Top picks for Diagram Extraction (2026)
Reading flowcharts, org charts, architecture diagrams. Ranked from 334 live models on the OpenRouter catalog, weighted for vision input, structured output, reasoning quality.
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Anthropic: Claude Sonnet 4.6anthropic/claude-sonnet-4.6 | 156 | $3.00 | $15.00 | 1,000,000 | Details → |
| 2 | Anthropic: Claude Opus 4.7anthropic/claude-opus-4.7 | 153 | $5.00 | $25.00 | 1,000,000 | Details → |
| 3 | OpenAI: GPT-5.4openai/gpt-5.4 | 150 | $2.50 | $15.00 | 1,050,000 | Details → |
| 4 | Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash | 148 | $1.50 | $9.00 | 1,048,576 | Details → |
| 5 | Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 148 | $2.00 | $12.00 | 1,048,576 | Details → |
| 6 | MoonshotAI: Kimi K2.6moonshotai/kimi-k2.6 | 147 | $0.66 | $3.41 | 262,144 | Details → |
| 7 | MiniMax: MiniMax M3minimax/minimax-m3 | 147 | $0.30 | $1.20 | 1,048,576 | Details → |
| 8 | MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code | 147 | $0.61 | $3.07 | 262,144 | Details → |
| 9 | Anthropic: Claude Opus 4.8anthropic/claude-opus-4.8 | 146 | $5.00 | $25.00 | 1,000,000 | Details → |
| 10 | OpenAI: GPT-5.4 Miniopenai/gpt-5.4-mini | 145 | $0.75 | $4.50 | 400,000 | Details → |
| 11 | OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nano | 145 | $0.20 | $1.25 | 400,000 | Details → |
| 12 | Qwen: Qwen3.6 Plusqwen/qwen3.6-plus | 145 | $0.33 | $1.95 | 1,000,000 | Details → |
| 13 | Qwen: Qwen3.7 Plusqwen/qwen3.7-plus | 144 | $0.32 | $1.28 | 1,000,000 | Details → |
| 14 | Qwen: Qwen3.6 27Bqwen/qwen3.6-27b | 144 | $0.29 | $3.17 | 262,144 | Details → |
| 15 | OpenAI: GPT-5.5openai/gpt-5.5 | 144 | $5.00 | $30.00 | 1,050,000 | Details → |
How we ranked these
For Diagram Extraction, we weight models on vision input, structured output, reasoning quality. Scores combine each model's public specs with independent benchmark results (Aider Polyglot coding scores, Artificial Analysis intelligence/coding/agentic indices) and live pricing. See full methodology →
About Diagram Extraction
Diagram extraction is the task of reading visual flowcharts, organizational hierarchies, system architecture diagrams, and similar structured graphics to extract their logical content, relationships, and text. You need this when you have hundreds of legacy diagrams in image format that must become machine-readable data, or when you're building systems that ingest visual workflows at scale. Good models recognize nodes, edges, labels, and hierarchy without hallucinating missing connections or misreading text overlaps common in dense diagrams. Poor models confuse similar shapes, lose spatial relationships, or fail on hand-drawn or low-contrast inputs. Processing time scales with image resolution and diagram complexity-a 4K screenshot of a 50-node architecture diagram can take 10-15 seconds on slower inference pipelines. # WHEN_TO_USE Use this when you have visual diagrams (flowcharts, org charts, network diagrams, system architecture) that you need to convert into structured data, searchable text, or editable formats, without manually redrawing them yourself. # FAQ_Q1 What is the difference between diagram extraction and general OCR? # FAQ_A1 OCR reads isolated text; diagram extraction must also understand spatial relationships, node connections, hierarchy, and the semantic meaning of shapes and arrows. A good diagram extractor knows that an arrow pointing downward in a flowchart means "flows to," not just "text appears below text." Models like Claude 3.5 Sonnet or GPT-4V handle this contextually, while basic OCR tools cannot. # FAQ_Q2 How much does it cost to extract diagrams from a large document set, and how fast does it run? # FAQ_A2 API-based models (GPT-4V, Claude) typically cost $0.01-0.10 per diagram depending on resolution and provider pricing. Speed ranges from 2-30 seconds per image depending on model and queue load; batch processing APIs are slower but cheaper per unit. If you process 1,000 diagrams monthly, expect $10-100 in API costs plus time overhead.
