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.

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

ModelCapabilitiesContextInput / 1MOutput / 1M≈ 1,000 words
Dots3-Note Previewdots-studio/dots-3-note-preview:freeFree · shared capacityImage inputTool callingReasoningJSON output512,000000
Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it:freeFree · shared capacityImage inputTool callingReasoningJSON output262,144000
Gemma 4 31Bgoogle/gemma-4-31b-it:freeFree · shared capacityImage inputTool callingReasoningJSON output262,144000
Lyria 3 Clip Previewgoogle/lyria-3-clip-previewImage inputJSON output1,048,576000
Lyria 3 Pro Previewgoogle/lyria-3-pro-previewImage inputJSON output1,048,576000
Nemotron 3 Nano Omninvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeFree · shared capacityImage inputTool callingReasoningAudio input256,000000
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety:freeFree · shared capacityImage inputReasoning128,000000
Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl:freeFree · shared capacityImage inputTool callingReasoningJSON output1,000,000000
Crouton Alphastealth/crouton-alphaImage inputTool callingReasoningJSON output1,048,576000
Extractscaledown/extractImage inputFile input1,000,00013,849018
Summarizescaledown/summarizeImage inputFile input1,000,00013,849018
GLM FlashLatest~z-ai/glm-flash-latestImage inputTool callingReasoningJSON output1,048,5769,86731,95654
Nex-N2.5-Mininex-agi/nex-n2.5-miniImage inputReasoningJSON output262,1448,65534,62256
Gemma 3 4Bgoogle/gemma-3-4b-itImage inputJSON output131,07217,31134,62268
Qwen3.7 Flashqwen/qwen3.7-flashImage inputTool callingReasoningJSON output1,000,00010,38745,00972
Gemma 3 12Bgoogle/gemma-3-12b-itImage inputTool callingJSON output131,07217,31151,93390
Ministral 3 3B 2512mistralai/ministral-3b-2512Image inputTool callingJSON output131,07234,62234,62290
Reka Edgerekaai/reka-edgeImage inputTool callingJSON output16,38434,62234,62290
Ternary Bonsai 2 9Bprism-ml/ternary-bonsai-2-9bImage inputTool callingReasoningJSON output262,14427,69845,00995
GPT-5 NanoBatchopenai/gpt-5-nano:batchImage inputTool callingReasoningJSON output400,0008,65569,244101
GLM 5.3 FlashBatchz-ai/glm-5.3-flash:batchImage inputTool callingReasoningJSON output1,048,57617,31162,319104
Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vlImage inputTool callingReasoningJSON output131,07220,77362,319108
Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-itImage inputTool callingReasoningJSON output262,14423,19769,244120
Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instructImage inputTool callingJSON output256,00025,96669,244124
Nova Lite 1.0amazon/nova-lite-v1Image inputTool calling300,00020,77383,093135
Claude Haiku 5.5Batchanthropic/claude-haiku-5.5:batchImage inputTool callingReasoningJSON output1,000,00017,31186,555135
UI-TARS 7Bbytedance/ui-tars-1.5-7bImage inputJSON output128,00034,62269,244135
Ministral 3 8B 2512mistralai/ministral-8b-2512Image inputTool callingJSON output262,14451,93351,933135
GPT-6 Luna ProBatchopenai/gpt-6-luna-pro:batchImage inputTool callingReasoningJSON output1,050,00017,31186,555135
GPT-6 LunaBatchopenai/gpt-6-luna:batchImage inputTool callingReasoningJSON output1,050,00017,31186,555135
Nex-N2.5-Pronex-agi/nex-n2.5-proImage inputTool callingReasoningJSON output262,14425,96686,555146
Qwen3.5-Flashqwen/qwen3.5-flash-02-23Image inputTool callingReasoningJSON output1,000,00022,50490,017146
Llama Guard 4 12Bmeta-llama/llama-guard-4-12bImage input163,84062,31962,319162
Seed 1.6 Flashbytedance-seed/seed-1.6-flashImage inputTool callingReasoningJSON output262,14425,966103,866169
Llama 4 Scoutmeta-llama/llama-4-scoutImage inputTool callingJSON output327,68034,622103,866180
Ministral 3 14B 2512mistralai/ministral-14b-2512Image inputTool callingJSON output262,14469,24469,244180
Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safetyImage inputReasoning131,07269,24469,244180
Qwen3.5-9Bqwen/qwen3.5-9bImage inputTool callingReasoningJSON output262,14458,85786,555189
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flashImage inputTool callingReasoningJSON output1,050,00048,47196,941189
Gemma 3 27Bgoogle/gemma-3-27b-itImage inputTool callingJSON output131,07227,698121,177194
DeepSeek V4.1 FlashBatchdeepseek/deepseek-v4.1-flash:batchImage inputTool callingReasoningJSON output1,048,57638,777116,330202
