Vision models
Models that accept image input. 159 of 338 catalog models match as of July 2026.
- 159
- Models
- $0.052
- Input from /1M
- 10M
- Max context
- Jun 30, 2026
- Newest release
Vision on OpenKey now covers 159 models across 52 labs, everything from image-in/text-out workhorses to models that generate images back out. The newest is Claude Sonnet 5 (2026-06-30), priced at $2/$10 per M input/output tokens with a 1M-token context window. At the other end, Gemma 4 26B A4B runs $0.06/$0.33 per M — and there's a free version too. Eight models in this category cost nothing, 151 are paid, and the spread between cheapest and priciest paid vision model is enormous, so picking by price band matters as much as picking by capability.
Top picks
Claude Opus 4.8
Ranks 1st on design_arena androidnative (elo 1343), the highest elo score in this category's benchmark data. At $5/$25 per M tokens ($5.15/$25.75 on OpenKey after the 3% fee) with a 1M context window, it's the strongest documented performer for UI-heavy vision work.
Nano Banana 2 (Gemini 3.1 Flash Image)
One of the few models here that outputs images as well as text (text+image->text+image), at $0.5/$3 per M ($0.515/$3.09 on OpenKey). Cheapest image-generating vision model in the set by a wide margin.
Qwen3.6 35B A3B
$0.14/$1.00 per M ($0.1442/$1.03 on OpenKey) with a 262,144-token context window — one of the lowest-cost paid options in the list for teams processing high image volume without a benchmark-topping requirement.
All 159 models
Full catalog →Claude Sonnet 5Anthropic1Mctx 1M · inout
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google66Kctx 66K · inout
Fugu UltraSakana AI1Mctx 1M · inout
Nano Banana Pro (Gemini 3 Pro Image)Google66Kctx 66K · inout
Nano Banana 2 (Gemini 3.1 Flash Image)Google131Kctx 131K · inout
Kimi K2.7 CodeMoonshot AI262Kctx 262K · inout
Claude Fable 5Anthropic1Mctx 1M · inout
Nex-N2-ProNex262Kctx 262K · inout
Nemotron 3.5 Content Safety (free)FreeNVIDIA128KFreeFreectx 128K · inFreeoutFree
Qwen3.7 PlusQwen1Mctx 1M · inout
MiniMax M3MiniMax1.0Mctx 1.0M · inout
Step 3.7 FlashStepFun256Kctx 256K · inout
Claude Opus 4.8Anthropic1Mctx 1M · inout
Claude Opus 4.8 (Fast)Anthropic1Mctx 1M · inout
Grok Build 0.1xAI256Kctx 256K · inout
Gemini 3.5 FlashGoogle1.0Mctx 1.0M · inout
Claude Opus 4.7 (Fast)Anthropic1Mctx 1M · inout
Perceptron Mk1Perceptron AI33Kctx 33K · inout
Gemini 3.1 Flash LiteGoogle1.0Mctx 1.0M · inout
GPT Chat LatestOpenAI400Kctx 400K · inout
Mistral Medium 3.5Mistral AI262Kctx 262K · inout
Grok 4.3xAI1Mctx 1M · inout
Nemotron 3 Nano Omni (free)FreeNVIDIA256KFreeFreectx 256K · inFreeoutFree
Qwen3.5 Plus 2026-04-20Qwen1Mctx 1M · inout
Qwen3.6 27BQwen262Kctx 262K · inout
Qwen3.6 35B A3BQwen262Kctx 262K · inout
Qwen3.6 FlashQwen1Mctx 1M · inout
GPT-5.5OpenAI1.1Mctx 1.1M · inout
GPT-5.5 ProOpenAI1.1Mctx 1.1M · inout
MiMo-V2.5Xiaomi1.0Mctx 1.0M · inout
GPT-5.4 Image 2OpenAI272Kctx 272K · inout
Kimi K2.6Moonshot AI262Kctx 262K · inout
Claude Opus 4.7Anthropic1Mctx 1M · inout
Gemma 4 26B A4B Google262Kctx 262K · inout
Gemma 4 26B A4B (free)FreeGoogle262KFreeFreectx 262K · inFreeoutFree
Gemma 4 31BGoogle262Kctx 262K · inout
Gemma 4 31B (free)FreeGoogle262KFreeFreectx 262K · inFreeoutFree
Qwen3.6 PlusQwen1Mctx 1M · inout
GLM 5V TurboZ.ai203Kctx 203K · inout
Grok 4.20xAI2Mctx 2M · inout
Grok 4.20 Multi-AgentxAI2Mctx 2M · inout