When to use: Use this when you have visual diagrams (flowcharts, org charts, network diagrams, system architecture) that you need to convert into structured data, searchable text, or editable formats, without manually redrawing them yourself. # FAQ_Q1 What is the difference between diagram extraction and general OCR? # FAQ_A1 OCR reads isolated text; diagram extraction must also understand spatial relationships, node connections, hierarchy, and the semantic meaning of shapes and arrows. A good diagram extractor knows that an arrow pointing downward in a flowchart means "flows to," not just "text appears below text." Models like Claude 3.5 Sonnet or GPT-4V handle this contextually, while basic OCR tools cannot. # FAQ_Q2 How much does it cost to extract diagrams from a large document set, and how fast does it run? # FAQ_A2 API-based models (GPT-4V, Claude) typically cost $0.01-0.10 per diagram depending on resolution and provider pricing. Speed ranges from 2-30 seconds per image depending on model and queue load; batch processing APIs are slower but cheaper per unit. If you process 1,000 diagrams monthly, expect $10-100 in API costs plus time overhead.
Common questions
What is the difference between diagram extraction and general OCR? # FAQ_A1 OCR reads isolated text; diagram extraction must also understand spatial relationships, node connections, hierarchy, and the semantic meaning of shapes and arrows. A good diagram extractor knows that an arrow pointing downward in a flowchart means "flows to," not just "text appears below text." Models like Claude 3.5 Sonnet or GPT-4V handle this contextually, while basic OCR tools cannot. # FAQ_Q2 How much does it cost to extract diagrams from a large document set, and how fast does it run? # FAQ_A2 API-based models (GPT-4V, Claude) typically cost $0.01-0.10 per diagram depending on resolution and provider pricing. Speed ranges from 2-30 seconds per image depending on model and queue load; batch processing APIs are slower but cheaper per unit. If you process 1,000 diagrams monthly, expect $10-100 in API costs plus time overhead.
OCR reads isolated text; diagram extraction must also understand spatial relationships, node connections, hierarchy, and the semantic meaning of shapes and arrows. A good diagram extractor knows that an arrow pointing downward in a flowchart means "flows to," not just "text appears below text." Models like Claude 3.5 Sonnet or GPT-4V handle this contextually, while basic OCR tools cannot. # FAQ_Q2 How much does it cost to extract diagrams from a large document set, and how fast does it run? # FAQ_A2 API-based models (GPT-4V, Claude) typically cost $0.01-0.10 per diagram depending on resolution and provider pricing. Speed ranges from 2-30 seconds per image depending on model and queue load; batch processing APIs are slower but cheaper per unit. If you process 1,000 diagrams monthly, expect $10-100 in API costs plus time overhead.
How much does it cost to extract diagrams from a large document set, and how fast does it run? # FAQ_A2 API-based models (GPT-4V, Claude) typically cost $0.01-0.10 per diagram depending on resolution and provider pricing. Speed ranges from 2-30 seconds per image depending on model and queue load; batch processing APIs are slower but cheaper per unit. If you process 1,000 diagrams monthly, expect $10-100 in API costs plus time overhead.
API-based models (GPT-4V, Claude) typically cost $0.01-0.10 per diagram depending on resolution and provider pricing. Speed ranges from 2-30 seconds per image depending on model and queue load; batch processing APIs are slower but cheaper per unit. If you process 1,000 diagrams monthly, expect $10-100 in API costs plus time overhead.