GPT-5.4
Capable, cost-efficient predecessor to GPT-5.5 with a 1M+ context window
Context window
1,050,000 tokens (128,000 max output)
Input / 1M tokens
$2.50
Output / 1M tokens
$15.00
Provider
OpenAI
Cached input $0.25 per 1M. Prompts exceeding 272K input tokens are billed at 2x input and 1.5x output for the full session. A gpt-5.4-pro variant is priced at $30 input / $180 output per 1M. · Data verified 2026-07-05
GPT-5.4 is a GPT-5-generation frontier model available in the OpenAI API, with a snapshot dated March 5, 2026 (gpt-5.4-2026-03-05). It offers a 1,050,000-token context window with up to 128,000 output tokens, accepts text and image input, and has a knowledge cutoff of August 31, 2025. It sits below GPT-5.5 in capability but is priced lower ($2.50 input / $15 output per 1M), making it a strong value option for large-context work that does not require the newest frontier reasoning. A gpt-5.4-pro variant offers extended reasoning at higher cost.
Capability index
Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.
How to access it
Available in the OpenAI API via model id 'gpt-5.4' (snapshot 'gpt-5.4-2026-03-05'), plus a gpt-5.4-pro variant. Superseded by GPT-5.5 as the recommended frontier model but still fully available.
Strengths
- ✓Large 1.05M-token context window
- ✓Lower price than GPT-5.5 ($2.50/$15 vs $5/$30)
- ✓Solid general coding, reasoning, and tool use
- ✓Multimodal text + image input
Best for developers who...
When to choose it (and when not to)
Reach for GPT-5.4 when...
- →Large-context tasks where GPT-5.5-level frontier reasoning is not required
- →Cost-conscious production workloads that still need strong capability
- →Migrating from GPT-5.4-based systems where behavior is already tuned
Look elsewhere if...
- ✕Tasks needing the strongest available reasoning/coding (use GPT-5.5 or GPT-5.6 Sol)
- ✕Latency-critical chat where an Instant tier would be faster
- ✕Budgets sensitive to the >272K-token long-context surcharge
How to use it
- ›Prefer gpt-5.4 over gpt-5.5 when cost matters more than the last increment of quality
- ›Stay under 272K input tokens to avoid the long-context price multiplier
- ›Use cached input ($0.25/1M) for repeated large prefixes
- ›Pin the snapshot 'gpt-5.4-2026-03-05' for reproducible behavior
Quickstart
Pythonfrom openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5.4",
input="Explain this stack trace and propose a fix.",
)
print(response.output_text)Snapshot 'gpt-5.4-2026-03-05' pins behavior. gpt-5.4-pro is available for deeper reasoning at higher cost.
API model id: gpt-5.4
Compare GPT-5.4 with
GPT-5.4 vs GPT-5
OpenAI - 400,000 tokens (128,000 max output) ctx
GPT-5.4 vs GPT-5.5
OpenAI - 1,050,000 tokens (128,000 max output) ctx