GPT-5 Nanoopenai/gpt-5-nanoImage inputTool callingReasoningJSON output400,00017,311138,488203
Seed-2.0-Minibytedance-seed/seed-2.0-miniImage inputTool callingReasoningJSON output262,14434,622138,488225
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-liteImage inputTool callingReasoningJSON output1,048,57634,622138,488225
GPT-4.1 Nanoopenai/gpt-4.1-nanoImage inputTool callingJSON outputFile input1,047,57634,622138,488225
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017Image inputTool callingReasoningJSON output1,048,5762,077173,110228
DeepSeek FlashLatest~deepseek/deepseek-flash-latestImage inputTool callingReasoningJSON output1,048,5762,077173,110228
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashImage inputTool callingReasoningJSON output1,048,57615,580173,110245
Particle-1particle-ai/particle-1Image inputTool callingReasoningJSON output1,048,57617,311173,110248
Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27bImage inputTool callingReasoningJSON output262,14425,966173,110259
Claude Haiku 5.5anthropic/claude-haiku-5.5Image inputTool callingReasoningJSON output1,000,00034,622173,110270
Gemma 4 31Bgoogle/gemma-4-31b-itImage inputTool callingReasoningJSON output262,14469,244138,488270
GPT-6 Lunaopenai/gpt-6-lunaImage inputTool callingReasoningJSON output1,050,00034,622173,110270
GPT-6 Luna Proopenai/gpt-6-luna-proImage inputTool callingReasoningJSON output1,050,00034,622173,110270
Claude HaikuLatest~anthropic/claude-haiku-latestImage inputTool callingReasoningJSON output1,000,00034,622173,110270
GPT LunaLatest~openai/gpt-luna-latestImage inputTool callingReasoningJSON output1,050,00034,622173,110270
Qwen3.8 Flashqwen/qwen3.8-flashImage inputTool callingReasoningJSON output1,000,00051,933162,723279
Qwen3.8 Omni Flashqwen/qwen3.8-omni-flashImage inputTool callingReasoningJSON output1,000,00051,933162,723279
Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vlImage inputTool callingReasoningJSON output1,048,57651,933173,110293
GLM 5.3 Flashz-ai/glm-5.3-flashImage inputTool callingReasoningJSON output1,048,57651,933173,110293
GPT-5.6 Luna ProBatchopenai/gpt-5.6-luna-pro:batchImage inputTool callingReasoningJSON output1,050,00034,622207,732315
GPT-5.6 LunaBatchopenai/gpt-5.6-luna:batchImage inputTool callingReasoningJSON output1,050,00034,622207,732315
MiniMax M3.1 Flashminimax/minimax-m3.1-flashImage inputTool callingReasoningJSON output1,048,57651,933207,732338
Mistral Small 4mistralai/mistral-small-2603Image inputTool callingReasoningJSON output262,14451,933207,732338
GPT-4o-miniopenai/gpt-4o-miniImage inputTool callingJSON outputFile input128,00051,933207,732338
GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18Image inputTool callingJSON outputFile input128,00051,933207,732338
Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instructImage inputTool callingJSON output262,14451,933207,732338
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-expImage inputTool callingReasoningJSON output1,048,57674,645223,935388
Gemini 3.1 Flash LiteBatchgoogle/gemini-3.1-flash-lite:batchImage inputTool callingReasoningJSON output1,048,57643,277259,665394
Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instructImage inputTool callingJSON output128,000121,523192,152408
Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instructImage inputTool callingJSON output262,14486,555259,665450
Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bImage inputTool callingReasoningJSON output262,14434,622311,597450
Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3bImage inputTool callingReasoningJSON output262,14448,471346,219513
Qwen3.7 PlusBatchqwen/qwen3.7-plus:batchImage inputTool callingReasoningJSON output262,14479,630318,522518
GLM 4.6Vz-ai/glm-4.6vImage inputTool callingReasoningJSON output131,072103,866311,597540
Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinkingImage inputTool callingReasoningJSON output262,144100,404346,219581
MiniMax-01minimax/minimax-01Image input1,000,19269,244380,841585
MiMo-V2.6-Proxiaomi/mimo-v2.6-proImage inputTool callingReasoningJSON output1,050,000150,605301,211587
Qwen3.6 Flashqwen/qwen3.6-flashImage inputTool callingReasoningJSON output1,000,00064,916389,497591
Llama 4 Maverickmeta-llama/llama-4-maverickImage inputTool callingJSON output524,288121,177346,219608
Step 3.7 Flashstepfun/step-3.7-flashImage inputTool callingReasoningJSON output262,14469,244398,152608
