Vision models, ranked
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.
Most used in this category
Each model's share of this category's usage over the last 30 days, and its output price per 1M tokens in toman.
- 1
Gemini 3.8 Flash49% share1,298,323 toman - 2Gemini 2.5 Flash Lite29% share138,488 toman
- 3Gemini 3.1 Flash Lite5.6% share519,329 toman
- 4Claude Sonnet 54.6% share3,462,194 toman
- 5Gemini 2.5 Flash4.1% share865,548 toman
Best value in this category
Score out of 100: 50% cheapness, 30% capabilities, 20% context size — not a quality benchmark.
| # | Model | Context (tokens) | ≈ 1,000 words (toman) | Score |
|---|---|---|---|---|
| 1 | 1GLM Flash Latest | 1,048,576 | 54 | 88.9 |
| 2 | 2Qwen3.7 Flash | 1,000,000 | 72 | 85.6 |
| 3 | 3GPT-6 Luna Pro (batch) | 1,050,000 | 135 | 84.9 |
| 4 | 4GPT-6 Luna (batch) | 1,050,000 | 135 | 84.9 |
| 5 | 5Claude Haiku 5.5 (batch) | 1,000,000 | 135 | 84.8 |
| 6 | 6GPT-5 Nano (batch) | 400,000 | 101 | 84.7 |
| 7 | 7Gemma 4 26B A4B | 262,144 | 67 | 81.7 |
| 8 | 8GLM 5.3 Flash (batch) | 1,048,576 | 104 | 81.7 |
| 9 | 9Extract | 1,000,000 | 18 | 81.1 |
| 10 | 10Summarize | 1,000,000 | 18 | 81.1 |
| 11 | 11Gemini 2.5 Flash Lite | 1,048,576 | 225 | 79.4 |
| 12 | 12Ternary Bonsai 2 9B | 262,144 | 95 | 77.9 |
| 13 | 13Qwen3.5-Flash | 1,000,000 | 146 | 77.9 |
| 14 | 14Nex-N2.5-Mini | 262,144 | 56 | 77.7 |
| 15 | 15GPT-6 Luna | 1,050,000 | 270 | 77.4 |