Model List
Updated at：2026-09-07
Text Generation
Tutorial: Text Generation | API: Text Generation
ERNIE Series
| Model Name | model Parameter Endpoint ID |
Context Length (token) |
Max Input (token) |
Max Output (token) |
Default Rate Limit |
|---|---|---|---|---|---|
| ERNIE 5.1 | ernie-5.1 | 128k | 119k | [1, 65536] | RPM = 60 TPM = 150000 |
| ERNIE 5.0 | ernie-5.0 | 128k | 119k | [1, 65536] | RPM = 60 TPM = 150000 |
| ERNIE 4.5 Turbo | ernie-4.5-turbo-32k | 32k | 27k | [2，12288] | RPM = 5000 TPM = 400000 |
| ERNIE 4.5 Turbo | ernie-4.5-turbo-128k | 128k | 123k | [2，12288] | RPM = 5000 TPM = 400000 |
DeepSeek Series
| Model Name | Version | model Parameter Endpoint ID |
Context Length (token) |
Max Input (token) |
Max Output (token) |
Default Rate Limit |
|---|---|---|---|---|---|---|
| DeepSeek-V4 | DeepSeek-V4-Pro-0813 | deepseek-v4-pro-0813 | 1M | 1M | [1,393216] | RPM = 60 TPM = 1000000 |
| DeepSeek-V4 | DeepSeek-V4-Pro | deepseek-v4-pro | 1M | 1M | [1,393216] | RPM = 60 TPM = 150000 |
| DeepSeek-V4 | DeepSeek-V4-Flash-0731 | deepseek-v4-flash-0731 | 1M | 1M | [1,393216] | RPM = 60 TPM = 150000 |
| DeepSeek-V4 | DeepSeek-V4-Flash | deepseek-v4-flash | 1M | 1M | [1,393216] | RPM = 60 TPM = 150000 |
| DeepSeek-V3.2 | DeepSeek-V3.2 | deepseek-v3.2 | 128k | 96k | 32k Default 4k |
RPM = 5000 TPM = 1000000 |
Visual Understanding
Tutorial: Visual Understanding | API: Visual Understanding
ERNIE Series
| Model Name | model Parameter Endpoint ID |
Context Length (token) |
Max Input (token) |
Max Output (token) |
Default Rate Limit |
|---|---|---|---|---|---|
| ERNIE 5.0 | ernie-5.0 | 128k | 119k | [1, 65536] | RPM = 60 TPM = 150000 |
| ERNIE 4.5 Turbo VL | ernie-4.5-turbo-vl | 128k | 123k | [2，16384] | RPM = 1000 TPM = 200000 |
| ERNIE 4.5 Turbo VL | ernie-4.5-turbo-vl-32k | 32k | 27k | [2，12288] | RPM = 1000 TPM = 200000 |
Deep Thinking
Tutorial: Deep Thinking | API: Deep Thinking
ERNIE Series
| Model Name | Version | model Parameter Endpoint ID |
Context Length (token) |
Max Input (token) |
Max Output (token) |
Chain of Thought Length (token) |
Default Rate Limit |
|---|---|---|---|---|---|---|---|
| ERNIE 5.0 | ERNIE 5.0 | ernie-5.0 | 128k | 119k | [1, 65536] | 60k | RPM = 60 TPM = 150000 |
The ERNIE series thinking models do not support thinking_budget. Additionally, max_tokens limits the total length of reasoning_content + content.
DeepSeek Series
| Model Name | Version | model Parameter Endpoint ID |
Context Length (token) |
Max Input (token) |
Max Output (token) |
Chain of Thought Length (token) |
Default Rate Limit |
|---|---|---|---|---|---|---|---|
| DeepSeek-V4 | DeepSeek-V4-Pro-0813 | deepseek-v4-pro-0813 | 1M | 1M | [1,393216] | 32k | RPM = 60 TPM = 1000000 |
| DeepSeek-V4 | DeepSeek-V4-Pro | deepseek-v4-pro | 1M | 1M | [1,393216] | 32k | RPM = 60 TPM = 150000 |
| DeepSeek-V4 | DeepSeek-V4-Flash-0731 | deepseek-v4-flash-0731 | 1M | 1M | [1,393216] | 32k | RPM = 60 TPM = 150000 |
| DeepSeek-V4 | DeepSeek-V4-Flash | deepseek-v4-flash | 1M | 1M | [1,393216] | 32k | RPM = 60 TPM = 150000 |
Others
| Model Name | Version | model Parameter Endpoint ID |
Context Length (token) |
Max Input (token) |
Max Output (token) |
Chain of Thought Length (token) |
Default Rate Limit |
|---|---|---|---|---|---|---|---|
| GLM-5.2 | GLM-5.2 | glm-5.2 | 500k | 500k | [1, 131072] | 32k | RPM = 60 TPM = 250000 |
| GLM-5.2 | GLM-5.2-Fast | glm-5.2-fast | 1024k | 1024k | [1, 131072] | 32k | RPM = 60 TPM = 250000 |
| GLM-5.1 | GLM-5.1 | glm-5.1 | 198k | 198k | [1, 131072] | 32k | RPM = 60 TPM = 250000 |
| GLM-5 | GLM-5 | glm-5 | 198k | 198k | [1, 131072] | 32k | RPM = 60 TPM = 250000 |
| Kimi-K2.6 | Kimi-K2.6 | kimi-k2.6 | 256k | 256k | [1, 262144] | 32k | RPM = 60 TPM = 250000 |
| MiMo-V2.5 | MiMo-V2.5 | mimo-v2.5 | 1024K | 1024K | [1, 131072] | 32k | RPM = 60 TPM = 250000 |