rekaai
Reka Flash 3
rekaai/reka-flash-3
Input$0.100 /1M tokens
·Output$0.200 /1M tokens
Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...
Code Examples
import requests
response = requests.post(
"https://neurongate.net/v1/chat/completions",
headers={
"Authorization": "Bearer ng-your-api-key",
"Content-Type": "application/json"
},
json={
"model": "rekaai/reka-flash-3",
"messages": [
{"role": "user", "content": "Hello!"}
]
}
)
print(response.json()["choices"][0]["message"]["content"])Pricing Details
| Example | Cost |
|---|---|
| 1K input tokens (short prompt) | $0.00010 |
| 1K in + 500 out (typical response) | $0.00020 |
| 10K in + 2K out (document analysis) | $0.00140 |
| 100K in + 10K out (large context) | $0.0120 |
Prices in USD. Billed per actual token usage. Prepay with USDT, USDC, ETH, or BTC.
Frequently Asked Questions
Capabilities
Streaming
YesFunction Calling / Tools
NoVision (Image Input)
NoAudio Processing
NoContext Window
66K tokens
~49K words of text
Max output
66K tokens
Modalities
Input
text
Output
text