Lyria 3 Clip PreviewFreeGoogle1.0MFreeFreectx 1.0M · inFreeoutFree
Lyria 3 Pro PreviewFreeGoogle1.0MFreeFreectx 1.0M · inFreeoutFree
Reka EdgeReka16Kctx 16K · inout
GPT-5.4 MiniOpenAI400Kctx 400K · inout
GPT-5.4 NanoOpenAI400Kctx 400K · inout
Mistral Small 4Mistral AI262Kctx 262K · inout
Seed-2.0-LiteByteDance Seed262Kctx 262K · inout
Qwen3.5-9BQwen262Kctx 262K · inout
GPT-5.4OpenAI1.1Mctx 1.1M · inout
GPT-5.4 ProOpenAI1.1Mctx 1.1M · inout
Gemini 3.1 Flash Lite PreviewGoogle1.0Mctx 1.0M · inout
GPT-5.3 ChatOpenAI128Kctx 128K · inout
Seed-2.0-MiniByteDance Seed262Kctx 262K · inout
Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google131Kctx 131K · inout
Gemini 3.1 Pro Preview Custom ToolsGoogle1.0Mctx 1.0M · inout
Qwen3.5-122B-A10BQwen262Kctx 262K · inout
Qwen3.5-27BQwen262Kctx 262K · inout
Qwen3.5-35B-A3BQwen262Kctx 262K · inout
Qwen3.5-FlashQwen1Mctx 1M · inout
GPT-5.3-CodexOpenAI400Kctx 400K · inout
Gemini 3.1 Pro PreviewGoogle1.0Mctx 1.0M · inout
Claude Sonnet 4.6Anthropic1Mctx 1M · inout
Qwen3.5 397B A17BQwen256Kctx 256K · inout
Qwen3.5 Plus 2026-02-15Qwen1Mctx 1M · inout
Claude Opus 4.6Anthropic1Mctx 1M · inout
Free Models RouterFreeOpenRouter200KFreeFreectx 200K · inFreeoutFree
Kimi K2.5Moonshot AI262Kctx 262K · inout
GPT-5.2-CodexOpenAI400Kctx 400K · inout
Seed 1.6ByteDance Seed262Kctx 262K · inout
Seed 1.6 FlashByteDance Seed262Kctx 262K · inout
Gemini 3 Flash PreviewGoogle1.0Mctx 1.0M · inout
GPT-5.2OpenAI400Kctx 400K · inout
GPT-5.2 ChatOpenAI128Kctx 128K · inout
GPT-5.2 ProOpenAI400Kctx 400K · inout
GLM 4.6VZ.ai131Kctx 131K · inout
GPT-5.1-Codex-MaxOpenAI400Kctx 400K · inout
Nova 2 LiteAmazon1Mctx 1M · inout
Ministral 3 14B 2512Mistral AI262Kctx 262K · inout
Ministral 3 3B 2512Mistral AI131Kctx 131K · inout
Ministral 3 8B 2512Mistral AI262Kctx 262K · inout
Mistral Large 3 2512Mistral AI262Kctx 262K · inout
Claude Opus 4.5Anthropic200Kctx 200K · inout
Nano Banana Pro (Gemini 3 Pro Image Preview)Google66Kctx 66K · inout
GPT-5.1OpenAI400Kctx 400K · inout
GPT-5.1 ChatOpenAI128Kctx 128K · inout
GPT-5.1-CodexOpenAI400Kctx 400K · inout
GPT-5.1-Codex-MiniOpenAI400Kctx 400K · inout
Nova Premier 1.0Amazon1Mctx 1M · inout
Sonar Pro SearchPerplexity200Kctx 200K · inout
Nemotron Nano 12B 2 VL (free)FreeNVIDIA128KFreeFreectx 128K · inFreeoutFree
Qwen3 VL 32B InstructQwen262Kctx 262K · inout
GPT-5 Image MiniOpenAI400Kctx 400K · inout
Claude Haiku 4.5Anthropic200Kctx 200K · inout
GPT-5 ImageOpenAI400Kctx 400K · inout
Qwen3 VL 8B InstructQwen256Kctx 256K · inout
Qwen3 VL 8B ThinkingQwen256Kctx 256K · inout
o3 Deep ResearchOpenAI200Kctx 200K · inout
o4 Mini Deep ResearchOpenAI200Kctx 200K · inout
Nano Banana (Gemini 2.5 Flash Image)Google33Kctx 33K · inout
GPT-5 ProOpenAI400Kctx 400K · inout
Qwen3 VL 30B A3B InstructQwen262Kctx 262K · inout
Qwen3 VL 30B A3B ThinkingQwen131Kctx 131K · inout
Claude Sonnet 4.5Anthropic1Mctx 1M · inout
Gemini 2.5 Flash Lite Preview 09-2025Google1.0Mctx 1.0M · inout
GPT-5 CodexOpenAI400Kctx 400K · inout
Qwen3 VL 235B A22B InstructQwen262Kctx 262K · inout
Qwen3 VL 235B A22B ThinkingQwen131Kctx 131K · inout
Mistral Medium 3.1Mistral AI131Kctx 131K · inout
GLM 4.5VZ.ai66Kctx 66K · inout
GPT-5OpenAI400Kctx 400K · inout
GPT-5 ChatOpenAI128Kctx 128K · inout
GPT-5 MiniOpenAI400Kctx 400K · inout
GPT-5 NanoOpenAI400Kctx 400K · inout
Claude Opus 4.1Anthropic200Kctx 200K · inout
UI-TARS 7B ByteDance128Kctx 128K · inout
