Traffic rank on Composite
#10 of 196
3.65% of tokens and 3.43% of requests over 30 days, including routing variants.
AI model
DeepSeek: DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813
DeepSeek: DeepSeek V4 Pro 0813 is a 1,048,576-token model served on Composite at $0.312 per million tokens in and $0.936 per million tokens out. Ranked #10 of 196 models by traffic on Composite over the last 30 days, taking 3.65% of tokens and 3.43% of requests (this model and its routing variants). Measured on Composite, 92.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 14577 ms, output runs at about 70.3 tokens per second.
Try in PlaygroundSpecifications
| Model ID | deepseek/deepseek-v4-pro-0813 |
|---|---|
| Provider | cv11 |
| Context window | 1,048,576 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.312 per million tokens |
| Output price | $0.936 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Optional - see "DeepSeek: DeepSeek V4 Pro 0813 (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | About 2.7 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Success rate
92.0%
Across the last 100 requests Composite served for this model.
Time to first token
14577 ms
Median across the same sample.
Output speed
70.3 tok/s
Median generation rate after the first token.
Prompt cache hits
48.9%
Share of prompt tokens served from the provider's cache over 7 days.
Routing variants
The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | deepseek/deepseek-v4-pro-0813-normal |
cv11 | $0.825 per million tokens input · $2.48 per million tokens output |
| Normal + cheapThink | deepseek/deepseek-v4-pro-0813-normal:cheapThink |
cv11 | $0.825 per million tokens input · $2.48 per million tokens output |
| Cheapest provider | deepseek/deepseek-v4-pro-0813:cheapest-provider |
Baidu | $0.312 per million tokens input · $0.936 per million tokens output |
| Cheapest provider + cheapThink | deepseek/deepseek-v4-pro-0813:cheapest-provider:cheapThink |
Baidu | $0.312 per million tokens input · $0.936 per million tokens output |
| cheapThink | deepseek/deepseek-v4-pro-0813:cheapThink |
cv11 | $0.312 per million tokens input · $0.936 per million tokens output |
| Fast | deepseek/deepseek-v4-pro-0813:fast |
Baidu | $0.312 per million tokens input · $0.936 per million tokens output |
| Fast + cheapThink | deepseek/deepseek-v4-pro-0813:fast:cheapThink |
Baidu | $0.312 per million tokens input · $0.936 per million tokens output |
| Quality | deepseek/deepseek-v4-pro-0813:quality |
CoreWeave | $1.64 per million tokens input · $4.95 per million tokens output |
| Quality + cheapThink | deepseek/deepseek-v4-pro-0813:quality:cheapThink |
CoreWeave | $1.64 per million tokens input · $4.95 per million tokens output |
Pricing
$0.312 per million tokens input · $0.936 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 2.7 plan credits, at the provider's own price.
Provider
cv11
Roleplay fit
DeepSeek models are known for strong reasoning and coding ability at aggressive pricing, which makes them a common pick for roleplay accounts that send a high volume of messages.
Context behavior
With a 1,048,576-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
Cost for regular use
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
From the provider
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Supplied by cv11, not written by Composite.
Related models
DeepSeek: DeepSeek V4.1 Flash · DeepSeek: DeepSeek V4 Flash Vision Exp · DeepSeek: DeepSeek V4 Flash 0731