ModelMint

Zerogpu

llama-3.2-3b-instruct-fast

zerogpu/llama-3.2-3b-instruct-fast

What it would cost per month

  1. Support chatbot2,000 chats a day · no caching discount$8.70/mo
  2. Document Q&A1,000 questions a day · no caching discount$16.50/mo
  3. Coding agent300 agent steps a day · missing a required feature · no caching discount$17.55/mo
  4. Content writing200 drafts a day$2.85/mo
  5. Data extraction20,000 records a day · missing a required feature$18.60/mo

Typical workloads at list prices. Open one to adjust it to yours.

Pricing (per 1M tokens)

Input

$0.050

Output

$0.300

Cache Write

—

Cache Read

$0.025

Specs

Context Window131K (131,072 tokens)
Max Output Tokens8K (8,192 tokens)

Capabilities

Vision
Function Calling
Prompt Caching
Reasoning
Computer Use
Response Schema
PDF Input
← Back to directory