Models/Mistral AI/Mistral Tiny

Mistral Tiny

Mistral AI 🧠 Language Model

Mistral's smallest and fastest model, ideal for simple tasks, classification, and high-throughput applications.

Specifications

ModalitiesInput: text  ·  Output: text
Context window32K tokens
Max output8K tokens
Speed●●●●● Blazing
FeaturesTools: No Streaming: Yes Vision: No

Pricing

$0.175 / 1M input tokens  ·  $0.525 / 1M output tokens

Platform credit pricing — live rates on the Models page.

Use Mistral Tiny on Zubnet →

More from Mistral AI

M
Mistral Large 3
Open-weight flagship. 675B MoE (41B active), multimodal with vision. Apache 2.0 licensed.
🧠 Language Model
M
Mistral Small
Fast and efficient model for simple tasks. Great balance of performance and cost.
🧠 Language Model
C
Codestral
Specialized model for code generation, completion, and understanding.
🧠 Language Model
M
Magistral Medium
Advanced reasoning model for complex multi-step logic and problem-solving.
🧠 Language Model