uttapen

Models that read images

Every model here accepts image input. If your documents are in Persian, resolution decides the outcome more than the model does: send a high-DPI scan and skip aggressive JPEG compression. Pair it with a model that also supports structured output and the fields come back as JSON instead of prose.

262 models in this category · prices in toman per 1M tokens

ModelCapabilitiesContextInput / 1MOutput / 1M≈ 1,000 words
Dots3-Note Preview (free)dots-studio/dots-3-note-preview:freeFree · shared capacityvisiontoolsreasoningjson512,000000
Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:freeFree · shared capacityvisiontoolsreasoningjson262,144000
Gemma 4 31B (free)google/gemma-4-31b-it:freeFree · shared capacityvisiontoolsreasoningjson262,144000
Lyria 3 Clip Previewgoogle/lyria-3-clip-previewvisionjson1,048,576000
Lyria 3 Pro Previewgoogle/lyria-3-pro-previewvisionjson1,048,576000
MiniMax M3 (free)minimax/minimax-m3:freeFree · shared capacityvisiontoolsreasoningjson1,048,576000
Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeFree · shared capacityvisiontoolsreasoningaudio256,000000
Nemotron 3.5 Content Safety (free)nvidia/nemotron-3.5-content-safety:freeFree · shared capacityvisionreasoning128,000000
Free Models Routeropenrouter/freeFree · shared capacityvisiontoolsreasoningjson200,000000
Inkling Small (free)thinkingmachines/inkling-small:freeFree · shared capacityvisiontoolsreasoningaudio1,048,576000
Inkling (free)thinkingmachines/inkling:freeFree · shared capacityvisiontoolsreasoningaudio1,048,576000
Nex-N2-Mininex-agi/nex-n2-minivisiontoolsreasoningjson262,1447,25329,01347
Gemma 3 4Bgoogle/gemma-3-4b-itvisionjson131,07214,50629,01357
Qwen3.7 Flashqwen/qwen3.7-flashvisiontoolsreasoningjson1,000,0008,70437,71660
Gemma 3 12Bgoogle/gemma-3-12b-itvisiontoolsjson131,07214,50643,51975
Ministral 3 3B 2512mistralai/ministral-3b-2512visiontoolsjson131,07229,01329,01375
Reka Edgerekaai/reka-edgevisiontoolsjson16,38429,01329,01375
GPT-5 Nano (batch)openai/gpt-5-nano:batchvisiontoolsreasoningjson400,0007,25358,02585
Gemini 2.5 Flash Lite (batch)google/gemini-2.5-flash-lite:batchvisiontoolsreasoningjson1,048,57614,50658,02594
GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batchvisiontoolsjsonfiles1,047,57614,50658,02594
Qwen3.5-9Bqwen/qwen3.5-9bvisiontoolsreasoningjson262,14429,01343,51994
Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instructvisiontoolsjson131,07221,75958,025104
Nova Lite 1.0amazon/nova-lite-v1visiontools300,00017,40869,630113
UI-TARS 7B bytedance/ui-tars-1.5-7bvisionjson128,00029,01358,025113
Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributorvisiontoolsreasoningjson1,048,57629,01358,025113
Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributorvisiontoolsreasoningjson1,048,57629,01358,025113
Ministral 3 8B 2512mistralai/ministral-8b-2512visiontoolsjson262,14443,51943,519113
GLM Flash Latest~z-ai/glm-flash-latestvisiontoolsreasoningjson1,310,72020,67168,905116
Qwen3.5-Flashqwen/qwen3.5-flash-02-23visiontoolsreasoningjson1,000,00018,85875,433123
GLM 5.3 Flashz-ai/glm-5.3-flashvisiontoolsreasoningjson1,310,72021,75972,531123
Llama Guard 4 12Bmeta-llama/llama-guard-4-12bvisionjson163,84052,22352,223136
Seed 1.6 Flashbytedance-seed/seed-1.6-flashvisiontoolsreasoningjson262,14421,75987,038141
GPT-4o-mini (batch)openai/gpt-4o-mini:batchvisiontoolsjsonfiles128,00021,75987,038141
Llama 4 Scoutmeta-llama/llama-4-scoutvisiontoolsjson1,310,72029,01387,038151
Ministral 3 14B 2512mistralai/ministral-14b-2512visiontoolsjson262,14458,02558,025151
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safetyvisionreasoningjson131,07258,02558,025151
Gemma 4 26B A4B google/gemma-4-26b-a4b-itvisiontoolsreasoningjson262,14420,30998,643155
Qwen3.5-9B (batch)qwen/qwen3.5-9b:batchvisiontoolsreasoningjson262,14449,32172,531158
