RolmOCR
RolmOCR is IBM's image to text model with a 128K context window, starting at $0.200 / 1M input and $0.200 / 1M output. An open-source document OCR model built on Qwen2.5-VL-7B-Instruct, offering fast and memory-efficient document text extraction as an alternative to olmOCR.
IBM's image to text model with a 128K context window, starting at $0.200 / 1M input and $0.200 / 1M output. An open-source document OCR model built on Qwen2.5-VL-7B-Instruct, offering fast and memory-efficient document text extraction as an alternative to olmOCR.ibm-rolm-ocr |
| Image to Text |
| Active |
| IBM |
| 128K tokens |
| Text |
| Text |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Fireworks AI | $0.200 | $0.200 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen2.5 VL 32B Instruct | 131K | $0.200 | $0.600 | Available | |
| Qwen2.5 VL 72B Instruct | 131K | $0.130 | $0.400 | Available | |
| RolmOCR | — | 128K | $0.200 | $0.200 | Current |
| Qwen2.5 VL 3B Instruct | — | 131K | $0.200 | $0.200 | Available |
| Qwen2.5 VL 7B Instruct | — | 131K | $0.200 | $0.200 | Available |