DeepSeek's fast, low-cost model - currently DeepSeek V4.1 Flash, with text and image input. Thinking mode is on by default, with a 1M-token context window, up to 384K output tokens, and cache reads at ~98% off. $0.30 input / $1.20 output per million tokens.
Test this model instantly in the Console Playground โ no code required
Copy usage instructions for Claude, ChatGPT, or other AI
| Token Type | Credits | USD Equivalent |
|---|---|---|
| Input Tokens | 557 | $0.37 |
| Output Tokens | 2,230 | $1.49 |
| Cached Tokens | 11.148 | $0.01 |
* 1,500 credits โ $1 (actual charges may vary based on usage)
curl -X POST "https://api.core.today/llm/deepseek/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer cdt_your_api_key" \
-d '{
"model": "deepseek-flash",
"messages": [
{
"role": "user",
"content": "Explain vector databases in 3 sentences."
}
],
"max_tokens": 1024
}'| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Yes | - | Model ID, e.g. "deepseek-flash". |
messages | array | Yes | - | Chat messages in OpenAI format (system/user/assistant roles). |
temperature | number | No | 0.7 | Sampling temperature (0-2). |
max_tokens | integer | No | 2048 | Maximum completion tokens. |
stream | boolean | No | false | Stream the response as server-sent events. |
OpenAI-compatible chat completion request
curl -X POST "https://api.core.today/llm/deepseek/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer cdt_your_api_key" \
-d '{
"model": "deepseek-flash",
"messages": [
{
"role": "user",
"content": "Explain vector databases in 3 sentences."
}
],
"max_tokens": 1024
}'POST /llm/deepseek/v1/chat/completions