LiteLLMLiteLLM/ MODELS

Vision Medium API Pricing

1 providervispark/vision-mediumCompare
Input / output
$4.21 / $12.63 per 1M tokens
Cache read
$0 / 1M
Context
1M tokens
Max output
64K tokens

As of November 21, 2026, Vision Medium costs $4.21 per 1M input tokens and $12.63 per 1M output tokens on Vispark, with cache reads at $0 per 1M tokens. It has a 1,000,000-token context window and returns up to 65,536 tokens per response.

Prices updated Checked

Vision Medium 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.

Vision Medium prices by provider in US dollars, token prices per 1M tokens, as of November 21, 2026. Source: LiteLLM model price file.
ProviderModel name in LiteLLMInputOutputCache readContext
Visparkvispark/vision-medium$4.21$12.63$01M

What Vision Medium costs in practice

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

Vispark$14.73

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

Vispark$44.63

Vision Medium cost calculator

At Vispark's price ($4.21 input, $12.63 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $105 a day, about $3,158 a month. Change the numbers for your workload, or compare it with other models.

Per request
$0.01052
Per day
$105
Per month (30 days)
$3,158

Vision Medium features

Input: text, image, audio, video. Output: text.

Use Vision Medium with LiteLLM

Call Vision Medium 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="vispark/vision-medium",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: vision-medium
    litellm_params:
      model: vispark/vision-medium
      # 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 $LITELLM_API_KEY" \
  -d '{
    "model": "vision-medium",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Vision Medium FAQ

How much does Vision Medium cost?

Vision Medium costs $4.21 per 1M input tokens and $12.63 per 1M output tokens on Vispark, with cache reads at $0 per 1M tokens.

What is the context window of Vision Medium?

Vision Medium has a 1,000,000-token context window and returns up to 65,536 tokens per response.

Which providers offer Vision Medium?

Vision Medium is available from Vispark through LiteLLM, using the model name vispark/vision-medium.

How do I call Vision Medium with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="vispark/vision-medium", 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 Vision Medium support?

Vision Medium supports function calling, parallel tool calls, structured output, image input, PDF input and reasoning.

When did LiteLLM add Vision Medium?

Vision Medium was added to LiteLLM's model price file on November 17, 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. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:

Provider pages: Vispark.