LiteLLMModels

Agnes 2.5 Pro API Pricing

As of October 10, 2026, Agnes 2.5 Pro costs $0.45 per 1M input tokens and $0.90 per 1M output tokens on AIHubMix, with cache reads at $0.00378 per 1M tokens. It has a 1,000,000-token context window and returns up to 65,536 tokens per response.

Model ID aihubmix/agnes-2.5-proPrices updated Checked
Input
$0.45 / 1M tokens
Output
$0.90 / 1M tokens
Cache read
$0.00378 / 1M tokens
Context window
1,000,000 tokens
Max output
65,536 tokens
Providers
1
Added to LiteLLM
September 16, 2026

Agnes 2.5 Pro pricing by provider

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

ProviderModel name in LiteLLMInputOutputCache readContext
AIHubMixaihubmix/agnes-2.5-pro$0.45$0.90$0.003781M

What Agnes 2.5 Pro costs in practice

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

AIHubMix$1.35

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

AIHubMix$4.68

Agnes 2.5 Pro features

Use Agnes 2.5 Pro with LiteLLM

Call Agnes 2.5 Pro 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="aihubmix/agnes-2.5-pro",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: agnes-2.5-pro
    litellm_params:
      model: aihubmix/agnes-2.5-pro
      # credentials: see the provider's LiteLLM docs page
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": "agnes-2.5-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Agnes 2.5 Pro FAQ

How much does Agnes 2.5 Pro cost?

Agnes 2.5 Pro costs $0.45 per 1M input tokens and $0.90 per 1M output tokens on AIHubMix, with cache reads at $0.00378 per 1M tokens.

What is the context window of Agnes 2.5 Pro?

Agnes 2.5 Pro has a 1,000,000-token context window and returns up to 65,536 tokens per response.

Which providers offer Agnes 2.5 Pro?

Agnes 2.5 Pro is available from AIHubMix through LiteLLM, using the model name aihubmix/agnes-2.5-pro.

How do I call Agnes 2.5 Pro with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="aihubmix/agnes-2.5-pro", 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 Agnes 2.5 Pro support?

Agnes 2.5 Pro supports image input, reasoning and prompt caching.

When did LiteLLM add Agnes 2.5 Pro?

Agnes 2.5 Pro was added to LiteLLM's model price file on September 16, 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: AIHubMix.

Provider pages: AIHubMix.