MiMo-V2.5xiaomi/mimo-v2.5visiontoolsreasoningjson1,050,00040,61881,235158
Gemma 4 31Bgoogle/gemma-4-31b-itvisiontoolsreasoningjson262,14426,11198,643162
GPT-5 Nanoopenai/gpt-5-nanovisiontoolsreasoningjson400,00014,506116,050170
Seed-2.0-Minibytedance-seed/seed-2.0-minivisiontoolsreasoningjson262,14429,013116,050189
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-litevisiontoolsreasoningjson1,048,57629,013116,050189
GPT-4.1 Nanoopenai/gpt-4.1-nanovisiontoolsjsonfiles1,047,57629,013116,050189
Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instructvisiontoolsjson131,07230,173120,692196
Gemma 3 27Bgoogle/gemma-3-27b-itvisiontoolsjson131,07223,210130,556200
Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instructvisiontoolsjson262,14433,945132,007216
Qwen3.8 Flashqwen/qwen3.8-flashvisiontoolsreasoningjson1,000,00043,519136,359234
GLM 5.3 Flash (batch)z-ai/glm-5.3-flash:batchvisiontoolsreasoningjson1,048,57543,519145,063245
GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batchvisiontoolsreasoningjson1,050,00029,013174,075264
GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batchvisiontoolsreasoningjson1,050,00029,013174,075264
GPT-5.4 Nano (batch)openai/gpt-5.4-nano:batchvisiontoolsreasoningjson400,00029,013181,328273
Mistral Small 4mistralai/mistral-small-2603visiontoolsreasoningjson262,14443,519174,075283
GPT-4o-miniopenai/gpt-4o-minivisiontoolsjsonfiles128,00043,519174,075283
GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18visiontoolsjsonfiles128,00043,519174,075283
Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instructvisiontoolsjson262,14443,519174,075283
Gemini 3.1 Flash Lite (batch)google/gemini-3.1-flash-lite:batchvisiontoolsreasoningjson1,048,57636,266217,594330
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-expvisiontoolsreasoningjson1,048,57663,828191,483332
Llama 4 Maverickmeta-llama/llama-4-maverickvisiontoolsjson1,048,57658,025201,927338
Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instructvision128,000101,834161,019342
GPT-4.1 Mini (batch)openai/gpt-4.1-mini:batchvisiontoolsjsonfiles1,047,57658,025232,100377
Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bvisiontoolsreasoningjson262,14429,013261,113377
GPT-5 Mini (batch)openai/gpt-5-mini:batchvisiontoolsreasoningjson400,00036,266290,125424
GLM 4.6Vz-ai/glm-4.6vvisiontoolsreasoningjson131,07287,038261,113453
Nex-N2-Pronex-agi/nex-n2-provisiontoolsreasoning262,14472,531290,125471
MiniMax-01minimax/minimax-01vision1,000,19258,025319,138490
Qwen3.6 Flashqwen/qwen3.6-flashvisiontoolsreasoningjson1,000,00054,398326,391495
Step 3.7 Flashstepfun/step-3.7-flashvisiontoolsreasoningjson262,14458,025333,644509
Gemma 4 31B (batch)google/gemma-4-31b-it:batchvisiontoolsreasoningjson262,144113,149281,421513
Gemini 2.5 Flash (batch)google/gemini-2.5-flash:batchvisiontoolsreasoningjson1,048,57643,519362,656528
Gemini 3.5 Flash Lite (batch)google/gemini-3.5-flash-lite:batchvisiontoolsreasoningjson1,048,57643,519362,656528
Muse Glimmer 30Bmeta/muse-glimmer-30bvisiontoolsreasoningjson131,07287,038319,138528
GPT-5.6 Lunaopenai/gpt-5.6-lunavisiontoolsreasoningjson1,050,00058,025348,150528
GPT-5.6 Luna Proopenai/gpt-5.6-luna-provisiontoolsreasoningjson1,050,00058,025348,150528
GPT-5.4 Nanoopenai/gpt-5.4-nanovisiontoolsreasoningjson400,00058,025362,656547
Claude 3 Haikuanthropic/claude-3-haikuvisiontools200,00072,531362,656566
MiniMax M3minimax/minimax-m3visiontoolsreasoningjson1,048,57687,038348,150566
MiniMax M3 (batch)minimax/minimax-m3:batchvisiontoolsreasoningjson524,28887,038348,150566
Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3bvisiontoolsreasoningjson262,14490,664362,656589
Qwen3.7 Plusqwen/qwen3.7-plusvisiontoolsreasoningjson1,000,00092,840371,360603
Perceptron Mk1perceptron/perceptron-mk1visionreasoningjson32,76843,519435,188622
