Reka Flash 3
RekaReleased Mar 12, 2025
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...
- Context window
- 66K tokens
- Max output
- 66K tokens
- Input
- text
- Output
- text
- Tokenizer
- Other
- Knowledge cutoff
- Jan 31, 2025
- Released
- Mar 12, 2025
- Reasoning
- always on
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | $0.100 | $0.0030 | $0.103 |
| Output | $0.200 | $0.0060 | $0.206 |
Supported parameters
- frequency_penalty
- include_reasoning
- logprobs
- max_tokens
- presence_penalty
- reasoning
- seed
- stop
- structured_outputs
- temperature
- top_k
- top_logprobs
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model rekaai/reka-flash-3.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "rekaai/reka-flash-3",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="rekaai/reka-flash-3",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "rekaai/reka-flash-3",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);Questions
- How much does Reka Flash 3 cost via API?
- Through OpenKey, Reka Flash 3 costs $0.103 per 1M input tokens and $0.206 per 1M output tokens. That is the provider price ($0.100 / $0.200) plus a flat 3% fee — nothing else.
- What is Reka Flash 3's context window?
- Reka Flash 3 accepts up to 66K tokens of context and returns up to 66K tokens per request.
- Is Reka Flash 3 OpenAI-compatible?
- Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "rekaai/reka-flash-3" using any OpenAI SDK — only the base URL and API key change.
- What inputs does Reka Flash 3 support?
- Reka Flash 3 accepts text input and produces text output. Its knowledge cutoff is Jan 31, 2025.