DeepSeek V4 Pro Save up to 5%deepseek-v4-pro
Type
Spec
Rate
Input
per 1M prompt tokens
$1.74$1.65
Output
per 1M generated tokens
$3.48$3.30
Web Search (Linkup)
per call when invoked
$0.013
DeepSeek V4 Pro and GLM 5.1 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
DeepSeek 
Z.ai Text GenerationDeepSeek V4 Pro from DeepSeek and GLM 5.1 from Z.ai are both in the Text Generation category, available through the EmpirioLabs API.
| Spec | DeepSeek V4 Pro | GLM 5.1 |
|---|---|---|
| Model ID | deepseek-v4-pro | glm-5-1 |
| Author | DeepSeek | Z.ai |
| Released | Apr 24, 2026 | Apr 7, 2026 |
| Context window | 1M tokens | 202.7K tokens |
| Max output | 393,216 tokens | 128,000 tokens |
| Input | Text | Text |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Mode |
| Region | Germany | China |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/deepseek-v4-pro:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/glm-5-1:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | DeepSeek V4 Pro | GLM 5.1 |
|---|---|---|
| temperature | 0 to 2 Default: 0.7 | 0 to 1.99 Default: 1 |
| top_p | 0 to 1 Default: 0.9 | 0 to 1 Default: 0.95 |
| max_tokens | 1 to 393216 | 1 to 128000 |
| stop | string | array |
| enable_thinking | boolean Default: true | boolean Default: true |
| reasoning_effort | none, low, medium, high, max Default: medium | none, low, medium, high, max Default: medium |
| thinking_budget | 1 to 393216 Default: 32768 | 1 to 38912 Default: 32768 |
| response_format | enum | enum |
| web_search_linkup | boolean Default: false | boolean Default: false |
| disable_formatting | boolean Default: false | boolean Default: false |
| top_k | - | 1 to 100 Default: 20 |
| repetition_penalty | - | min 0.1 Default: 1 |
| tool_stream | - | boolean Default: false |
| tools | - | array Default: [] |
| tool_choice | - | object |
| parallel_tool_calls | - | boolean |
DeepSeek V4 Pro serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id deepseek-v4-pro. Both models are called through the same endpoint. Set model to deepseek-v4-pro or glm-5-1. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'DeepSeek V4 Pro is the newer release (Apr 24, 2026); GLM 5.1 was released on Apr 7, 2026. DeepSeek V4 Pro has the larger context window: 1M tokens, against 202.7K for GLM 5.1. DeepSeek V4 Pro returns up to 393,216 output tokens per response, GLM 5.1 up to 128,000. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
DeepSeek V4 Pro is the newer release (Apr 24, 2026); GLM 5.1 was released on Apr 7, 2026.
Both models list the same rate for Web Search (Linkup) (per call when invoked). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.