UltraGPT
Reka Flash 3
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...
Intelligence overview
65.5K tok
Context window
59.0K tok
Max output
What Reka Flash 3 can do.
Reasoning
Extended reasoning
Works through problems step by step before answering, trading latency for accuracy on harder tasks.
Development
Structured output
Returns responses constrained to a JSON schema, ready to parse without cleanup.
Streaming
Streams tokens as they're generated instead of waiting on the full response.
Pay for what you use.
Every model in UltraGPT runs behind one flat subscription — this is the underlying per-token cost the catalog tracks.
$0.1 / 1M tok
$0.2 / 1M tok
Built for serious work.
Build
Generate and refactor code, with the ability to return structured, parseable output.
Think
Works through multi-step problems with extended reasoning before it answers.
Ask Reka Flash 3 anything.
A preview of the real UltraGPT composer — the model you see here is the model you get.
Continues in the UltraGPT app — one login, every model.
How Reka Flash 3 stacks up.
The closest models in the catalog by provider, capability and score — real entries, pulled from the same directory.
Technical details.
Specification
- Context window
- 65.5K tokens
- Max output
- 59.0K tokens
- Input modalities
- Text
- Output modalities
- Text
- Knowledge cutoff
- Jan 31, 2025
- Release date
- Mar 12, 2025
- Streaming
- Supported
- Tool calling
- Not supported
- JSON mode
- Supported
More from Rekaai, and everything else.
This model is one entry in the full UltraGPT catalog — browse the rest, compare pricing and context windows, or filter by capability.