DeepSeek V4 Pro 0813
by DeepSeekdeepseek/deepseek-v4-pro-0813
LLMCompare cannot run DeepSeek V4 Pro 0813 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.
See the models that can be run nowDeepSeek V4 Pro 0813 at a glance
- Context length
- 1,048,576 tokens
- Maximum output
- 393,216 tokens
- Accepts
- Text
- Returns
- Text
- Features
- ReasoningJSON outputTool callingPrompt caching
- Reasoning effort levels
maxhighlownoneReasoning can be turned off.- Released
- 12 Aug 2026
- Knowledge cutoff
- Not published
Model facts synced from the OpenRouter model list on 21 Oct 2026.
DeepSeek V4 Pro 0813 pricing by route
A route is the service LLMCompare calls to reach the model. DeepSeek V4 Pro 0813 has 1 route. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Cache readper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|---|
| OpenRouterDefault | Not configured | $0.66 | $1.98 | $0.022 | openrouter.ai/deepseek/deepseek-v4-pro-0813 |
The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.
Cost calculator
Estimate what a batch of calls to DeepSeek V4 Pro 0813 costs. The starting numbers are examples. Change them to match your task.
Part of the input tokens above, billed at the cache read price.
Billed in addition to the output tokens.
- Cost per call
- $0.0017
- 2 credits
- Cost of 100 calls
- $0.165
- 200 credits
Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.
Parameters you can set
These are the parameters LLMCompare can set when it calls the model through OpenRouter.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
temperature | Number | 0 to 2in steps of 0.1 | Provider default |
top_p | Number | 0 to 1in steps of 0.05 | Provider default |
max_tokens | Integer | 1 to 393,216 | Provider default |
reasoning_effort | One of | maxhighlownone | high |
seed | Integer | -2,147,483,648 to 4,294,967,295 | Provider default |
response_format | One of | textjson_object | Provider default |
About DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Description as published for this model. LLMCompare has not edited it.
Models to compare with DeepSeek V4 Pro 0813
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
R1 0528DeepSeekdeepseek/deepseek-r1-0528 | 164k | 32.8k | $0.50 | $2.15 | JSONToolsCache | No route yet | ||
DeepSeek V3 0324DeepSeekdeepseek/deepseek-chat-v3-0324 | 164k | 115k | $0.29 | $1.14 | JSONToolsCache | No route yet | ||
DeepSeek V3DeepSeekdeepseek/deepseek-chat | 164k | 16k | $0.2574 | $1.03 | JSONTools | No route yet | ||
Qwen3.5 397B A17BQwenqwen/qwen3.5-397b-a17b | 262k | 65.5k | $0.39 | $2.34 | JSONToolsVision | No route yet | ||
GLM 4.6Z.aiz-ai/glm-4.6 | 205k | 131k | $0.55 | $2.20 | JSONToolsCache | No route yet | ||
MiniMax M1MiniMaxminimax/minimax-m1 | 1M | 40k | $0.55 | $2.20 | Tools | No route yet |
Questions about DeepSeek V4 Pro 0813
- How much does DeepSeek V4 Pro 0813 cost?
- On the OpenRouter route, DeepSeek V4 Pro 0813 costs $0.66 per 1 million input tokens and $1.98 per 1 million output tokens, in US dollars. Input tokens that DeepSeek V4 Pro 0813 reads from the prompt cache cost $0.022 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
- What is the context length of DeepSeek V4 Pro 0813?
- DeepSeek V4 Pro 0813 has a context length of 1,048,576 tokens and returns up to 393,216 output tokens in one call.
- What inputs does DeepSeek V4 Pro 0813 accept?
- DeepSeek V4 Pro 0813 accepts these inputs: Text. DeepSeek V4 Pro 0813 returns: Text.
- Which reasoning effort levels does DeepSeek V4 Pro 0813 support?
- DeepSeek V4 Pro 0813 supports these reasoning effort levels: max, high, low, none. Reasoning can be turned off for DeepSeek V4 Pro 0813.
- Can I test DeepSeek V4 Pro 0813 on my own data?
- Not yet. LLMCompare lists the prices and parameters of DeepSeek V4 Pro 0813, but no route to DeepSeek V4 Pro 0813 is configured on LLMCompare, so it cannot be selected for an evaluation.