Vision

Models that take images as input. Listed by input price, cheapest first. The first 25 of 110.

ModelInputOutputContextServed by
Google: Gemma 4 26B A4B (free)$0.00 per M$0.00 per M262,144 tokensgoogle
Google: Gemma 4 31B (free)$0.00 per M$0.00 per M262,144 tokensgoogle
Google: Lyria 3 Clip Preview$0.00 per M$0.00 per M1,048,576 tokensgoogle
Google: Lyria 3 Pro Preview$0.00 per M$0.00 per M1,048,576 tokensgoogle
MiniMax: MiniMax M3 (free)$0.00 per M$0.00 per M1,048,576 tokensminimax
NVIDIA: Nemotron 3 Nano Omni (free)$0.00 per M$0.00 per M256,000 tokensnvidia
NVIDIA: Nemotron 3.5 Content Safety (free)$0.00 per M$0.00 per M128,000 tokensnvidia
nvidia/llama-nemotron-embed-vl-1b-v2$0.01 per M—10,240 tokensdeepinfra
PaddleOCR VL$0.02 per M$0.02 per M16,384 tokensnovita
DeepSeek OCR 2$0.03 per M$0.03 per M8,192 tokensnovita
Qwen: Qwen3.7 Flash$0.03 per M$0.13 per M1,000,000 tokensalibaba
Qwen: Qwen3.5-Flash$0.065 per M$0.26 per M1,000,000 tokensalibaba
Google: Gemma 4 26B A4B$0.07 per M$0.34 per M262,144 tokensgoogle
Ling 3.0 Flash VL$0.075 per M$0.22 per M262,144 tokensnovita
mistralai/Mistral-Small-3.2-24B-Instruct-2506$0.075 per M$0.20 per M128,000 tokensdeepinfra
Z.ai: GLM 5.3 Flash$0.075 per M$0.25 per M1,310,720 tokenszai
Z.ai: GLM Flash Latest$0.075 per M$0.25 per M1,310,720 tokenszai
google/gemma-4-31B-it-turbo$0.09 per M$0.34 per M262,144 tokensdeepinfra
Google: Gemma 4 31B$0.09 per M$0.34 per M262,144 tokensgoogle
meta-llama/Llama-4-Scout-17B-16E-Instruct$0.10 per M$0.30 per M327,680 tokensdeepinfra
Qwen: Qwen3.5-9B$0.10 per M$0.15 per M262,144 tokensalibaba
Qwen: Qwen3.6 35B A3B$0.10 per M$0.90 per M262,144 tokensalibaba
Mistral: Mistral Small 4$0.15 per M$0.60 per M262,144 tokensmistral
Qwen: Qwen3.8 Flash$0.15 per M$0.47 per M1,000,000 tokensalibaba
Qwen: Qwen3.6 Flash$0.1875 per M$1.125 per M1,000,000 tokensalibaba

Prices are the providers' list prices per million tokens, as of , on your own provider key with no fee on the tokens.