GPT-5.4 Mini
GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.
gpt-5.4-miniReleased 17 Mar 2026 (Mar 2026)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.75 | $4.50 | |
| Cached input 90% off input | $0.075 | 90% off input | |
| Batch 50% off | $0.375 | $2.25 | 50% off |
| Flex 50% off | $0.375 | $2.25 | 50% off |
| Priority 100% more | $1.50 | $9.00 | 100% more |
| Web search $10.00 per 1,000 searches | $10.00 per 1,000 searches | ||
| Regional endpoints 10% more | 10% more |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$502
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$360
- Coding agent1,000 requests a day, 40K in / 2K out, cached$603
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$1,440
Where to run it
7 hosts serve GPT-5.4 Mini. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-5.4-mini | $0.75 / $4.50 | gpt-5.4-mini | |
DatabricksCloud databricks-gpt-5-4-mini | $0.75 / $4.50 | databricks-gpt-5-4-mini | |
Azure OpenAICloud gpt-5.4-mini | $0.75 / $4.50 Retires 21 Sep 2027 | gpt-5.4-mini | Retires 21 Sep 2027 |
Azure AI FoundryCloud gpt-5.4-mini | $0.75 / $4.50 Retires 21 Sep 2027 | gpt-5.4-mini | Retires 21 Sep 2027 |
GMI CloudInference gpt-5.4-mini | $0.75 / $4.50 | gpt-5.4-mini | |
AIHubMixGateway gpt-5.4-mini | $0.75 / $4.50 | gpt-5.4-mini | |
PerplexityGateway gpt-5.4-mini | $0.75 / $4.50 | gpt-5.4-mini | |
GitHub CopilotSubscription gpt-5.4-mini | In the subscription | gpt-5.4-mini |
Show 5 more listings: regions, snapshots and variantsHide regional listings
| OpenAI | |||||||
| 2026-03-17 gpt-5.4-mini-2026-03-17 | $0.75 / $4.50 | gpt-5.4-mini-2026-03-17 | |||||
| Azure OpenAI | |||||||
| 2026-03-17 gpt-5.4-mini-2026-03-17 | $0.75 / $4.50 Retires 21 Sep 2027 | gpt-5.4-mini-2026-03-17 | Retires 21 Sep 2027 | ||||
| eu gpt-5.4-mini | $0.825 / $4.95 +10% vs headline Retires 21 Sep 2027 | gpt-5.4-mini | Retires 21 Sep 2027 | ||||
| us gpt-5.4-mini | $0.825 / $4.95 +10% vs headline Retires 21 Sep 2027 | gpt-5.4-mini | Retires 21 Sep 2027 | ||||
| Azure AI Foundry | |||||||
| 2026-03-17 gpt-5.4-mini-2026-03-17 | $0.75 / $4.50 Retires 21 Sep 2027 | gpt-5.4-mini-2026-03-17 | Retires 21 Sep 2027 | ||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- ImagesTextPDFs
- Produces
- Text
- Effort settings the source lists
- nonexhigh
- Features
- Parallel tool callsPDF inputPrompt cachingTool searchBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than OpenAI.
Smaller OpenAI models
- 73% less
- 88% less
- 84% less
Other frontier labs
- 11% less
- 26% less
- 88% less
- 50% less
Open-weight picks
- 59% less
- 62% less
- 69% less
- 71% less
Model line
Newer and older versions, at each lab's own price.
- Mar 2026GPT-5.4 MiniLatest$0.75 / $4.50
- Aug 2025GPT-5 Mini$0.25 / $2.00
- Apr 2025GPT-4.1 Mini$0.40 / $1.60
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-5.4-mini", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-5.4-mini", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-5.4-mini",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-5.4 Mini cost?
On OpenAI, GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens. Cached input costs $0.075 per million tokens.
Which APIs offer GPT-5.4 Mini?
GPT-5.4 Mini runs on 7 APIs: OpenAI, Databricks, Azure OpenAI, Azure AI Foundry, GMI Cloud, AIHubMix and Perplexity.
What is GPT-5.4 Mini's context window?
272K tokens, with up to 128K tokens in one reply.
Is GPT-5.4 Mini being retired?
Azure AI Foundry and Azure OpenAI retire it on 21 Sep 2027. 5 hosts keep serving it.
Is there a newer version of GPT-5.4 Mini?
No. GPT-5.4 Mini is the newest model in its line.
What are cheaper alternatives to GPT-5.4 Mini?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (73% less), Gemini 3.8 Flash on Google AI Studio (11% less), Grok Build 0.1 on xAI (26% less) and Kimi K2.7 Code on CLF AI Gateway (59% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GPT-5.4 Mini released?
OpenAI released it on 17 Mar 2026.
What is GPT-5.4 Mini's API model id?
Use gpt-5.4-mini with OpenAI. Other hosts use their own ids: databricks-gpt-5-4-mini on Databricks.
Sources
- Databricks pricing
- AIHubMix pricing
- Azure OpenAI pricing
- Azure AI Foundry pricing
- GitHub Copilot pricing
- GMI Cloud pricing
- OpenAI pricing
- Perplexity pricing
- LiteLLM model map
Raw catalog entry for gpt-5.4-mini on OpenAI
{
"cache_read_input_token_cost": 7.5e-8,
"cache_read_input_token_cost_batches": 3.75e-8,
"cache_read_input_token_cost_flex": 3.75e-8,
"cache_read_input_token_cost_priority": 1.5e-7,
"input_cost_per_token": 7.5e-7,
"input_cost_per_token_flex": 3.75e-7,
"input_cost_per_token_batches": 3.75e-7,
"input_cost_per_token_priority": 0.0000015,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.0000045,
"output_cost_per_token_flex": 0.00000225,
"output_cost_per_token_batches": 0.00000225,
"output_cost_per_token_priority": 0.000009,
"reasoning_contexts": [
"auto",
"current_turn",
"all_turns"
],
"reasoning_modes": [
"standard"
],
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"fedramp_uplift_multiplier": 1.1,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_tool_search": true,
"supports_vision": true,
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"source": "https://developers.openai.com/api/docs/pricing",
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
}