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
| Model | Capabilities | Context | Input / 1M | Output / 1M | ≈ 1,000 words |
|---|---|---|---|---|---|
| Dots3-Note Preview (free)dots-studio/dots-3-note-preview:free | Free · shared capacityvisiontoolsreasoningjson | 512,000 | 0 | 0 | 0 |
| Free · shared capacityvisiontoolsreasoningjson | 262,144 | 0 | 0 | 0 | |
| Free · shared capacityvisiontoolsreasoningjson | 262,144 | 0 | 0 | 0 | |
| visionjson | 1,048,576 | 0 | 0 | 0 | |
| visionjson | 1,048,576 | 0 | 0 | 0 | |
| Free · shared capacityvisiontoolsreasoningjson | 1,048,576 | 0 | 0 | 0 | |
| Free · shared capacityvisiontoolsreasoningaudio | 256,000 | 0 | 0 | 0 | |
| Free · shared capacityvisionreasoning | 128,000 | 0 | 0 | 0 | |
| Free · shared capacityvisiontoolsreasoningjson | 200,000 | 0 | 0 | 0 | |
| Inkling Small (free)thinkingmachines/inkling-small:free | Free · shared capacityvisiontoolsreasoningaudio | 1,048,576 | 0 | 0 | 0 |
| Inkling (free)thinkingmachines/inkling:free | Free · shared capacityvisiontoolsreasoningaudio | 1,048,576 | 0 | 0 | 0 |
| Nex-N2-Mininex-agi/nex-n2-mini | visiontoolsreasoningjson | 262,144 | 7,253 | 29,013 | 47 |
| visionjson | 131,072 | 14,506 | 29,013 | 57 | |
| visiontoolsreasoningjson | 1,000,000 | 8,704 | 37,716 | 60 | |
| visiontoolsjson | 131,072 | 14,506 | 43,519 | 75 | |
| visiontoolsjson | 131,072 | 29,013 | 29,013 | 75 | |
| Reka Edgerekaai/reka-edge | visiontoolsjson | 16,384 | 29,013 | 29,013 | 75 |
| GPT-5 Nano (batch)openai/gpt-5-nano:batch | visiontoolsreasoningjson | 400,000 | 7,253 | 58,025 | 85 |
| visiontoolsreasoningjson | 1,048,576 | 14,506 | 58,025 | 94 | |
| GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batch | visiontoolsjsonfiles | 1,047,576 | 14,506 | 58,025 | 94 |
| visiontoolsreasoningjson | 262,144 | 29,013 | 43,519 | 94 | |
| visiontoolsjson | 131,072 | 21,759 | 58,025 | 104 | |
| visiontools | 300,000 | 17,408 | 69,630 | 113 | |
| visionjson | 128,000 | 29,013 | 58,025 | 113 | |
| visiontoolsreasoningjson | 1,048,576 | 29,013 | 58,025 | 113 | |
| visiontoolsreasoningjson | 1,048,576 | 29,013 | 58,025 | 113 | |
| visiontoolsjson | 262,144 | 43,519 | 43,519 | 113 | |
| GLM Flash Latest~z-ai/glm-flash-latest | visiontoolsreasoningjson | 1,310,720 | 20,671 | 68,905 | 116 |
| visiontoolsreasoningjson | 1,000,000 | 18,858 | 75,433 | 123 | |
| GLM 5.3 Flashz-ai/glm-5.3-flash | visiontoolsreasoningjson | 1,310,720 | 21,759 | 72,531 | 123 |
| visionjson | 163,840 | 52,223 | 52,223 | 136 | |
| visiontoolsreasoningjson | 262,144 | 21,759 | 87,038 | 141 | |
| GPT-4o-mini (batch)openai/gpt-4o-mini:batch | visiontoolsjsonfiles | 128,000 | 21,759 | 87,038 | 141 |
| visiontoolsjson | 1,310,720 | 29,013 | 87,038 | 151 | |
| visiontoolsjson | 262,144 | 58,025 | 58,025 | 151 | |
| visionreasoningjson | 131,072 | 58,025 | 58,025 | 151 | |
| visiontoolsreasoningjson | 262,144 | 20,309 | 98,643 | 155 | |
| visiontoolsreasoningjson | 262,144 | 49,321 | 72,531 | 158 | |
| MiMo-V2.5xiaomi/mimo-v2.5 | visiontoolsreasoningjson | 1,050,000 | 40,618 | 81,235 | 158 |
| visiontoolsreasoningjson | 262,144 | 26,111 | 98,643 | 162 | |
| GPT-5 Nanoopenai/gpt-5-nano | visiontoolsreasoningjson | 400,000 | 14,506 | 116,050 | 170 |
| visiontoolsreasoningjson | 262,144 | 29,013 | 116,050 | 189 | |
| visiontoolsreasoningjson | 1,048,576 | 29,013 | 116,050 | 189 | |
| GPT-4.1 Nanoopenai/gpt-4.1-nano | visiontoolsjsonfiles | 1,047,576 | 29,013 | 116,050 | 189 |
| visiontoolsjson | 131,072 | 30,173 | 120,692 | 196 | |
| visiontoolsjson | 131,072 | 23,210 | 130,556 | 200 | |
| visiontoolsjson | 262,144 | 33,945 | 132,007 | 216 | |
| visiontoolsreasoningjson | 1,000,000 | 43,519 | 136,359 | 234 | |
| GLM 5.3 Flash (batch)z-ai/glm-5.3-flash:batch | visiontoolsreasoningjson | 1,048,575 | 43,519 | 145,063 | 245 |
| GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batch | visiontoolsreasoningjson | 1,050,000 | 29,013 | 174,075 | 264 |
| GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batch | visiontoolsreasoningjson | 1,050,000 | 29,013 | 174,075 | 264 |
| GPT-5.4 Nano (batch)openai/gpt-5.4-nano:batch | visiontoolsreasoningjson | 400,000 | 29,013 | 181,328 | 273 |
| visiontoolsreasoningjson | 262,144 | 43,519 | 174,075 | 283 | |
| GPT-4o-miniopenai/gpt-4o-mini | visiontoolsjsonfiles | 128,000 | 43,519 | 174,075 | 283 |
| GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18 | visiontoolsjsonfiles | 128,000 | 43,519 | 174,075 | 283 |
| visiontoolsjson | 262,144 | 43,519 | 174,075 | 283 | |
| visiontoolsreasoningjson | 1,048,576 | 36,266 | 217,594 | 330 | |
| visiontoolsreasoningjson | 1,048,576 | 63,828 | 191,483 | 332 | |
| visiontoolsjson | 1,048,576 | 58,025 | 201,927 | 338 | |
| vision | 128,000 | 101,834 | 161,019 | 342 | |
| GPT-4.1 Mini (batch)openai/gpt-4.1-mini:batch | visiontoolsjsonfiles | 1,047,576 | 58,025 | 232,100 | 377 |
| visiontoolsreasoningjson | 262,144 | 29,013 | 261,113 | 377 | |
| GPT-5 Mini (batch)openai/gpt-5-mini:batch | visiontoolsreasoningjson | 400,000 | 36,266 | 290,125 | 424 |
| GLM 4.6Vz-ai/glm-4.6v | visiontoolsreasoningjson | 131,072 | 87,038 | 261,113 | 453 |
| Nex-N2-Pronex-agi/nex-n2-pro | visiontoolsreasoning | 262,144 | 72,531 | 290,125 | 471 |
| vision | 1,000,192 | 58,025 | 319,138 | 490 | |
| visiontoolsreasoningjson | 1,000,000 | 54,398 | 326,391 | 495 | |
| visiontoolsreasoningjson | 262,144 | 58,025 | 333,644 | 509 | |
| visiontoolsreasoningjson | 262,144 | 113,149 | 281,421 | 513 | |
| visiontoolsreasoningjson | 1,048,576 | 43,519 | 362,656 | 528 | |
| visiontoolsreasoningjson | 1,048,576 | 43,519 | 362,656 | 528 | |
| visiontoolsreasoningjson | 131,072 | 87,038 | 319,138 | 528 | |
| GPT-5.6 Lunaopenai/gpt-5.6-luna | visiontoolsreasoningjson | 1,050,000 | 58,025 | 348,150 | 528 |
| GPT-5.6 Luna Proopenai/gpt-5.6-luna-pro | visiontoolsreasoningjson | 1,050,000 | 58,025 | 348,150 | 528 |
| GPT-5.4 Nanoopenai/gpt-5.4-nano | visiontoolsreasoningjson | 400,000 | 58,025 | 362,656 | 547 |
| Claude 3 Haikuanthropic/claude-3-haiku | visiontools | 200,000 | 72,531 | 362,656 | 566 |
| visiontoolsreasoningjson | 1,048,576 | 87,038 | 348,150 | 566 | |
| visiontoolsreasoningjson | 524,288 | 87,038 | 348,150 | 566 | |
| visiontoolsreasoningjson | 262,144 | 90,664 | 362,656 | 589 | |
| visiontoolsreasoningjson | 1,000,000 | 92,840 | 371,360 | 603 | |
| Perceptron Mk1perceptron/perceptron-mk1 | visionreasoningjson | 32,768 | 43,519 | 435,188 | 622 |
| Inkling Smallthinkingmachines/inkling-small | visiontoolsreasoningaudio | 1,048,576 | 130,556 | 348,150 | 622 |
