This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
OpenAI has launched a newer release, GPT-5.6 Luna. We suggest considering it instead.
GPT-5.4 nano: Intelligence, Performance & Price Analysis
Available providers
Model summary
Verbosity
GPT-5.4 nano (Xhigh) supports text and image input, outputs text, and has a 400k tokens context window with knowledge up to August 2025.
Pricing for GPT-5.4 nano (Xhigh) is $0.20 per 1M input tokens (moderately priced, median: $0.24) and $1.25 per 1M output tokens (somewhat expensive, median: $0.83).
| Input modality | Supports: text and image |
|---|---|
| Output modality | Supports: text |
| Knowledge cutoff | Aug 31, 2025 |
| Context window | 400k ~600 A4 pages of size 12 Arial font |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Evaluations
Agentic knowledge work, Elo
Agentic SaaS workflows
Professional document reasoning, All-pass
Agentic coding & terminal use
Agentic business operations
Agentic real-world work tasks, Elo
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Performance
Measured by time per task (minutes), output speed (tokens per second), time to first answer token and time to first token (seconds)
Time per Intelligence Index Task
Output Speed
Time to First Answer Token
Context Window
Context Window
Further details
Weights | |||||||||
|---|---|---|---|---|---|---|---|---|---|
| GPT-5.4 nano (Xhigh) | - | - | 400k | $0.18 | - | 146 | Not available | ||
| GPT-5.4 nano (Medium) | - | - | 400k | $0.18 | - | 137 | Not available | ||
| GPT-5.4 nano (Non-reasoning) | - | - | 400k | $0.18 | - | 127 | Not available |
Frequently Asked Questions
Common questions about GPT-5.4 nano
GPT-5.4 nano was released on March 17, 2026.
GPT-5.4 nano was created by OpenAI.
GPT-5.4 nano has a time to first answer token of 59.21s (xhigh), 6.44s (medium), and 1.26s (non-reasoning) (based on OpenAI's API). GPT-5.4 nano (Xhigh)'s time to first answer token is at the higher end compared to other models in a similar price tier (median: 8.26s).
GPT-5.4 nano costs $0.20 per 1M input tokens (better than average, median: $0.24) and $1.25 per 1M output tokens (somewhat higher than average, median: $0.83), based on OpenAI's API.
GPT-5.4 nano costs $0.20 per 1M input tokens and $1.25 per 1M output tokens (based on OpenAI's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.18 per 1M tokens. Pricing may vary by provider. Compare provider pricing
Yes, GPT-5.4 nano (xhigh and medium) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer. No, GPT-5.4 nano (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
GPT-5.4 nano supports text and image input.
GPT-5.4 nano supports text output.
Yes, GPT-5.4 nano supports image input and can analyze, describe, and answer questions about images.
Yes, GPT-5.4 nano is multimodal. It can process text and image input and generate text output.
GPT-5.4 nano has a context window of 400k tokens. This determines how much text and conversation history the model can process in a single request.
No, GPT-5.4 nano is proprietary. The model weights are not publicly available.
GPT-5.4 nano is a proprietary model and OpenAI has not disclosed the model size or parameter count.
GPT-5.4 nano has a knowledge cutoff of August 2025. The model's training data includes information up to this date.
Yes, GPT-5.4 nano is available via API through 1 provider. Compare API providers
GPT-5.4 nano is available through 1 API provider. Compare providers