Reka Flash 3: AI model
Reka Flash 3 is Reka's 21B instruction-tuned model with explicit reasoning and a 65K-token context. Reachable from inside Iran through Hormouz.
- Context window:
- 65,536 tokens
- Input:
- $0.1/1M tokens
- Output:
- $0.2/1M tokens
- Type:
- text
- Streaming
Thinking levels: Always thinks
Reka Flash 3 is a general-purpose, instruction-tuned 21B-parameter model from Reka. It handles general chat, coding, instruction-following and function calling, and uses explicit reasoning tags to expose its internal thought process.
Tuned with reinforcement learning, it offers competitive quality within a compact footprint and is well suited to low-latency or on-device deployments. It is primarily an English-language model.
Through Hormouz, Reka Flash 3 is served behind an OpenAI-compatible API. Point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged. Pricing is usage-based: $0.1 per million input tokens and $0.2 per million output tokens, with no fixed monthly fee.
Hormouz provides stable access to Reka Flash 3 from inside Iran, with no foreign credit card or circumvention tooling required.
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...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "rekaai/reka-flash-3",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Reka AI |
|---|---|
| Type | Text |
| Context window | 65,536 tokens |
| Pricing | $0.10/M in · $0.20/M out |
| API | Chat Completions |
| Capabilities | Streaming |
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "rekaai/reka-flash-3",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="rekaai/reka-flash-3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "rekaai/reka-flash-3",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Reka Flash 3 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Reka Flash 3 and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- What is Reka Flash 3 and what is it good for?
- Reka Flash 3 is Reka's compact instruction-tuned model with explicit reasoning for chat and coding.
- What is the context window of Reka Flash 3?
- It supports up to 65K tokens of context, which suits coding tasks and multi-turn chat.
- How much does Reka Flash 3 cost?
- Pricing is usage-based: $0.1 per million input tokens and $0.2 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
- How do I access Reka Flash 3 from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to Reka Flash 3 from inside Iran, with no foreign credit card required.
- Is Reka Flash 3 compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
Updated 2026-10-13