GPT-5 Mini API Pricing
As of October 10, 2026, GPT-5 Mini costs $0.25 per 1M input tokens and $2.00 per 1M output tokens on OpenAI, with cache reads at $0.025 per 1M tokens. Across 8 providers on LiteLLM, the input price ranges from $0.25 to $0.30. It has a 272,000-token context window and returns up to 128,000 tokens per response.
- Input
- $0.25 / 1M tokens
- Output
- $2.00 / 1M tokens
- Cache read
- $0.025 / 1M tokens
- Context window
- 272,000 tokens
- Max output
- 128,000 tokens
- Providers
- 8
- Added to LiteLLM
- August 2025
GPT-5 Mini pricing by provider
14 listings across 8 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Cache write | Batch in | Batch out | Context |
|---|---|---|---|---|---|---|---|---|
| OpenAI | gpt-5-mini | $0.25 | $2.00 | $0.025 | – | $0.125 | $1.00 | 272K |
| OpenAIsnapshot 2025-08-07 | gpt-5-mini-2025-08-07 | $0.25 | $2.00 | $0.025 | – | $0.125 | $1.00 | 272K |
| Azure OpenAI | azure/gpt-5-mini | $0.25 | $2.00 | $0.025 | – | $0.125 | $1.00 | 272K |
| Azure OpenAIsnapshot 2025-08-07 | azure/gpt-5-mini-2025-08-07 | $0.25 | $2.00 | $0.025 | – | $0.125 | $1.00 | 272K |
| Databricks | databricks/databricks-gpt-5-mini | $0.25 | $2.00 | $0.02499 | $0.25 | – | – | 272K |
| GitHub Copilot | github_copilot/gpt-5-mini | $0.25 | $2.00 | $0.025 | – | – | – | 128K |
| Oracle Cloud (OCI) | oci/openai.gpt-5-mini | $0.25 | $2.00 | – | – | – | – | 272K |
| Perplexity | perplexity/openai/gpt-5-mini | $0.25 | $2.00 | $0.025 | – | – | – | – |
| Replicate | replicate/openai/gpt-5-mini | $0.25 | $2.00 | – | – | – | – | – |
| Snowflake Cortex | snowflake/openai-gpt-5-mini | $0.30 | $1.20 | – | – | – | – | 1M |
| Azure OpenAIeu | azure/eu/gpt-5-mini | $0.275 | $2.20 | $0.0275 | – | $0.1375 | $1.10 | – |
| Azure OpenAIeu, snapshot 2025-08-07 | azure/eu/gpt-5-mini-2025-08-07 | $0.275 | $2.20 | $0.0275 | – | $0.1375 | $1.10 | 272K |
| Azure OpenAIus | azure/us/gpt-5-mini | $0.275 | $2.20 | $0.0275 | – | $0.1375 | $1.10 | – |
| Azure OpenAIus, snapshot 2025-08-07 | azure/us/gpt-5-mini-2025-08-07 | $0.275 | $2.20 | $0.0275 | – | $0.1375 | $1.10 | 272K |
Other GPT-5 Mini prices on OpenAI
| Priority input | $0.45 per 1M tokens |
| Priority output | $3.60 per 1M tokens |
| Flex input | $0.125 per 1M tokens |
| Flex output | $1.00 per 1M tokens |
| Web search | $10.00 per 1K searches |
What GPT-5 Mini costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $1.50 |
| Databricks | $1.50 |
| Azure OpenAI | $1.50 |
| GitHub Copilot | $1.50 |
| OpenAI batch | $0.75 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $2.90 |
| Databricks | $2.90 |
| Azure OpenAI | $2.90 |
| GitHub Copilot | $2.90 |
GPT-5 Mini features
Input: text, image. Output: text.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Reasoning
- Prompt caching
- Web search
Use GPT-5 Mini with LiteLLM
Call GPT-5 Mini through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="gpt-5-mini",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-5-mini
litellm_params:
model: gpt-5-mini
api_key: os.environ/OPENAI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-5-mini",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT-5 Mini FAQ
How much does GPT-5 Mini cost?
GPT-5 Mini costs $0.25 per 1M input tokens and $2.00 per 1M output tokens on OpenAI, with cache reads at $0.025 per 1M tokens. Batch requests cost $0.125 per 1M input tokens and $1.00 per 1M output tokens. Across 8 providers on LiteLLM, the input price ranges from $0.25 to $0.30.
What is the context window of GPT-5 Mini?
GPT-5 Mini has a 272,000-token context window and returns up to 128,000 tokens per response.
Which providers offer GPT-5 Mini?
GPT-5 Mini is available from 8 providers through LiteLLM: OpenAI, Azure OpenAI, Databricks, GitHub Copilot, Oracle Cloud (OCI), Perplexity, Replicate and Snowflake Cortex. The lowest price is on Databricks.
How do I call GPT-5 Mini with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gpt-5-mini", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT-5 Mini support?
GPT-5 Mini supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.
When did LiteLLM add GPT-5 Mini?
GPT-5 Mini was added to LiteLLM's model price file in August 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- developers.openai.com/api/docs/pricing
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
- www.databricks.com/product/pricing/proprietary-foundation-model-serving
- www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing
LiteLLM docs: OpenAI, Azure OpenAI, Databricks, GitHub Copilot, Oracle Cloud (OCI), Perplexity.
Provider pages: OpenAI, Azure OpenAI, Databricks, GitHub Copilot, Oracle Cloud (OCI), Perplexity, Replicate, Snowflake Cortex.
