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...
Context window
This model accepts 66K tokens in one request (~49K words of text).
What fits in one request
- FitsShort documentAbout 1,500 words of text
- FitsLong documentAbout 37K words of text
- Won't fitSmall codebaseAbout 150K words of text
- Won't fitFull novelAbout 375K words of text
Specifications
Context size, pricing, and release info in one place.
- Context window
- 65,536 tokens (66K)
- Max output tokens
- 65,536 tokens (66K)
- Speed tier
- fast
- Provider
- Reka Ai
- Release date
- Mar 2025
Capabilities
See which features this model supports, such as vision, tools, and streaming.
- Extended thinking
- Shows its chain-of-thought reasoning
- Supported
- Streaming
- Returns tokens as they are generated
- Supported
- Vision
- Accepts image inputs alongside text
- Not supported
- Tool use
- Can call external tools and APIs
- Not supported
- Function calling
- Structured function call interface
- Not supported
- Web search
- Can browse the web during a request
- Not supported
- Batch API
- Process many requests asynchronously
- Not supported
- Prompt caching
- Reuse repeated prompt prefixes cheaply
- Not supported
Best for
Jump to a guide or ranking that matches each workload.
Compare Reka Flash 3
Open a side-by-side comparison with one click.
- Reka Flash 3 vs Amazon Titan Text Express
Reka Flash 3 has 56% larger context window
- Reka Flash 3 vs Amazon Titan Text Lite
Reka Flash 3 has 56% larger context window
- Reka Flash 3 vs Amazon Titan Text Premier
Reka Flash 3 has 56% larger context window
- Reka Flash 3 vs Claude Instant
Claude Instant has 52% larger context window
- Reka Flash 3 vs Anthropic Claude
Anthropic Claude has 52% larger context window
- Reka Flash 3 vs Codellama 34b Instruct
Reka Flash 3 has 1500% larger context window
Frequently asked questions
Short answers about context size and how this model behaves.
More from Reka Ai
Other models by Reka Ai in our catalog.
Powered by Mem0
Use a smaller model.
Get better results.
Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.
Example: a multi-turn chat session
80% less to send — works with any model