AI model
deepseek/deepseek-v4-flash
DeepSeek: DeepSeek V4 Flash 0423 is a 1,048,576-token model served on Composite at $0.103 per million tokens in and $0.206 per million tokens out. Ranked #45 of 179 models by traffic on Composite over the last 30 days, taking 0.19% of tokens and 0.19% of requests. Measured on Composite, 100.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 11647 ms, output runs at about 59.0 tokens per second.
Try in Playground| Model ID | deepseek/deepseek-v4-flash |
|---|---|
| Provider | cv11 |
| Context window | 1,048,576 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.103 per million tokens |
| Output price | $0.206 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 Flash 0423 (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | About 0.8 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Make a Composite API key and type deepseek/deepseek-v4-flash as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#45 of 179
0.19% of tokens and 0.19% of requests over 30 days.
100.0%
Across the last 100 requests Composite served for this model.
11647 ms
Median across the same sample.
59.0 tok/s
Median generation rate after the first token.
59.7%
Share of prompt tokens served from the provider's cache over 7 days.
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-flash-normal |
cv11 | $0.112 per million tokens input · $0.225 per million tokens output |
| Normal + cheapThink | deepseek/deepseek-v4-flash-normal:cheapThink |
cv11 | $0.112 per million tokens input · $0.225 per million tokens output |
| Cheapest provider | deepseek/deepseek-v4-flash:cheapest-provider |
StreamLake | $0.103 per million tokens input · $0.206 per million tokens output |
| Cheapest provider + cheapThink | deepseek/deepseek-v4-flash:cheapest-provider:cheapThink |
StreamLake | $0.103 per million tokens input · $0.206 per million tokens output |
| cheapThink | deepseek/deepseek-v4-flash:cheapThink |
cv11 | $0.103 per million tokens input · $0.206 per million tokens output |
| Fast | deepseek/deepseek-v4-flash:fast |
StreamLake | $0.103 per million tokens input · $0.206 per million tokens output |
| Fast + cheapThink | deepseek/deepseek-v4-flash:fast:cheapThink |
StreamLake | $0.103 per million tokens input · $0.206 per million tokens output |
| Quality | deepseek/deepseek-v4-flash:quality |
Parasail | $0.175 per million tokens input · $0.350 per million tokens output |
| Quality + cheapThink | deepseek/deepseek-v4-flash:quality:cheapThink |
Parasail | $0.175 per million tokens input · $0.350 per million tokens output |
$0.103 per million tokens input · $0.206 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 0.8 plan credits, at the provider's own price.
cv11
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.
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.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Supplied by cv11, not written by Composite.
DeepSeek: DeepSeek V4.1 Flash 1017 · DeepSeek: DeepSeek V4.1 Flash · DeepSeek: DeepSeek V4 Flash Vision Exp