● DeepSeek · chat
DeepSeek V3
SAMPLE: DeepSeek's general-purpose MoE chat model for coding, reasoning, and long documents.
Input / 1M tokens$0.27
Output / 1M tokens$1.10
Context128K
Example: 1M input + 1M output tokens = $1.37
Call DeepSeek V3
OpenAI-compatible. Use any OpenAI SDK with the Keyra base URL and your key.
curl
curl https://api.keyra.example/v1/chat/completions \
-H "Authorization: Bearer $KEYRA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v3", "messages": [{"role": "user", "content": "Hello"}]}'Python · openai SDK
import os
from openai import OpenAI
client = OpenAI(base_url="https://api.keyra.example/v1", api_key=os.environ["KEYRA_API_KEY"])
reply = client.chat.completions.create(
model="deepseek-v3",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)Related models
| Model | Creator | Type | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Llama 3.3 70B | Meta | chat | 128K | $0.23 | $0.40 |
| Qwen3 32B | Qwen | chat | 40K | $0.10 | $0.30 |
| Gemma 3 27B | chat | 128K | $0.09 | $0.17 |