Qianfan Models by Baidu AI
2 models2026Up to 131K ctxFrom $0.68/1M input
About
Qianfan is Baidu's umbrella line for Qianfan platform specialist models, including coding and OCR-focused models separate from the ERNIE flagship family.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
2 in view
CoBuddyCurrent
Use when the workload needs code, 131K context, and reasoning.
2026-05code131K contextreasoning
Qianfan-OCR-FastCurrent
Use when the workload needs ocr, 66K context, and multimodal inputs.
2026-04ocr66K contextmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| CoBuddy | Use when the workload needs code, 131K context, and reasoning. | 2026-05 | code131K contextreasoning | Current |
| Qianfan-OCR-Fast | Use when the workload needs ocr, 66K context, and multimodal inputs. | 2026-04 | ocr66K contextmultimodal inputs | Current |
Release Timeline
2 release groups2026-05
1 current
CoBuddy
Currentcode131K contextreasoning
2026-04
1 current
Qianfan-OCR-Fast
Currentocr66K contextmultimodal inputs
Specifications(2 models)
| Model | Released | Context | Vision | Multimodal | Reasoning | Fn Calling | Tool Use |
|---|---|---|---|---|---|---|---|
| CoBuddy | 2026-05 | 131K | No | No | Yes | Yes | Yes |
| Qianfan-OCR-Fast | 2026-04 | 66K | Yes | Yes | No | No | No |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Qianfan-OCR-Fast | OpenRouter | $0.68 | $2.81 | Serverless |
Frequently Asked Questions
- What is Qianfan used for?
- Qianfan is used for code, coding, and ocr. The family description and listed model capabilities point to those workloads as the best fit.
- How does Qianfan compare to ERNIE 4.5?
- Qianfan by Baidu AI is strongest where you need code, while ERNIE 4.5 by Baidu AI is the closest related family to check for vision and multimodal work. Qianfan has 2 listed variants and reaches up to 131K context, while ERNIE 4.5 reaches up to 128K context, so compare the specs and pricing tables before choosing a production model.
- Which Qianfan model should I use?
- For the lowest listed input price, start with Qianfan-OCR-Fast through OpenRouter at $0.68/1M input tokens. For the most capable/latest local choice, evaluate CoBuddy with 131K context and reasoning, tool use, and function calling.