AI City Remix$11,500 prize pool. Pick a city, let AI tell its story, Oct 22 – 28.Join now

DeepSeek V3

deepseek/deepseek-chat

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.

Input price
$0.32USD / 1M tokens
Output price
$0.89USD / 1M tokens
Context window
163.8K
Max output
16.4K
Production route

Try the model

Playground

Open playground
Input⌘ / Ctrl + Enter

Try a prompt

163.8K context16.4K max output
Input$0.32/MOutput$0.89/M
OutputReady

Your response will appear here

Choose an example or write a prompt, then click Run.

Model card

Specifications

Pricing

Input
$0.32 / 1M tokens
Output
$0.89 / 1M tokens

Context & modalities

Context window
163,840 tokens
Max output
16,384 tokens
Input
Text
Output
Text

Capabilities

Chat
Supported
Vision
Not supported
Reasoning
Not supported
Structured output
Supported
Function calling
Supported
Audio input
Not supported

Access

Provider
DeepSeek
Model ID
deepseek/deepseek-chat
Execution
sync
Base URL
https://api.sandbase.ai
API
Chat Completions API
Endpoint
/v1/chat/completions

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Chat Completions API endpoint
https://api.sandbase.ai/v1/chat/completions
Model ID
deepseek/deepseek-chat
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/chat/completions" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "deepseek/deepseek-chat",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
DeepSeek V3This model
DeepSeek
160K$0.32$0.89Dec 26, 2024
DeepSeek1M$0.30$1.20Sep 10, 2026
DeepSeek1M$0.30$1.20Aug 21, 2026
DeepSeek1M$1.32$3.96Aug 12, 2026
DeepSeek1M$0.30$1.20Jul 31, 2026
DeepSeek1M$1.32$3.96Apr 24, 2026

Questions

FAQ

How do I call DeepSeek V3 through SandBase?

Create a SandBase API key, then send requests with the model ID "deepseek/deepseek-chat" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does DeepSeek V3 cost?

$0.32 per 1M input tokens and $0.89 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of DeepSeek V3?

163.8K tokens of context, with up to 16.4K output tokens per response.

Which features does DeepSeek V3 support?

DeepSeek V3 supports function calling, structured output. See Specifications above for the full list.

Do I need a separate DeepSeek account?

No. One SandBase API key and balance gives you access to DeepSeek V3 and the other models in the catalog; you do not need to sign up with DeepSeek separately.