Start free trial

Reka Flash 3

rekaai/reka-flash-3
CompareAPITry this model

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.

Modalities
In / out per 1M$0.10 / $0.20
Context64K
ReleasedMar 12, 2025

Providers

1 provider serves this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Reka AI$0.10$0.20Variable0.98s86 tps100%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Reka Flash 3 in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Reka Flash 3 costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.10
per 1M tokens
Output
$0.20
per 1M tokens
Cache read
—
not published
Included in every pass
Reka Flash 3 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s20.0s40.0s60.0s80.0s
Oct 16, 9 AMOct 17, 9 PMOct 18, 3 PM
Median 90th percentile 99th percentile
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 16, 9 AMOct 17, 9 PMOct 18, 3 PM
Median 90th percentile 99th percentile

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 88.5%
Oct 16, 12:00 PMNow
Availability over the last 24 hoursAvailability 85.82%
100% 81% 63% 45%
Oct 18, 12:20 PMNow

Apps

Tools that most often run Reka Flash 3, by tokens this week.

ADM SFS Jev calibrated benchmark31.3% of tokens2.8MHello HavenPersonal Agent · 23.4% of tokens2.1MModel Tested18.9% of tokens1.7MKingsdaq Fusion315% of tokens1.3MSpin11.4% of tokens1.0M

Activity

241.4M tokens processed market-wide in the last month.

010.0M20.0M30.0M40.0M
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens

FAQ

Which model id do I use for Reka Flash 3?
rekaai/reka-flash-3. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Reka Flash 3 hold?
65,536 tokens per request, of which up to 58,982 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Reka Flash 3 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.10 per 1M input tokens and $0.20 per 1M output tokens.
How current is its knowledge?
Training data runs to Jan 2025. Anything later has to come from your prompt or a tool call.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion