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
| Model | Capabilities | Context | Input / 1M | Output / 1M | ≈ 1,000 words |
|---|---|---|---|---|---|
Dots3-Note Previewdots-studio/dots-3-note-preview:free | Free · shared capacityImage inputTool callingReasoningJSON output | 512,000 | 0 | 0 | 0 |
google/gemma-4-26b-a4b-it:free | Free · shared capacityImage inputTool callingReasoningJSON output | 262,144 | 0 | 0 | 0 |
google/gemma-4-31b-it:free | Free · shared capacityImage inputTool callingReasoningJSON output | 262,144 | 0 | 0 | 0 |
google/lyria-3-clip-preview | Image inputJSON output | 1,048,576 | 0 | 0 | 0 |
google/lyria-3-pro-preview | Image inputJSON output | 1,048,576 | 0 | 0 | 0 |
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Free · shared capacityImage inputTool callingReasoningAudio input | 256,000 | 0 | 0 | 0 |
nvidia/nemotron-3.5-content-safety:free | Free · shared capacityImage inputReasoning | 128,000 | 0 | 0 | 0 |
nvidia/nemotron-3.5-super-vl:free | Free · shared capacityImage inputTool callingReasoningJSON output | 1,000,000 | 0 | 0 | 0 |
Crouton Alphastealth/crouton-alpha | Image inputTool callingReasoningJSON output | 1,048,576 | 0 | 0 | 0 |
Extractscaledown/extract | Image inputFile input | 1,000,000 | 13,849 | 0 | 18 |
Summarizescaledown/summarize | Image inputFile input | 1,000,000 | 13,849 | 0 | 18 |
GLM FlashLatest~z-ai/glm-flash-latest | Image inputTool callingReasoningJSON output | 1,048,576 | 9,867 | 31,956 | 54 |
Nex-N2.5-Mininex-agi/nex-n2.5-mini | Image inputReasoningJSON output | 262,144 | 8,655 | 34,622 | 56 |
google/gemma-3-4b-it | Image inputJSON output | 131,072 | 17,311 | 34,622 | 68 |
qwen/qwen3.7-flash | Image inputTool callingReasoningJSON output | 1,000,000 | 10,387 | 45,009 | 72 |
google/gemma-3-12b-it | Image inputTool callingJSON output | 131,072 | 17,311 | 51,933 | 90 |
mistralai/ministral-3b-2512 | Image inputTool callingJSON output | 131,072 | 34,622 | 34,622 | 90 |
Reka Edgerekaai/reka-edge | Image inputTool callingJSON output | 16,384 | 34,622 | 34,622 | 90 |
Ternary Bonsai 2 9Bprism-ml/ternary-bonsai-2-9b | Image inputTool callingReasoningJSON output | 262,144 | 27,698 | 45,009 | 95 |
GPT-5 NanoBatchopenai/gpt-5-nano:batch | Image inputTool callingReasoningJSON output | 400,000 | 8,655 | 69,244 | 101 |
GLM 5.3 FlashBatchz-ai/glm-5.3-flash:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 17,311 | 62,319 | 104 |
Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl | Image inputTool callingReasoningJSON output | 131,072 | 20,773 | 62,319 | 108 |
google/gemma-4-26b-a4b-it | Image inputTool callingReasoningJSON output | 262,144 | 23,197 | 69,244 | 120 |
mistralai/mistral-small-3.2-24b-instruct | Image inputTool callingJSON output | 256,000 | 25,966 | 69,244 | 124 |
amazon/nova-lite-v1 | Image inputTool calling | 300,000 | 20,773 | 83,093 | 135 |
Claude Haiku 5.5Batchanthropic/claude-haiku-5.5:batch | Image inputTool callingReasoningJSON output | 1,000,000 | 17,311 | 86,555 | 135 |
bytedance/ui-tars-1.5-7b | Image inputJSON output | 128,000 | 34,622 | 69,244 | 135 |
mistralai/ministral-8b-2512 | Image inputTool callingJSON output | 262,144 | 51,933 | 51,933 | 135 |
GPT-6 Luna ProBatchopenai/gpt-6-luna-pro:batch | Image inputTool callingReasoningJSON output | 1,050,000 | 17,311 | 86,555 | 135 |
GPT-6 LunaBatchopenai/gpt-6-luna:batch | Image inputTool callingReasoningJSON output | 1,050,000 | 17,311 | 86,555 | 135 |
Nex-N2.5-Pronex-agi/nex-n2.5-pro | Image inputTool callingReasoningJSON output | 262,144 | 25,966 | 86,555 | 146 |
qwen/qwen3.5-flash-02-23 | Image inputTool callingReasoningJSON output | 1,000,000 | 22,504 | 90,017 | 146 |
meta-llama/llama-guard-4-12b | Image input | 163,840 | 62,319 | 62,319 | 162 |
bytedance-seed/seed-1.6-flash | Image inputTool callingReasoningJSON output | 262,144 | 25,966 | 103,866 | 169 |
meta-llama/llama-4-scout | Image inputTool callingJSON output | 327,680 | 34,622 | 103,866 | 180 |
mistralai/ministral-14b-2512 | Image inputTool callingJSON output | 262,144 | 69,244 | 69,244 | 180 |
nvidia/nemotron-3.5-content-safety | Image inputReasoning | 131,072 | 69,244 | 69,244 | 180 |
qwen/qwen3.5-9b | Image inputTool callingReasoningJSON output | 262,144 | 58,857 | 86,555 | 189 |
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | Image inputTool callingReasoningJSON output | 1,050,000 | 48,471 | 96,941 | 189 |
google/gemma-3-27b-it | Image inputTool callingJSON output | 131,072 | 27,698 | 121,177 | 194 |
deepseek/deepseek-v4.1-flash:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 38,777 | 116,330 | 202 |
GPT-5 Nanoopenai/gpt-5-nano | Image inputTool callingReasoningJSON output | 400,000 | 17,311 | 138,488 | 203 |
bytedance-seed/seed-2.0-mini | Image inputTool callingReasoningJSON output | 262,144 | 34,622 | 138,488 | 225 |
google/gemini-2.5-flash-lite | Image inputTool callingReasoningJSON output | 1,048,576 | 34,622 | 138,488 | 225 |
GPT-4.1 Nanoopenai/gpt-4.1-nano | Image inputTool callingJSON outputFile input | 1,047,576 | 34,622 | 138,488 | 225 |
deepseek/deepseek-v4.1-flash-1017 | Image inputTool callingReasoningJSON output | 1,048,576 | 2,077 | 173,110 | 228 |
~deepseek/deepseek-flash-latest | Image inputTool callingReasoningJSON output | 1,048,576 | 2,077 | 173,110 | 228 |
deepseek/deepseek-v4.1-flash | Image inputTool callingReasoningJSON output | 1,048,576 | 15,580 | 173,110 | 245 |
Particle-1particle-ai/particle-1 | Image inputTool callingReasoningJSON output | 1,048,576 | 17,311 | 173,110 | 248 |
Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27b | Image inputTool callingReasoningJSON output | 262,144 | 25,966 | 173,110 | 259 |
Claude Haiku 5.5anthropic/claude-haiku-5.5 | Image inputTool callingReasoningJSON output | 1,000,000 | 34,622 | 173,110 | 270 |
google/gemma-4-31b-it | Image inputTool callingReasoningJSON output | 262,144 | 69,244 | 138,488 | 270 |
GPT-6 Lunaopenai/gpt-6-luna | Image inputTool callingReasoningJSON output | 1,050,000 | 34,622 | 173,110 | 270 |
GPT-6 Luna Proopenai/gpt-6-luna-pro | Image inputTool callingReasoningJSON output | 1,050,000 | 34,622 | 173,110 | 270 |
Claude HaikuLatest~anthropic/claude-haiku-latest | Image inputTool callingReasoningJSON output | 1,000,000 | 34,622 | 173,110 | 270 |
GPT LunaLatest~openai/gpt-luna-latest | Image inputTool callingReasoningJSON output | 1,050,000 | 34,622 | 173,110 | 270 |
qwen/qwen3.8-flash | Image inputTool callingReasoningJSON output | 1,000,000 | 51,933 | 162,723 | 279 |
qwen/qwen3.8-omni-flash | Image inputTool callingReasoningJSON output | 1,000,000 | 51,933 | 162,723 | 279 |
nvidia/nemotron-3.5-super-vl | Image inputTool callingReasoningJSON output | 1,048,576 | 51,933 | 173,110 | 293 |
GLM 5.3 Flashz-ai/glm-5.3-flash | Image inputTool callingReasoningJSON output | 1,048,576 | 51,933 | 173,110 | 293 |
GPT-5.6 Luna ProBatchopenai/gpt-5.6-luna-pro:batch | Image inputTool callingReasoningJSON output | 1,050,000 | 34,622 | 207,732 | 315 |
GPT-5.6 LunaBatchopenai/gpt-5.6-luna:batch | Image inputTool callingReasoningJSON output | 1,050,000 | 34,622 | 207,732 | 315 |
minimax/minimax-m3.1-flash | Image inputTool callingReasoningJSON output | 1,048,576 | 51,933 | 207,732 | 338 |
mistralai/mistral-small-2603 | Image inputTool callingReasoningJSON output | 262,144 | 51,933 | 207,732 | 338 |
GPT-4o-miniopenai/gpt-4o-mini | Image inputTool callingJSON outputFile input | 128,000 | 51,933 | 207,732 | 338 |
GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18 | Image inputTool callingJSON outputFile input | 128,000 | 51,933 | 207,732 | 338 |
qwen/qwen3-vl-30b-a3b-instruct | Image inputTool callingJSON output | 262,144 | 51,933 | 207,732 | 338 |
deepseek/deepseek-v4-flash-vision-exp | Image inputTool callingReasoningJSON output | 1,048,576 | 74,645 | 223,935 | 388 |
google/gemini-3.1-flash-lite:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 43,277 | 259,665 | 394 |
mistralai/mistral-small-3.1-24b-instruct | Image inputTool callingJSON output | 128,000 | 121,523 | 192,152 | 408 |
qwen/qwen3-vl-8b-instruct | Image inputTool callingJSON output | 262,144 | 86,555 | 259,665 | 450 |
qwen/qwen3.6-35b-a3b | Image inputTool callingReasoningJSON output | 262,144 | 34,622 | 311,597 | 450 |
qwen/qwen3.5-35b-a3b | Image inputTool callingReasoningJSON output | 262,144 | 48,471 | 346,219 | 513 |
qwen/qwen3.7-plus:batch | Image inputTool callingReasoningJSON output | 262,144 | 79,630 | 318,522 | 518 |
GLM 4.6Vz-ai/glm-4.6v | Image inputTool callingReasoningJSON output | 131,072 | 103,866 | 311,597 | 540 |
qwen/qwen3-vl-30b-a3b-thinking | Image inputTool callingReasoningJSON output | 262,144 | 100,404 | 346,219 | 581 |
minimax/minimax-01 | Image input | 1,000,192 | 69,244 | 380,841 | 585 |
MiMo-V2.6-Proxiaomi/mimo-v2.6-pro | Image inputTool callingReasoningJSON output | 1,050,000 | 150,605 | 301,211 | 587 |
qwen/qwen3.6-flash | Image inputTool callingReasoningJSON output | 1,000,000 | 64,916 | 389,497 | 591 |
meta-llama/llama-4-maverick | Image inputTool callingJSON output | 524,288 | 121,177 | 346,219 | 608 |
stepfun/step-3.7-flash | Image inputTool callingReasoningJSON output | 262,144 | 69,244 | 398,152 | 608 |
google/gemini-3.5-flash-lite:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 51,933 | 432,774 | 630 |
GPT-5.6 Lunaopenai/gpt-5.6-luna | Image inputTool callingReasoningJSON output | 1,050,000 | 69,244 | 415,463 | 630 |
GPT-5.6 Luna Proopenai/gpt-5.6-luna-pro | Image inputTool callingReasoningJSON output | 1,050,000 | 69,244 | 415,463 | 630 |
GPT-5.4 Nanoopenai/gpt-5.4-nano | Image inputTool callingReasoningJSON output | 400,000 | 69,244 | 432,774 | 653 |
meta/muse-glimmer-30b | Image inputTool callingReasoningJSON output | 131,072 | 103,866 | 415,463 | 675 |
minimax/minimax-m3 | Image inputTool callingReasoningJSON output | 1,048,576 | 103,866 | 415,463 | 675 |
qwen/qwen3.7-plus | Image inputTool callingReasoningJSON output | 1,000,000 | 110,790 | 443,161 | 720 |
GLM 5.3 FlashXz-ai/glm-5.3-flashx | Image inputTool callingReasoningJSON output | 1,048,576 | 128,101 | 432,774 | 729 |
GLM 5.3 FlashX Legalz-ai/glm-5.3-flashx-legal | Image inputTool callingReasoningJSON output | 1,048,576 | 128,101 | 432,774 | 729 |
Perceptron Mk1perceptron/perceptron-mk1 | Image inputReasoningJSON output | 32,768 | 51,933 | 519,329 | 743 |
Perceptron Mk1.5perceptron/perceptron-mk1.5 | Image inputTool callingReasoningJSON output | 36,864 | 51,933 | 519,329 | 743 |
Inkling Smallthinkingmachines/inkling-small | Image inputTool callingReasoningAudio input | 524,288 | 155,799 | 415,463 | 743 |
tencent/hy4 | Image inputTool callingReasoningJSON output | 1,048,576 | 144,373 | 432,947 | 751 |
google/gemini-3-flash-preview:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 86,555 | 519,329 | 788 |
google/gemini-3.1-flash-lite | Image inputTool callingReasoningJSON output | 1,048,576 | 86,555 | 519,329 | 788 |
google/gemini-3.1-flash-lite-image | Image inputReasoningJSON outputImage output | 65,536 | 86,555 | 519,329 | 788 |
google/gemini-3.1-flash-lite-preview | Image inputTool callingReasoningJSON output | 1,048,576 | 86,555 | 519,329 | 788 |
cohere/command-a-plus | Image inputTool callingReasoningJSON output | 192,000 | 103,866 | 519,329 | 810 |
qwen/qwen2.5-vl-72b-instruct | Image inputJSON output | 128,000 | 276,975 | 346,219 | 810 |
qwen/qwen3.5-plus-02-15 | Image inputTool callingReasoningJSON output | 1,000,000 | 90,017 | 540,102 | 819 |
mistralai/mistral-large-2512 | Image inputTool callingJSON outputFile input | 262,144 | 173,110 | 519,329 | 900 |
GPT-4.1 Miniopenai/gpt-4.1-mini | Image inputTool callingJSON outputFile input | 1,047,576 | 138,488 | 553,951 | 900 |
perplexity/sonar | Image input | 127,072 | 346,219 | 346,219 | 900 |
qwen/qwen3.8-27b | Image inputTool callingReasoningJSON output | 1,024,000 | 51,933 | 649,161 | 911 |
qwen/qwen3.5-plus-20260420 | Image inputTool callingReasoningJSON output | 1,000,000 | 103,866 | 623,195 | 945 |
qwen/qwen3-vl-235b-a22b-instruct | Image inputTool callingJSON output | 262,144 | 72,706 | 657,817 | 950 |
bytedance-seed/seed-1.6 | Image inputTool callingReasoningJSON output | 262,144 | 86,555 | 692,439 | 1,013 |
bytedance-seed/seed-2.0-lite | Image inputTool callingReasoningJSON output | 262,144 | 86,555 | 692,439 | 1,013 |
google/gemini-3.6-flash:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 129,832 | 649,161 | 1,013 |
google/gemini-3.7-flash:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 129,832 | 649,161 | 1,013 |
google/gemini-3.8-flash:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 129,832 | 649,161 | 1,013 |
GPT-5 Miniopenai/gpt-5-mini | Image inputTool callingReasoningJSON output | 400,000 | 86,555 | 692,439 | 1,013 |
GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini | Image inputTool callingReasoningJSON output | 400,000 | 86,555 | 692,439 | 1,013 |
qwen/qwen3.6-plus | Image inputTool callingReasoningJSON output | 1,000,000 | 112,521 | 675,128 | 1,024 |
qwen/qwen3.5-122b-a10b | Image inputTool callingReasoningJSON output | 262,144 | 90,017 | 720,136 | 1,053 |
mistralai/mistral-medium-3 | Image inputTool callingJSON outputFile input | 131,072 | 138,488 | 692,439 | 1,080 |
mistralai/mistral-medium-3.1 | Image inputTool callingJSON outputFile input | 131,072 | 138,488 | 692,439 | 1,080 |
MiMo-V2.5xiaomi/mimo-v2.5 | Image inputTool callingReasoningJSON output | 1,000,000 | 138,488 | 692,439 | 1,080 |
GLM 4.5Vz-ai/glm-4.5v | Image inputTool callingReasoningJSON output | 65,536 | 207,732 | 623,195 | 1,080 |
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)