Best for Vision & Documents

All models2292Chat & Knowledge558Coding381Agents & Tool Use541Writing & Language360Vision & Documents395Image Generation & Editing183Video Generation148Speech & Voice358Embeddings & Retrieval671Decision models118Music & Sound29
ModelVideo-MME 2 · No subtitlesPer taskPriceSpeedSupportsContext
Gemini 3 Flash PreviewGoogle
32.9unstated
—$0.50 / $3—1M
MiMo v2 OmniXiaomi
29.9unstated
—$0.14 / $0.28—262K
Kimi K2.5Moonshot AIOpen
27.3unstated
—$0.60 / $3—256K
GPT-5OpenAI
26.4unstated
—$1.25 / $10—400K
Gemma 4 31BGoogleOpen
19unstated
—$0.10 / $0.34—256K
OInternVL3 5 241B A28B InstructOpenGVLabOpen
15.8
——41K
Qwen2.5 VL 72B InstructAlibaba (Qwen)Open
13.7unstated
—$2.80 / $8.40—131K
OInternVL3 5 30B A3B InstructOpenGVLabOpen
12.6
——41K
Qwen3 VL 8B InstructAlibaba (Qwen)Open
12.4unstated
—$0.18 / $0.69—256K
MiMo VL 7B RL 2508XiaomiOpen
11.9
——128K
Qwen3 VL 4B InstructAlibaba (Qwen)Open
11.6unstated
—$0.10 / $0.60—256K
OInternVL3 5 8B InstructOpenGVLabOpen
11.4
——41K
MiMo VL 7B SFT 2508XiaomiOpen
10.7
——128K
OInternVL3 5 4B InstructOpenGVLabOpen
9.9
——41K
KKeye VL 1 5 8BKwai-KeyeOpen
8.9
——131K
Qwen3 VL 30B A3B InstructAlibaba (Qwen)Open
7.8unstated
—$0.15 / $0.50—256K