AI model

DeepSeek: R1 0528

Name: DeepSeek: R1 0528
Brand: cv11
Price: 0.6250 USD
Availability: InStock

deepseek/deepseek-r1-0528

DeepSeek: R1 0528 is a 163,840-token model served on Composite at $0.625 per million tokens in and $2.69 per million tokens out. Ranked #54 of 196 models by traffic on Composite over the last 30 days, taking 0.5% of tokens and 0.44% of requests (this model and its routing variants). Measured on Composite, 100.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 15756 ms, output runs at about 39.2 tokens per second.

Try in Playground

Community rating

— No community ratings yet.

Specifications

Specifications and pricing as served by Composite
Model ID	deepseek/deepseek-r1-0528
Provider	cv11
Context window	163,840 tokens
Accepts	text
Returns	text
Input price	$0.625 per million tokens
Output price	$2.69 per million tokens
Prompt caching	Supported — cached input is billed at the provider's cache rate, on credits and plans alike
Thinking	Always on for this model
Moderated	No
Cost on a monthly plan	About 6.2 plan credits per typical call (8k in, 1k out)
Routing endpoints	10 (base plus 9 routing variants)

Traffic rank on Composite

#54 of 196

0.5% of tokens and 0.44% of requests over 30 days, including routing variants.

Success rate

100.0%

Across the last 100 requests Composite served for this model.

Time to first token

15756 ms

Median across the same sample.

Output speed

39.2 tok/s

Median generation rate after the first token.

Prompt cache hits

56.7%

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-r1-0528-normal`	cv11	$0.625 per million tokens input · $2.69 per million tokens output
Normal + cheapThink	`deepseek/deepseek-r1-0528-normal:cheapThink`	cv11	$0.625 per million tokens input · $2.69 per million tokens output
Cheapest provider	`deepseek/deepseek-r1-0528:cheapest-provider`	DeepInfra	$0.625 per million tokens input · $2.69 per million tokens output
Cheapest provider + cheapThink	`deepseek/deepseek-r1-0528:cheapest-provider:cheapThink`	DeepInfra	$0.625 per million tokens input · $2.69 per million tokens output
cheapThink	`deepseek/deepseek-r1-0528:cheapThink`	cv11	$0.625 per million tokens input · $2.69 per million tokens output
Fast	`deepseek/deepseek-r1-0528:fast`	DeepInfra	$0.625 per million tokens input · $2.69 per million tokens output
Fast + cheapThink	`deepseek/deepseek-r1-0528:fast:cheapThink`	DeepInfra	$0.625 per million tokens input · $2.69 per million tokens output
Quality	`deepseek/deepseek-r1-0528:quality`	SiliconFlow	$0.625 per million tokens input · $2.72 per million tokens output
Quality + cheapThink	`deepseek/deepseek-r1-0528:quality:cheapThink`	SiliconFlow	$0.625 per million tokens input · $2.72 per million tokens output

Pricing

$0.625 per million tokens input · $2.69 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 6.2 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 163,840-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 sits in the mid-range on price, a reasonable pick for regular roleplay use without going for the cheapest option available.

From the provider

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

Supplied by cv11, not written by Composite.