rekaai
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.
At a glance
- Input / 1M
- $0.10
- Output / 1M
- $0.20
- Context
- 66K
- Max output
- 59K
- Intelligence
- 6.4
- Released
- Mar 2025
Pricing
Reka Flash 3 API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.10 |
|---|---|
| Output tokensPer 1M tokens | $0.20 |
| Cached input (read)Per 1M tokens | Not available |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.30
per 1,000 requests
Coding task
30K in, 4K out
$3.80
per 1,000 requests
Long document summary
150K in, 2K out
$15.40
per 1,000 requests
Benchmarks
Reka Flash 3 benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
6.4
Coding index
Not available
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 66K tokens
- Max output
- 59K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- March 12, 2025
- Knowledge cutoff
- January 31, 2025
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Reka Flash 3 vs other models
See how Reka Flash 3 stacks up head to head on price, benchmarks, and features.
VS
Reka Flash 3 vs Qwen3 14B
rekaai vs Qwen
See comparisonVSReka Flash 3 vs Qwen3 30B A3B Instruct 2507
rekaai vs Qwen
See comparisonVSReka Flash 3 vs Llama 3.1 8B Instruct
rekaai vs Meta
See comparisonVS
Reka Flash 3 vs GPT-4o-mini
rekaai vs OpenAI
See comparisonVS
Reka Flash 3 vs Nova Lite 1.0
rekaai vs Amazon
See comparisonVS
Reka Flash 3 vs Ministral 3 14B 2512
rekaai vs Mistral
See comparisonAlternatives
Reka Flash 3 alternatives
Similar models worth considering, and where each one has the edge.
Qwen
Qwen3 14B
Qwen
Qwen3 30B A3B Instruct 2507
Meta
Llama 3.1 8B Instruct
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Reka Flash 3 cost?
Reka Flash 3 costs $0.10 per 1M input tokens and $0.20 per 1M output tokens through the API. A typical chat message costs about $0.30 per 1,000 messages.
What is the context window of Reka Flash 3?
Reka Flash 3 accepts up to 66K tokens of input and can write up to 59K tokens in a single response.
What is the best alternative to Reka Flash 3?
Qwen3 14B from Qwen is a strong alternative. It offers: higher intelligence score, newer release.
Can I use Reka Flash 3 alongside other models?
Yes. Shortcut Chat sends one prompt to Reka Flash 3 and any other models you pick at the same time, so you can compare answers side by side.
Try Reka Flash 3 next to every other model.
Use Reka Flash 3 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.