GPT 5.4 Mini via the Tokenator API
What the model is for
GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.
Specification
| Full name | GPT 5.4 Mini |
| API ID | gpt-5.4-mini |
| Model vendor | OpenAI |
| Type | Text model (chat / completions) |
| Context window | 400K tokens |
| Max output | 128K tokens |
| Image input | yes |
| Tokenator usage multiplier | 1.6× |
| Input modalities | text, image, file |
| Aliases | cursor-gpt-5.4-mini |
| Supported API formats | /v1/chat/completions /v1/responses /v1/messages |
| Upstream providers | 2 |
| Current status | available |
| Data updated | 2026-08-04 |
Benchmarks
| Intelligence index | 40 |
| Coding index | 56.1 |
| Agentic index | 30.2 |
Artificial Analysis data loaded into the catalog for this model.
Upstream providers
| Provider | Multiplier |
|---|---|
| OpenAI Plus | 1.6× |
| AiPartners Ltd | 1.6× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl
curl https://api.tokenator.top/v1/chat/completions \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.4-mini", "messages": [{"role": "user", "content": "Hello"}] }'
Compatible tools
The model can be used in any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code, OpenClaw.
See also
FAQ about GPT 5.4 Mini
What is the API ID of GPT 5.4 Mini?
gpt-5.4-mini — put this into the model field of your request.
What context window does GPT 5.4 Mini have?
400K tokens; max output is 128K tokens.
How many tokens will a request cost?
(input + output) × 1.6×. See the documentation for details.
Which tools support this model?
Any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code. Setup guides are in the integrations section.