Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
LLM Gateway logo

Model details

Qwen3 VL 30B A3B Instruct (DeepInfra)

We couldn't load the overview just now. Please try again in a little while.

LLM Gatewaydeepinfra/qwen3-vl-30b-a3b-instruct

Quick Info

Powered by
Provider
LLM Gateway
Model key
deepinfra/qwen3-vl-30b-a3b-instruct
Release date
Oct 5, 2025
Last updated
Oct 5, 2025
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$0.15
Output token cost
$0.60

Limits

Output tokens
32,768 tokens
Context window
262,144 tokens

Latest news about Qwen3 VL 30B A3B Instruct (DeepInfra)

LLM Gateway

CoverageBenchmark

The OpenOCR benchmark page reports reproducible OCR results for the DeepInfra-hosted variant "Qwen3-VL 30B A3B Instruct", explicitly referencing the provider offering "deepinfra-qwen-qwen3-vl-30b-a3b-instruct". It scores an average of 98.3% across 11 documents on a normalized corpus, with an average latency of 4.5s, an Scores are recomputed when the page is rendered and claims 11/11 reproducible results measured on 2026-08-22, including perfect 100% character LCS similarity on grocery and café receipts as well as handwritten letter and notes samples. While this is a useful, narrow OCR capability signal for the DeepInfra variant, it i

Videos about Qwen3 VL 30B A3B Instruct (DeepInfra)