| visionreasoning | 123,000 | 121,853 | 362,656 | 630 | |
| Inkling Small (batch)thinkingmachines/inkling-small:batch | visiontoolsreasoningaudio | 524,288 | 145,063 | 348,150 | 641 |
| visiontoolsreasoningjson | 1,048,576 | 72,531 | 435,188 | 660 | |
| visiontoolsreasoningjson | 1,048,576 | 72,531 | 435,188 | 660 | |
| visionreasoningjsonimage out | 65,536 | 72,531 | 435,188 | 660 | |
| visiontoolsreasoningjson | 1,048,576 | 72,531 | 435,188 | 660 | |
| visiontoolsreasoningjson | 262,144 | 56,574 | 452,595 | 662 | |
| visionjson | 128,000 | 232,100 | 290,125 | 679 | |
| visiontoolsreasoningjson | 1,000,000 | 75,433 | 452,595 | 686 | |
| visiontoolsreasoningjson | 131,072 | 101,544 | 435,188 | 698 | |
| visiontoolsjsonfiles | 262,144 | 145,063 | 435,188 | 754 | |
| GPT-4.1 Miniopenai/gpt-4.1-mini | visiontoolsjsonfiles | 1,047,576 | 116,050 | 464,200 | 754 |
| vision | 127,072 | 290,125 | 290,125 | 754 | |
| visiontoolsreasoningjson | 1,000,000 | 87,038 | 522,225 | 792 | |
| visiontoolsjson | 262,144 | 60,926 | 551,238 | 796 | |
| visiontoolsreasoningjson | 262,144 | 72,531 | 580,250 | 849 | |
| visiontoolsreasoningjson | 262,144 | 72,531 | 580,250 | 849 | |
| visiontoolsreasoningjson | 1,048,576 | 108,797 | 543,984 | 849 | |
| visiontoolsreasoningjson | 1,048,576 | 108,797 | 543,984 | 849 | |
| visiontoolsreasoningjson | 1,048,576 | 108,797 | 543,984 | 849 | |
| GPT-5 Miniopenai/gpt-5-mini | visiontoolsreasoningjson | 400,000 | 72,531 | 580,250 | 849 |
| GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini | visiontoolsreasoningjson | 400,000 | 72,531 | 580,250 | 849 |
| visiontoolsreasoningjson | 1,000,000 | 94,291 | 565,744 | 858 | |
| visiontoolsreasoningjson | 131,072 | 52,223 | 609,263 | 860 | |
| visiontoolsreasoningjson | 262,144 | 87,038 | 580,250 | 867 | |
| visiontoolsjsonfiles | 131,072 | 116,050 | 580,250 | 905 | |
| visiontoolsjsonfiles | 131,072 | 116,050 | 580,250 | 905 | |
| GLM 4.5Vz-ai/glm-4.5v | visiontoolsreasoningjson | 65,536 | 174,075 | 522,225 | 905 |
| visiontoolsreasoningjson | 262,144 | 58,025 | 696,300 | 981 | |
| GPT-5.4 Mini (batch)openai/gpt-5.4-mini:batch | visiontoolsreasoningjson | 400,000 | 108,797 | 652,781 | 990 |
| visiontoolsreasoningjson | 262,144 | 84,136 | 696,300 | 1,015 | |
| Kimi K2.5moonshotai/kimi-k2.5 | visiontoolsreasoningjson | 262,144 | 130,556 | 652,781 | 1,018 |
| visiontoolsreasoningjson | 262,144 | 113,149 | 678,893 | 1,030 | |
| o4 Mini (batch)openai/o4-mini:batch | visiontoolsreasoningjson | 200,000 | 159,569 | 638,275 | 1,037 |
| visiontoolsreasoningfiles | 1,000,000 | 87,038 | 725,313 | 1,056 | |
| visiontoolsreasoningjson | 1,048,576 | 87,038 | 725,313 | 1,056 | |
| visionreasoningjsonimage out | 32,768 | 87,038 | 725,313 | 1,056 | |
| visiontoolsreasoningjson | 1,048,576 | 87,038 | 725,313 | 1,056 |
Showing the first 120. For finer filters see the full catalogue .
Other categories
Models that hold up in a real codebaseCheap models for high-volume workFree models, shared capacityReasoning models, and what they costLong-context models for documents and codebasesModels that call your tools reliablyModels that return imagesEmbedding models for semantic searchBatch variants (cheaper, slower)