Published at: 2026-09-17
Billing & usage management overview
ShareCRM connects to mainstream large language models on the market. Because each provider offers different list prices, ShareCRM uses credits as the unified billing unit for the AI platform. 1 credit = 0.10 RMB.
Billing rules
During use (conversation, workflow, development, debugging, and so on), the system automatically deducts a quota based on actual resource consumption (that is, the underlying credit resources). The consumption depends on the following factors:
Model pricing
Baidu ERNIE
| Model name | Best for | Context length | Input unit price (RMB/million tokens) | Output unit price (RMB/million tokens) | Input token consumption (credits/million tokens) | Output tokens (credits/million tokens) |
|---|---|---|---|---|---|---|
| ERNIE 3.5 series | Content generation | 8K | 0.80 | 2.00 | 8.00 | 20.00 |
| ERNIE 4.0 series | Reasoning & web search | 8K | 4.00 | 16.00 | 40.00 | 160.00 |
| ERNIE 4.5 series | Reasoning & web search | 8K | 4.00 | 16.00 | 40.00 | 160.00 |
Alibaba Cloud
| Model name | Best for | Context length | Input unit price (RMB/million tokens) | Output unit price (RMB/million tokens) | Input unit price (credits/million tokens) | Output unit price (credits/million tokens) |
|---|---|---|---|---|---|---|
| qwen-turbo | Web search | Input 128K/Output 8K | 0.30 | 0.60 | 3.00 | 6.00 |
| qwen-plus | Reasoning & web search | Input 128K/Output 8K | 0.80 | 2.00 | 8.00 | 20.00 |
| qwen-max | Reasoning & web search | Input 32K/Output 8K | 2.40 | 9.60 | 24.00 | 96.00 |
| qwen3-235b | Content generation | Input 128K/Output 16K | 2.00 | 8.00 | 20.00 | 80.00 |
| qwen3-30b | Content generation | Input 126K/Output 32K | 0.75 | 3.00 | 7.50 | 30.00 |
| qwen3.5-plus | Content generation | Input 991K/Output 64K | 0.80 | 4.80 | 8.00 | 48.00 |
| qwen3.5-397b-a17b | Content generation | Input 254K/Output 64K | 1.20 | 7.20 | 12.00 | 72.00 |
| qwen-vl-plus | Visual understanding | Input 6K/Output 2K | 1.50 | 4.50 | 15.00 | 45.00 |
| qwen-vl-max | Visual understanding | Input 30K/Output 2K | 3.00 | 9.00 | 30.00 | 90.00 |
| qwen2.5-vl-32b | Visual understanding | Input 126K/Output 8K | 8.00 | 24.00 | 80.00 | 240.00 |
| qwen3-vl-plus | Visual understanding | Input 252K/Output 32K | 1.00 | 10.00 | 10.00 | 100.00 |
| deepseek-v3 | Content generation | Input 57K/Output 8K | 2.00 | 8.00 | 20.00 | 80.00 |
| deepseek-v3.1 | Content generation | Input 96K/Output 64K | 4.00 | 12.00 | 40.00 | 120.00 |
| deepseek-v3.2 | Content generation | Input 96K/Output 64K | 2.00 | 3.00 | 20.00 | 30.00 |
| deepseek-r1 | Reasoning | Input 57K/Output 8K | 4.00 | 16.00 | 40.00 | 160.00 |
Tencent Hunyuan
| Model name | Best for | Context length | Input unit price (RMB/million tokens) | Output unit price (RMB/million tokens) | Input unit price (credits/million tokens) | Output unit price (credits/million tokens) |
|---|---|---|---|---|---|---|
| qwen-image | Image generation | - | - | 25.00 | - | 250.00 |
| qwen-image-plus | Image generation | - | - | 20.00 | - | 200.00 |
| qwen-image-edit | Image generation | - | - | 30.00 | - | 300.00 |
| Hunyuan-Standard | Content generation & web search | Input 30K/Output 2K | 0.80 | 2.00 | 8.00 | 20.00 |
| hunyuan-pro | Content generation | Input 28K/Output 4K | 30.00 | 100.00 | 300.00 | 1000.00 |
| hunyuan-large | Content generation | Input 28K/Output 4K | 4.00 | 12.00 | 40.00 | 120.00 |
| hunyuan-turbo | Content generation & web search | Input 28K/Output 4K | 2.40 | 9.60 | 24.00 | 96.00 |
| deepseek-v3 | Content generation | 64K | 2.00 | 8.00 | 20.00 | 80.00 |
| deepseek-r1 | Reasoning | 64K | 4.00 | 16.00 | 40.00 | 160.00 |
ByteDance Doubao
| Model name | Best for | Context length | Input unit price (RMB/million tokens) | Output unit price (RMB/million tokens) | Input unit price (credits/million tokens) | Output unit price (credits/million tokens) |
|---|---|---|---|---|---|---|
| Doubao-Pro-4k | Content generation | 4K | 0.80 | 2.00 | 8.00 | 20.00 |
| Doubao-Pro-32k | Content generation | 32K | 0.80 | 2.00 | 8.00 | 20.00 |
| deepseek-v3 | Content generation | Input 57K/Output 8K | 2.00 | 8.00 | 20.00 | 80.00 |
| deepseek-v3.1 | Content generation | Input 96K/Output 32K | 4.00 | 12.00 | 40.00 | 120.00 |
| deepseek-v3.2 | Content generation | Input 96K/Output 32K | 2.00 | 3.00 | 20.00 | 30.00 |
| Doubao-seed-2.0-pro | Content generation | 256K | 3.20 | 16.00 | 32.00 | 160.00 |
| Doubao-seed-2.0-lite | Content generation | 256K | 0.60 | 3.60 | 6.00 | 36.00 |
| Doubao-seed-2.0-mini | Content generation | 256K | 0.20 | 2.00 | 2.00 | 20.00 |
Zhipu
| Model name | Best for | Context length | Input unit price (RMB/million tokens) | Output unit price (RMB/million tokens) | Input unit price (credits/million tokens) | Output unit price (credits/million tokens) |
|---|---|---|---|---|---|---|
| GLM-4-Flash | Content generation | - | 0.10 | 0.10 | 1.00 | 1.00 |
| GLM-4-Air | Content generation | - | 0.50 | 0.50 | 5.00 | 5.00 |
| GLM-4V-Plus | Visual understanding | 8K | 4.00 | 4.00 | 40.00 | 40.00 |