GPT-5.4 vs GPT-5.5

As of November 10, 2026, GPT-5.5 costs 100% more per input token than GPT-5.4 ($5.00 vs $2.50 per 1M), and both have a 1M-token context window.

Prices from LiteLLM's price fileChecked November 10, 2026

GPT-5.4 vs GPT-5.5 side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of November 10, 2026.
	GPT-5.4	GPT-5.5
Input, per 1M tokens	$2.50	$5.00
Output, per 1M tokens	$15.00	$30.00
Cache read, per 1M tokens	$0.25	$0.50
Cache write, per 1M tokens	–	–
Context window	1,050,000 tokens	1,050,000 tokens
Max output	128,000 tokens	128,000 tokens
Image input	Yes	Yes
Tool calling	Yes	Yes
Structured output (JSON)	Yes	Yes
Prompt caching	Yes	Yes
Reasoning	Yes	Yes
Providers on LiteLLM	10	11
Price shown is from	OpenAI	OpenAI
Added to LiteLLM	March 2026	April 2026

Cheapest provider for each

GPT-5.4: Databricks at $2.50 input and $15.00 output per 1M tokens (databricks/databricks-gpt-5-4)
GPT-5.5: OpenAI at $5.00 input and $30.00 output per 1M tokens (gpt-5.5)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of August 27, 2026. Some results were run by Epoch and others collected by Epoch from each benchmark's own leaderboard, linked in the first column. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	GPT-5.4	GPT-5.5
Overall
Epoch Capabilities Index	157.8	160.1
Coding and agents
Terminal-Bench	81.8%	84.7%
APEX-Agents	52.4%	55.1%
Reasoning and knowledge
GPQA Diamond	93.3% (xhigh)	90.7% (low)
ARC-AGI-2	74.0% (xhigh)	85.0% (xhigh)
SimpleQA Verified	45.1% (xhigh)	63.0% (xhigh)
Math
FrontierMath (tiers 1-3)	78.6% (xhigh)	85.3% (xhigh)
FrontierMath (tier 4)	49.0% (xhigh)	72.5% (xhigh)
OTIS Mock AIME 2024-2025	97.8% (high)	84.4% (low)

When to pick which

Pick GPT-5.4 for

Costs 50% less per input token: $2.50 vs $5.00 per 1M.

From differences in the data above only; where the data is equal, no reason is given.

Call GPT-5.4 or GPT-5.5 with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# GPT-5.4
response = completion(model="gpt-5.4", messages=messages)

# GPT-5.5
response = completion(model="gpt-5.5", messages=messages)

# GPT-5.4, falling back to GPT-5.5 if the call fails
response = completion(model="gpt-5.4", messages=messages, fallbacks=["gpt-5.5"])

FAQ

Which is cheaper, GPT-5.4 or GPT-5.5?

GPT-5.4 is cheaper at 3 input tokens per output token: $5.625 per 1M tokens blended ($2.50 input, $15.00 output), versus $11.25 ($5.00 and $30.00) for GPT-5.5, as of November 10, 2026.

Which has the larger context window, GPT-5.4 or GPT-5.5?

Both have a 1,050,000-token context window.

Can I switch from GPT-5.4 to GPT-5.5 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "gpt-5.4" to "gpt-5.5", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.