Chat API Pricing
As of October 10, 2026, Chat costs $5.00 per 1M input tokens and $30.00 per 1M output tokens on OpenAI, with cache reads at $0.50 per 1M tokens. Across 3 providers on LiteLLM, the input price ranges from $0 to $5.00. It has a 400,000-token context window and returns up to 128,000 tokens per response.
- Input
- $5.00 / 1M tokens
- Output
- $30.00 / 1M tokens
- Cache read
- $0.50 / 1M tokens
- Context window
- 400,000 tokens
- Max output
- 128,000 tokens
- Providers
- 3
- Added to LiteLLM
- August 20, 2026
Chat pricing by provider
3 listings across 3 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 | Context |
|---|---|---|---|---|---|
| OpenAIlatest alias | chat-latest | $5.00 | $30.00 | $0.50 | 400K |
| Azure OpenAIlatest alias | azure/chat-latest | $5.00 | $30.00 | $0.50 | 272K |
| Microsoft 365 Copilot | microsoft_365_copilot/chat | $0 | $0 | – | – |
What Chat costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $25.00 |
| Microsoft 365 Copilot | $0 |
| Azure OpenAI | $25.00 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $56.00 |
| Microsoft 365 Copilot | $0 |
| Azure OpenAI | $56.00 |
Chat features
Input: text, image. Output: text.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Reasoning
- Prompt caching
- Web search
Use Chat with LiteLLM
Call Chat 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="chat-latest",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: chat
litellm_params:
model: chat-latest
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": "chat",
"messages": [{"role": "user", "content": "Hello!"}]
}'Chat FAQ
How much does Chat cost?
Chat costs $5.00 per 1M input tokens and $30.00 per 1M output tokens on OpenAI, with cache reads at $0.50 per 1M tokens. Across 3 providers on LiteLLM, the input price ranges from $0 to $5.00.
What is the context window of Chat?
Chat has a 400,000-token context window and returns up to 128,000 tokens per response.
Which providers offer Chat?
Chat is available from 3 providers through LiteLLM: OpenAI, Azure OpenAI and Microsoft 365 Copilot. The lowest price is on Microsoft 365 Copilot.
How do I call Chat with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="chat-latest", 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 Chat support?
Chat supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.
When did LiteLLM add Chat?
Chat was added to LiteLLM's model price file on August 20, 2026.
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
- azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/
LiteLLM docs: OpenAI, Azure OpenAI, Microsoft 365 Copilot.
Provider pages: OpenAI, Azure OpenAI, Microsoft 365 Copilot.
