GPT-5.4 with Jev
GPT-5.4 is a model from OpenAI, released 2026-03-05. It costs $2.50 per million input tokens and $15 per million output tokens, reads up to 1.05M tokens of context, and writes up to 128,000 tokens in one reply. Through llm11, set model to openai/gpt-5.4.
- Input price
- $2.50 / 1M
- Output price
- $15 / 1M
- Context window
- 1.05M tokens
- Max output
- 128K tokens
- Cached input
- $0.250 / 1M
- Released
- 2026-03-05
- Accepts
- text, image, file
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 10% of the 332 priced models we can call cost more.
Using GPT-5.4 with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. GPT-5.4 does the answering when Jev sends it work, or when you name it yourself. GPT-5.4 falls in the llm11-smart band, and the labs and limits it meets make it eligible for that pack. Today it is the cheapest model in that pack's live pool, so it is where routine requests land.
Jev is new, so we have not published results for GPT-5.4 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00425 | $4.25 |
| Question over retrieved documents | 4,000 / 500 | $0.018 | $17.50 |
| Long document summary | 30,000 / 1,000 | $0.090 | $90.00 |
Cheaper models to try
The catalogue has no benchmark score for GPT-5.4, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| OpenAI GPT-5.3-Codex | $1.75 | $14 | 400K | |
| OpenAI GPT-5.2-Codex | $1.75 | $14 | 400K | |
| OpenAI GPT-5.2 | $1.75 | $14 | 400K | |
| OpenAI GPT-5.2 Chat | $1.75 | $14 | 128K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="openai/gpt-5.4",
messages=[{"role": "user", "content": "Hello"}],
)More from OpenAI
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| GPT-6 Luna | $0.100 | $0.500 | 1.05M | |
| GPT-6 Luna Pro | $0.100 | $0.500 | 1.05M | |
| GPT-6 Sol | $2.00 | $10 | 1.05M | |
| GPT-6 Sol Pro | $2.00 | $10 | 1.05M | |
| GPT-6 Astra | $10 | $50 | 1.05M | |
| GPT-6 Astra Pro | $10 | $50 | 1.05M |
Questions
- What is GPT-5.4 with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. GPT-5.4 does the answering when Jev sends it work, or when you name it yourself. GPT-5.4 falls in the llm11-smart band, and the labs and limits it meets make it eligible for that pack. Today it is the cheapest model in that pack's live pool, so it is where routine requests land. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is GPT-5.4 a System One model?
- No. GPT-5.4 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does GPT-5.4 cost?
- $2.50 per million input tokens and $15 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.018, so a thousand of them is about $17.50. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the GPT-5.4 context window?
- 1,050,000 tokens, with up to 128,000 tokens in a single reply.
- Does GPT-5.4 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use GPT-5.4 through llm11?
- Yes. Set model to openai/gpt-5.4 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to GPT-5.4?
- Routing decisions are made by Jev, TypeSafe AI's System One model. GPT-5.4 falls in the llm11-smart band, and the labs and limits it meets make it eligible for that pack. Today it is the cheapest model in that pack's live pool, so it is where routine requests land.
- What is a cheaper alternative to GPT-5.4?
- Nearest in price and below it: OpenAI GPT-5.3-Codex at $1.75 in and $14 out, OpenAI GPT-5.2-Codex at $1.75 in and $14 out and OpenAI GPT-5.2 at $1.75 in and $14 out. The catalogue has no benchmark score for GPT-5.4, so this is a price ordering. It does not claim these answer as well.