GPT-5.4
by OpenAIopenai/gpt-5.4
LLMCompare cannot run GPT-5.4 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.
See the models that can be run nowGPT-5.4 at a glance
- Context length
- 1,050,000 tokens
- Maximum output
- 128,000 tokens
- Accepts
- Text, Image, File
- Returns
- Text
- Features
- ReasoningJSON outputTool callingPrompt cachingImage input
- Reasoning effort levels
xhighhighmediumlownoneReasoning can be turned off.- Released
- 5 Mar 2026
- Knowledge cutoff
- Not published
Model facts synced from the OpenRouter model list on 21 Oct 2026.
GPT-5.4 pricing by route
A route is the service LLMCompare calls to reach the model. GPT-5.4 has 1 route. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Cache readper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|---|
| OpenRouterDefault | Not configured | $2.50 | $15.00 | $0.25 | openrouter.ai/openai/gpt-5.4 |
The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.
Cost calculator
Estimate what a batch of calls to GPT-5.4 costs. The starting numbers are examples. Change them to match your task.
Part of the input tokens above, billed at the cache read price.
Billed in addition to the output tokens.
- Cost per call
- $0.01
- 12 credits
- Cost of 100 calls
- $1.00
- 1,200 credits
Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.
Parameters you can set
These are the parameters LLMCompare can set when it calls the model through OpenRouter.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
max_tokens | Integer | 1 to 128,000 | Provider default |
reasoning_effort | One of | xhighhighmediumlownone | medium |
seed | Integer | -2,147,483,648 to 4,294,967,295 | Provider default |
response_format | One of | textjson_object | Provider default |
About GPT-5.4
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...
Description as published for this model. LLMCompare has not edited it.
Models to compare with GPT-5.4
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
GPT-5.3-CodexOpenAIopenai/gpt-5.3-codex | 400k | 128k | $1.75 | $14.00 | ReasoningJSONToolsCacheVision | No route yet | ||
GPT-5.2-CodexOpenAIopenai/gpt-5.2-codex | 400k | 128k | $1.75 | $14.00 | ReasoningJSONToolsCacheVision | No route yet | ||
GPT-5.2 ChatOpenAIopenai/gpt-5.2-chat | 128k | 32k | $1.75 | $14.00 | JSONToolsCacheVision | No route yet | ||
Ember-1Fireworksfireworks/ember-1 | 1.05M | 944k | $3.00 | $15.00 | ReasoningJSONToolsCacheVision | No route yet | ||
Claude Sonnet 4.6Anthropicanthropic/claude-sonnet-4.6 | 1M | 128k | $3.00 | $15.00 | ReasoningJSONToolsCacheVision | No route yet | ||
Sonar Pro SearchPerplexityperplexity/sonar-pro-search | 200k | 8k | $3.00 | $15.00 | JSONVision | No route yet |
Questions about GPT-5.4
- How much does GPT-5.4 cost?
- On the OpenRouter route, GPT-5.4 costs $2.50 per 1 million input tokens and $15.00 per 1 million output tokens, in US dollars. Input tokens that GPT-5.4 reads from the prompt cache cost $0.25 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
- What is the context length of GPT-5.4?
- GPT-5.4 has a context length of 1,050,000 tokens and returns up to 128,000 output tokens in one call.
- What inputs does GPT-5.4 accept?
- GPT-5.4 accepts these inputs: Text, Image, File. GPT-5.4 returns: Text.
- Which reasoning effort levels does GPT-5.4 support?
- GPT-5.4 supports these reasoning effort levels: xhigh, high, medium, low, none. Reasoning can be turned off for GPT-5.4.
- Can I test GPT-5.4 on my own data?
- Not yet. LLMCompare lists the prices and parameters of GPT-5.4, but no route to GPT-5.4 is configured on LLMCompare, so it cannot be selected for an evaluation.