Gemini 3.5 Flash LiteBatchgoogle/gemini-3.5-flash-lite:batchImage inputTool callingReasoningJSON output1,048,57651,933432,774630
GPT-5.6 Lunaopenai/gpt-5.6-lunaImage inputTool callingReasoningJSON output1,050,00069,244415,463630
GPT-5.6 Luna Proopenai/gpt-5.6-luna-proImage inputTool callingReasoningJSON output1,050,00069,244415,463630
GPT-5.4 Nanoopenai/gpt-5.4-nanoImage inputTool callingReasoningJSON output400,00069,244432,774653
Muse Glimmer 30Bmeta/muse-glimmer-30bImage inputTool callingReasoningJSON output131,072103,866415,463675
MiniMax M3minimax/minimax-m3Image inputTool callingReasoningJSON output1,048,576103,866415,463675
Qwen3.7 Plusqwen/qwen3.7-plusImage inputTool callingReasoningJSON output1,000,000110,790443,161720
GLM 5.3 FlashXz-ai/glm-5.3-flashxImage inputTool callingReasoningJSON output1,048,576128,101432,774729
GLM 5.3 FlashX Legalz-ai/glm-5.3-flashx-legalImage inputTool callingReasoningJSON output1,048,576128,101432,774729
Perceptron Mk1perceptron/perceptron-mk1Image inputReasoningJSON output32,76851,933519,329743
Perceptron Mk1.5perceptron/perceptron-mk1.5Image inputTool callingReasoningJSON output36,86451,933519,329743
Inkling Smallthinkingmachines/inkling-smallImage inputTool callingReasoningAudio input524,288155,799415,463743
Hy4tencent/hy4Image inputTool callingReasoningJSON output1,048,576144,373432,947751
Gemini 3 Flash PreviewBatchgoogle/gemini-3-flash-preview:batchImage inputTool callingReasoningJSON output1,048,57686,555519,329788
Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-liteImage inputTool callingReasoningJSON output1,048,57686,555519,329788
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google/gemini-3.1-flash-lite-imageImage inputReasoningJSON outputImage output65,53686,555519,329788
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-previewImage inputTool callingReasoningJSON output1,048,57686,555519,329788
Command A+cohere/command-a-plusImage inputTool callingReasoningJSON output192,000103,866519,329810
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instructImage inputJSON output128,000276,975346,219810
Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15Image inputTool callingReasoningJSON output1,000,00090,017540,102819
Mistral Large 3 2512mistralai/mistral-large-2512Image inputTool callingJSON outputFile input262,144173,110519,329900
GPT-4.1 Miniopenai/gpt-4.1-miniImage inputTool callingJSON outputFile input1,047,576138,488553,951900
Sonarperplexity/sonarImage input127,072346,219346,219900
Qwen3.8 27Bqwen/qwen3.8-27bImage inputTool callingReasoningJSON output1,024,00051,933649,161911
Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420Image inputTool callingReasoningJSON output1,000,000103,866623,195945
Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instructImage inputTool callingJSON output262,14472,706657,817950
Seed 1.6bytedance-seed/seed-1.6Image inputTool callingReasoningJSON output262,14486,555692,4391,013
Seed-2.0-Litebytedance-seed/seed-2.0-liteImage inputTool callingReasoningJSON output262,14486,555692,4391,013
Gemini 3.6 FlashBatchgoogle/gemini-3.6-flash:batchImage inputTool callingReasoningJSON output1,048,576129,832649,1611,013
Gemini 3.7 FlashBatchgoogle/gemini-3.7-flash:batchImage inputTool callingReasoningJSON output1,048,576129,832649,1611,013
Gemini 3.8 FlashBatchgoogle/gemini-3.8-flash:batchImage inputTool callingReasoningJSON output1,048,576129,832649,1611,013
GPT-5 Miniopenai/gpt-5-miniImage inputTool callingReasoningJSON output400,00086,555692,4391,013
GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-miniImage inputTool callingReasoningJSON output400,00086,555692,4391,013
Qwen3.6 Plusqwen/qwen3.6-plusImage inputTool callingReasoningJSON output1,000,000112,521675,1281,024
Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10bImage inputTool callingReasoningJSON output262,14490,017720,1361,053
Mistral Medium 3mistralai/mistral-medium-3Image inputTool callingJSON outputFile input131,072138,488692,4391,080
Mistral Medium 3.1mistralai/mistral-medium-3.1Image inputTool callingJSON outputFile input131,072138,488692,4391,080
MiMo-V2.5xiaomi/mimo-v2.5Image inputTool callingReasoningJSON output1,000,000138,488692,4391,080
GLM 4.5Vz-ai/glm-4.5vImage inputTool callingReasoningJSON output65,536207,732623,1951,080

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

Other categories

See this category ranked by real usage →