LiteLLMModels

GPT-5.6 Cyber API Pricing

As of October 10, 2026, GPT-5.6 Cyber costs $12.50 per 1M input tokens and $75.00 per 1M output tokens on OpenAI, with cache reads at $1.25 and cache writes at $15.63 per 1M tokens. Across 2 providers on LiteLLM, the input price ranges from $12.50 to $13.75. It has a 400,000-token context window and returns up to 128,000 tokens per response.

By OpenAIModel ID gpt-5.6-cyberPrices updated Checked
Input
$12.50 / 1M tokens
Output
$75.00 / 1M tokens
Cache read
$1.25 / 1M tokens
Context window
400,000 tokens
Max output
128,000 tokens
Providers
2
Added to LiteLLM
August 20, 2026

GPT-5.6 Cyber pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readCache writeContext
OpenAIgpt-5.6-cyber$12.50$75.00$1.25$15.63400K
Amazon Bedrock Mantlebedrock_mantle/openai.gpt-5.6-cyber$13.75$82.50$1.375$17.19272K

Other GPT-5.6 Cyber prices on OpenAI

Input above 272K tokens$25.00 per 1M tokens
Output above 272K tokens$112.50 per 1M tokens
Cache read above 272K tokens$2.50 per 1M tokens

What GPT-5.6 Cyber costs in practice

1,000 requests with 2,000 input and 500 output tokens each

OpenAI$62.50
Amazon Bedrock Mantle$68.75

100 long-document requests with 100,000 input and 2,000 output tokens each

OpenAI$140.00
Amazon Bedrock Mantle$154.00

GPT-5.6 Cyber features

Input: text, image. Output: text.

Use GPT-5.6 Cyber with LiteLLM

Call GPT-5.6 Cyber 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.

Python SDK
from litellm import completion

response = completion(
    model="gpt-5.6-cyber",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: gpt-5.6-cyber
    litellm_params:
      model: gpt-5.6-cyber
      api_key: os.environ/OPENAI_API_KEY
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "gpt-5.6-cyber",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GPT-5.6 Cyber FAQ

How much does GPT-5.6 Cyber cost?

GPT-5.6 Cyber costs $12.50 per 1M input tokens and $75.00 per 1M output tokens on OpenAI, with cache reads at $1.25 and cache writes at $15.63 per 1M tokens. Above 272K input tokens, input costs $25.00 and output costs $112.50 per 1M tokens. Across 2 providers on LiteLLM, the input price ranges from $12.50 to $13.75.

What is the context window of GPT-5.6 Cyber?

GPT-5.6 Cyber has a 400,000-token context window and returns up to 128,000 tokens per response.

Which providers offer GPT-5.6 Cyber?

GPT-5.6 Cyber is available from 2 providers through LiteLLM: OpenAI and Amazon Bedrock Mantle. The lowest price is on OpenAI.

How do I call GPT-5.6 Cyber with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-5.6-cyber", 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-5.6 Cyber support?

GPT-5.6 Cyber supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching, web search and computer use.

When did LiteLLM add GPT-5.6 Cyber?

GPT-5.6 Cyber 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:

LiteLLM docs: OpenAI, Amazon Bedrock Mantle.

Provider pages: OpenAI, Amazon Bedrock Mantle.