Vision Medium API Pricing
- 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.
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.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| Vispark | vispark/vision-medium | $4.21 | $12.63 | $0 | 1M |
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.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Reasoning
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.
from litellm import completion
response = completion(
model="vispark/vision-medium",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: vision-medium
litellm_params:
model: vispark/vision-medium
# credentials: see the provider's LiteLLM docs pagecurl 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.