Models/Sarvam AI/Sarvam Vision

Sarvam Vision

Sarvam AI 🧠 Language Model

Sarvam's 3B multimodal vision model, parses documents, extracts text, and understands visual content in 23 languages. Designed for India's diverse document formats.

Specifications

ModalitiesInput: text, image  ·  Output: text
Speed●●●●○ Fast
FeaturesTools: No Streaming: No Vision: No
Capabilitiesvision

Pricing

$0.0297 / generation

Platform credit pricing — live rates on the Models page.

Use Sarvam Vision on Zubnet →

More from Sarvam AI

S
Sarvam 30B
Sarvam's 24B multilingual LLM, fluent in all 22 official Indian languages + English. OpenAI-compatible API. Free tier with no per-token charges. Supports wiki grounding, reasoning
🧠 Language Model
S
Sarvam Translate v1
High-quality machine translation across 22 Indian languages and English. Handles complex sentence structures and idiomatic expressions with cultural context awareness.
🧠 Language Model
S
Sarvam 105B
Sarvam's 24B multilingual LLM, fluent in all 22 official Indian languages + English. OpenAI-compatible API. Free tier with no per-token charges. Supports wiki grounding, reasoning
🧠 Language Model
M
Mayura v1
Sarvam's multilingual translation model, translates between English and 22 Indian languages with high accuracy. Named after the Indian peacock.
🧠 Language Model