Reka: Flash 3
Analysis Summary
Reka Flash 3 is a text-only model with a 65K context window and function calling. Its benchmark results show limited overall intelligence and weak instruction-following performance, while the coding and math measurements offer some narrow task potential. Listed pricing is $0.10 per million input tokens and $0.20 per million output tokens, which supports inexpensive experimentation.
That cost profile could suit low-risk, lightweight text processing where quality requirements are modest and outputs are checked. The available results do not support relying on it for nuanced client-facing copy, complex reasoning, or dependable coding work. Function calling is available, but the supplied data does not show an agentic index that would establish strong multi-step execution.
Use Flash 3 only for tightly scoped, low-cost tasks after validating outputs against the team's own examples. Keep human review in place for published content and operational decisions.
Assessed September 23, 2026
Editorial notes
Reka Flash 3 is an inexpensive text model with function calling and a 65K context, but its measured reasoning and instruction-following results are weak.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
Reka Flash 3 is an inexpensive text model with function calling and a 65K context, but its measured reasoning and instruction-following results are weak.
Benchmarks
Artificial Analysis data refreshed Nov 9, 2026. Arena ratings from the Oct 28, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.
Artificial Analysis has not published coding or agentic results for Reka: Flash 3 yet. Until it does, the model sits below tested models on the Coding and AI Agents lists.
Artificial Analysis no longer lists this model, so its indexes are converted from their older scale to stay comparable.
How Reka: Flash 3 compares
Reka: Flash 3 ranks #383 of 449 AI models we track for overall intelligence. Its 66K-token context window is larger than 29% of the models we list. At $0.10 per million input tokens it is cheaper than 65% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.10 | $0.000100 |
| Output | $0.20 | $0.000200 |
What would Reka: Flash 3 cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 735 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save Reka: Flash 3 for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout 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..
Frequently asked questions about Reka: Flash 3
How much does Reka: Flash 3 cost?
Reka: Flash 3 costs $0.10 per million input tokens and $0.20 per million output tokens.
What is the context window of Reka: Flash 3?
Reka: Flash 3 has a context window of 65,536 tokens (66K).
What can Reka: Flash 3 do?
Reka: Flash 3 supports function calling.
Who created Reka: Flash 3?
Reka: Flash 3 is developed by Reka and was released on March 12, 2025.