Gemini 2.5 Flash LiteGoogle1.0Mctx 1.0M · inout
ERNIE 4.5 VL 424B A47B Baidu131Kctx 131K · inout
Mistral Small 3.2 24BMistral AI128Kctx 128K · inout
Gemini 2.5 FlashGoogle1.0Mctx 1.0M · inout
Gemini 2.5 ProGoogle1.0Mctx 1.0M · inout
o3 ProOpenAI200Kctx 200K · inout
Gemini 2.5 Pro Preview 06-05Google1.0Mctx 1.0M · inout
Claude Opus 4Anthropic200Kctx 200K · inout
Claude Sonnet 4Anthropic1Mctx 1M · inout
Gemini 2.5 Pro Preview 05-06Google1.0Mctx 1.0M · inout
Mistral Medium 3Mistral AI131Kctx 131K · inout
Llama Guard 4 12BMeta AI164Kctx 164K · inout
o3OpenAI200Kctx 200K · inout
o4 MiniOpenAI200Kctx 200K · inout
o4 Mini HighOpenAI200Kctx 200K · inout
GPT-4.1OpenAI1.0Mctx 1.0M · inout
GPT-4.1 MiniOpenAI1.0Mctx 1.0M · inout
GPT-4.1 NanoOpenAI1.0Mctx 1.0M · inout
Llama 4 MaverickMeta AI1.0Mctx 1.0M · inout
Llama 4 ScoutMeta AI10Mctx 10M · inout
o1-proOpenAI200Kctx 200K · inout
Mistral Small 3.1 24BMistral AI128Kctx 128K · inout
Gemma 3 12BGoogle131Kctx 131K · inout
Gemma 3 4BGoogle131Kctx 131K · inout
Gemma 3 27BGoogle131Kctx 131K · inout
Sonar ProPerplexity200Kctx 200K · inout
Sonar Reasoning ProPerplexity128Kctx 128K · inout
Qwen2.5 VL 72B InstructQwen131Kctx 131K · inout
SonarPerplexity127Kctx 127K · inout
MiniMax-01MiniMax1.0Mctx 1.0M · inout
o1OpenAI200Kctx 200K · inout
Nova Lite 1.0Amazon300Kctx 300K · inout
Nova Pro 1.0Amazon300Kctx 300K · inout
GPT-4o (2024-11-20)OpenAI128Kctx 128K · inout
Llama 3.2 11B Vision InstructMeta AI131Kctx 131K · inout
GPT-4o (2024-08-06)OpenAI128Kctx 128K · inout
GPT-4o-miniOpenAI128Kctx 128K · inout
GPT-4o-mini (2024-07-18)OpenAI128Kctx 128K · inout
GPT-4oOpenAI128Kctx 128K · inout
GPT-4o (2024-05-13)OpenAI128Kctx 128K · inout
GPT-4 TurboOpenAI128Kctx 128K · inout
Claude 3 HaikuAnthropic200Kctx 200K · inout
Auto RouterOpenRouter2MVariableVariablectx 2M · inVariableoutVariable
Prices per 1M tokens, flat 3% fee included. Hover or tap a price for the math.
How to choose
First tradeoff: text-out vs image-out. Most models here (Claude Sonnet 5, Claude Opus 4.8, Grok 4.3) read images and answer in text; only a handful, like Nano Banana 2 and GPT-5.4 Image 2, generate images back. Don't pay for image-out capability you won't use. Second: context window varies from 32,768 tokens (Perceptron Mk1) up to 2,000,000 (Grok 4.20) — matters if you're feeding in long documents alongside images, not just single screenshots. Third: benchmark coverage is thin — only 84 of 159 models have design_arena scores attached, so for the other ~75, you're picking on price and modality alone, not proven ranking.
Questions
- What's the newest vision model on OpenKey?
- Claude Sonnet 5, released 2026-06-30. It reads text, images, and files, returns text, and runs a 1,000,000-token context window at $2/$10 per M input/output tokens ($2.06/$10.30 on OpenKey after the 3% fee).
- Are there free vision models?
- Yes — 8 of the 159 vision models are free, including Gemma 4 26B A4B (free), Gemma 4 31B (free), and Nemotron 3 Nano Omni (free). They're fully functional vision models, not trials, though free-tier availability can be rate-limited by the provider.
- Which vision models can generate images, not just read them?
- Nano Banana Pro, Nano Banana 2, Nano Banana 2 Lite (all Gemini-based), and GPT-5.4 Image 2 support text+image->text+image, meaning they can return generated or edited images. Most other vision models in this list only take image input and return text.