Traffic rank on Composite
#105 of 196
0.02% of tokens and 0.04% of requests over 30 days.
AI model
DeepSeek: DeepSeek V4 Flash 0731 (Free)
deepseek/deepseek-v4-flash-0731:free
DeepSeek: DeepSeek V4 Flash 0731 (Free) is a 1,048,576-token model free on Composite. Ranked #105 of 196 models by traffic on Composite over the last 30 days, taking 0.02% of tokens and 0.04% of requests. 100% positive from 5 votes by Composite users who have run requests through the platform. Measured on Composite, 80.3% of its last 66 requests on Composite succeeded, the typical first token arrives in 6864 ms, output runs at about 21.6 tokens per second.
Try in PlaygroundSpecifications
| Model ID | deepseek/deepseek-v4-flash-0731:free |
|---|---|
| Provider | cv11 |
| Context window | 1,048,576 tokens |
| Accepts | text |
| Returns | text |
| Input price | Included in free allowance |
| Output price | Included in free allowance |
| 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 0731 (Free) (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | Free - does not spend plan credits |
| Routing endpoints | 1 |
Success rate
80.3%
Across the last 66 requests Composite served for this model.
Time to first token
6864 ms
Median across the same sample.
Output speed
21.6 tok/s
Median generation rate after the first token.
Prompt cache hits
23.1%
Share of prompt tokens served from the provider's cache over 7 days.
Pricing
Free - 80 requests/day shared across free models
Credits pay the provider’s price plus 25%; cache hits cost less.
Monthly plans serve this model without spending any of their included credits.
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 free on Composite, which makes it a reasonable place to test a character card, preset or lorebook before connecting your own provider.
From the provider
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Supplied by cv11, not written by Composite.
Related models
DeepSeek: DeepSeek V4.1 Flash · DeepSeek: DeepSeek V4 Flash Vision Exp · DeepSeek: DeepSeek V4 Pro 0813