GPT-4o Mini
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs.
gpt-4o-miniReleased 18 Jul 2024 (Jul 2024)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.15 | $0.60 | |
| Cached input 50% off input | $0.075 | 50% off input | |
| Batch 50% off | $0.075 | $0.30 | 50% off |
| Priority 67% more | $0.25 | $1.00 | 67% more |
| Web search $25.00 per 1,000 searches | $25.00 per 1,000 searches |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$83.25
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$75.60
- Coding agent1,000 requests a day, 40K in / 2K out, cached$153
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$252
Where to run it
5 hosts serve GPT-4o Mini. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-4o-mini | $0.15 / $0.60 Retires 14 Jan 2027 | gpt-4o-mini | Retires 14 Jan 2027 |
Azure OpenAICloud gpt-4o-mini | $0.15 / $0.60 Retires 14 Apr 2027 | gpt-4o-mini | Retires 14 Apr 2027 |
GMI CloudInference gpt-4o-mini | $0.15 / $0.60 | gpt-4o-mini | |
ReplicateInference gpt-4o-mini | $0.15 / $0.60 | gpt-4o-mini | |
Vercel AI GatewayGateway gpt-4o-mini | $0.15 / $0.60 | gpt-4o-mini | |
GitHub CopilotSubscription gpt-4o-mini | In the subscription | gpt-4o-mini |
Show 10 more listings: regions, snapshots and variantsHide regional listings
| OpenAI | |||||||
| 2024-07-18 gpt-4o-mini-2024-07-18 | $0.15 / $0.60 Retires 14 Jan 2027 | gpt-4o-mini-2024-07-18 | Retires 14 Jan 2027 | ||||
| 2024-07-18 · fine-tuning ft:gpt-4o-mini-2024-07-18 | $0.30 / $1.20 Retires 14 Jan 2027 | ft:gpt-4o-mini-2024-07-18 | Retires 14 Jan 2027 | ||||
| Azure OpenAI | |||||||
| Global Standard gpt-4o-mini | $0.15 / $0.60 Retires 14 Apr 2027 | gpt-4o-mini | Retires 14 Apr 2027 | ||||
| 2024-07-18 gpt-4o-mini-2024-07-18 | $0.15 / $0.60 Retires 14 Apr 2027 | gpt-4o-mini-2024-07-18 | Retires 14 Apr 2027 | ||||
| eu gpt-4o-mini | $0.165 / $0.66 +10% vs headline Retires 14 Apr 2027 | gpt-4o-mini | Retires 14 Apr 2027 | ||||
| us gpt-4o-mini | $0.165 / $0.66 +10% vs headline Retires 14 Apr 2027 | gpt-4o-mini | Retires 14 Apr 2027 | ||||
| eu · 2024-07-18 gpt-4o-mini-2024-07-18 | $0.165 / $0.66 +10% vs headline Retires 14 Apr 2027 | gpt-4o-mini-2024-07-18 | Retires 14 Apr 2027 | ||||
| us · 2024-07-18 gpt-4o-mini-2024-07-18 | $0.165 / $0.66 +10% vs headline Retires 14 Apr 2027 | gpt-4o-mini-2024-07-18 | Retires 14 Apr 2027 | ||||
| us-gov gpt-4o-mini | $0.207 / $0.825 +38% vs headline | gpt-4o-mini | |||||
| GitHub Copilot | |||||||
| 2024-07-18 gpt-4o-mini-2024-07-18 | In the subscription | gpt-4o-mini-2024-07-18 | |||||
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
- TextImagesPDFs
- Produces
- Text
- Features
- Parallel tool callsPDF inputPrompt caching
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
- 24% less
Other frontier labs
- 24% less
Open-weight picks
- 2% less
- 4% less
- 32% less
- 47% less
Benchmarks
Scores published on the model card.
- Aider Polyglot3.6%
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-4o-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-4o-mini", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-4o-mini",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-4o Mini cost?
On OpenAI, GPT-4o Mini costs $0.15 per million input tokens and $0.60 per million output tokens. Cached input costs $0.075 per million tokens.
Which APIs offer GPT-4o Mini?
GPT-4o Mini runs on 5 APIs: OpenAI, Azure OpenAI, GMI Cloud, Replicate and Vercel AI Gateway.
What is GPT-4o Mini's context window?
128K tokens, with up to 16K tokens in one reply.
Is GPT-4o Mini being retired?
OpenAI retires it on 14 Jan 2027; Azure OpenAI (except US government regions) on 14 Apr 2027. 4 hosts keep serving it.
What are cheaper alternatives to GPT-4o Mini?
Models that cost less and keep most of what it can do: GPT-6 Luna on OpenAI (24% less), Claude Haiku 5.5 on Anthropic (24% less) and Deepseekv4.1 Flash on Sarvam (2% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GPT-4o Mini released?
OpenAI released it on 18 Jul 2024.
What is GPT-4o Mini's API model id?
Use gpt-4o-mini with OpenAI.
Sources
Raw catalog entry for gpt-4o-mini on OpenAI
{
"cache_read_input_token_cost": 7.5e-8,
"cache_read_input_token_cost_priority": 1.25e-7,
"deprecation_date": "2027-01-14",
"deprecation_source": "https://developers.openai.com/api/docs/deprecations",
"successor_model": "gpt-6-luna",
"input_cost_per_token": 1.5e-7,
"input_cost_per_token_batches": 7.5e-8,
"input_cost_per_token_priority": 2.5e-7,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 6e-7,
"fedramp_uplift_multiplier": 1.1,
"output_cost_per_token_batches": 3e-7,
"output_cost_per_token_priority": 0.000001,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"search_context_cost_per_query": {
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"source": "https://developers.openai.com/api/docs/pricing"
}