Inkling Smallthinkingmachines/inkling-smallvisiontoolsreasoningaudio1,048,576130,556348,150622
ERNIE 4.5 VL 424B A47B baidu/ernie-4.5-vl-424b-a47bvisionreasoning123,000121,853362,656630
Inkling Small (batch)thinkingmachines/inkling-small:batchvisiontoolsreasoningaudio524,288145,063348,150641
Gemini 3 Flash Preview (batch)google/gemini-3-flash-preview:batchvisiontoolsreasoningjson1,048,57672,531435,188660
Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-litevisiontoolsreasoningjson1,048,57672,531435,188660
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google/gemini-3.1-flash-lite-imagevisionreasoningjsonimage out65,53672,531435,188660
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-previewvisiontoolsreasoningjson1,048,57672,531435,188660
Qwen3.5-27Bqwen/qwen3.5-27bvisiontoolsreasoningjson262,14456,574452,595662
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instructvisionjson128,000232,100290,125679
Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15visiontoolsreasoningjson1,000,00075,433452,595686
Muse Glimmer 30B (batch)meta/muse-glimmer-30b:batchvisiontoolsreasoningjson131,072101,544435,188698
Mistral Large 3 2512mistralai/mistral-large-2512visiontoolsjsonfiles262,144145,063435,188754
GPT-4.1 Miniopenai/gpt-4.1-minivisiontoolsjsonfiles1,047,576116,050464,200754
Sonarperplexity/sonarvision127,072290,125290,125754
Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420visiontoolsreasoningjson1,000,00087,038522,225792
Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instructvisiontoolsjson262,14460,926551,238796
Seed 1.6bytedance-seed/seed-1.6visiontoolsreasoningjson262,14472,531580,250849
Seed-2.0-Litebytedance-seed/seed-2.0-litevisiontoolsreasoningjson262,14472,531580,250849
Gemini 3.6 Flash (batch)google/gemini-3.6-flash:batchvisiontoolsreasoningjson1,048,576108,797543,984849
Gemini 3.7 Flash (batch)google/gemini-3.7-flash:batchvisiontoolsreasoningjson1,048,576108,797543,984849
Gemini 3.8 Flash (batch)google/gemini-3.8-flash:batchvisiontoolsreasoningjson1,048,576108,797543,984849
GPT-5 Miniopenai/gpt-5-minivisiontoolsreasoningjson400,00072,531580,250849
GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-minivisiontoolsreasoningjson400,00072,531580,250849
Qwen3.6 Plusqwen/qwen3.6-plusvisiontoolsreasoningjson1,000,00094,291565,744858
Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinkingvisiontoolsreasoningjson131,07252,223609,263860
Qwen3.6 27Bqwen/qwen3.6-27bvisiontoolsreasoningjson262,14487,038580,250867
Mistral Medium 3mistralai/mistral-medium-3visiontoolsjsonfiles131,072116,050580,250905
Mistral Medium 3.1mistralai/mistral-medium-3.1visiontoolsjsonfiles131,072116,050580,250905
GLM 4.5Vz-ai/glm-4.5vvisiontoolsreasoningjson65,536174,075522,225905
Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinkingvisiontoolsreasoningjson262,14458,025696,300981
GPT-5.4 Mini (batch)openai/gpt-5.4-mini:batchvisiontoolsreasoningjson400,000108,797652,781990
Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10bvisiontoolsreasoningjson262,14484,136696,3001,015
Kimi K2.5moonshotai/kimi-k2.5visiontoolsreasoningjson262,144130,556652,7811,018
Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17bvisiontoolsreasoningjson262,144113,149678,8931,030
o4 Mini (batch)openai/o4-mini:batchvisiontoolsreasoningjson200,000159,569638,2751,037
Nova 2 Liteamazon/nova-2-lite-v1visiontoolsreasoningfiles1,000,00087,038725,3131,056
Gemini 2.5 Flashgoogle/gemini-2.5-flashvisiontoolsreasoningjson1,048,57687,038725,3131,056
Nano Banana (Gemini 2.5 Flash Image)google/gemini-2.5-flash-imagevisionreasoningjsonimage out32,76887,038725,3131,056
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-litevisiontoolsreasoningjson1,048,57687,038725,3131,056

Showing the first 120. For finer filters see the full catalogue .

Other categories

See this category ranked by real usage →