openai
- Added to OpenRouter
- 05.03.2026
- Context length
- 1,050,000
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $2.5 / out $15
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · default medium · efforts: xhigh, high, medium, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | AA — next 20% of the cohort | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default medium · efforts: xhigh, high, medium, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 71.1 | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · 3dwin rate 42.3% · rank 96 | 1,084Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · asciiartwin rate 55.4% · rank 28 | 1,194Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 52.5% · rank 63 | 1,203Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 56.6% · rank 43 | 1,233Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 57.6% · rank 44 | 1,229Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 57.8% · rank 35 | 1,185Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 57.4% · rank 48 | 1,232Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 52.5% · rank 64 | 1,213Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 47.7% · rank 42 | 1,021Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 40.9% · rank 41 | 995Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 46.9% · rank 24 | 1,135Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 46.1% · rank 47 | 1,081Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · webappswin rate 40.3% · rank 43 | 1,041Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| OpenAI | 1,050,000 | $1.25 | $7.5 | — | — | 100% |
| Azure | 1,050,000 | $2.5 | $15 | — | — | 100% |
| OpenAI | 1,050,000 | $2.5 | $15 | — | — | 100% |
| Azure | 1,050,000 | $2.75 | $16.5 | — | — | — |
| Azure | 1,050,000 | $2.75 | $16.5 | — | — | 100% |
| Amazon Bedrock | 1,050,000 | $2.75 | $16.5 | — | — | — |
| OpenAI | 1,050,000 | $5 | $30 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
- Gondola says revenue more than doubled as its small team builds with Codex and ChatGPTOpenAI customer story: Gondola says Codex lifted engineering output 25% and revenue more than doubled year over year, while ChatGPT automates daily operations for its small team.
- OpenAI study links fading chain-of-thought transparency to capability and compute trade-offsAn analysis by OpenAI's safety team attributes the declining monitorability of frontier models like GPT-6 Astra to four training factors, framing the loss of visible reasoning as a trade-off between safety, capability, and cost.
- LLM batch APIs cut prices in half, but only for traffic that can waitA cost-modeling blog explains how batch discounts apply only to deferrable calls, why batch and caching stack multiplicatively, the billing bug this caused, and why dropping a model tier usually saves more.