Skip to main content

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 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient quantization (down to 11GB at 4-bit precision), and employs explicit reasoning tags (" ") to indicate its internal thought process. Reka Flash 3 is primarily an English model with limited multilingual understanding capabilities. The model weights are released under the Apache 2.0 license.

Input / output price
$0.10 / $0.20 per 1M
Context
66K tokens
Released
Mar 10, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "reka-flash-3".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
OpenRouteropenrouter/reka-flash-3
$0.10/M$0.20/M

Is a provider down? OpenRouter status

Pricing

USD per 1M tokens on OpenRouter, after gateway discounts.

Input
$0.10 per 1M
Output
$0.20 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.10/MOpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

3.6tokens/sacross providers

Faster than 5% of the other 599 models on the gateway

Response latency

Lower is better

0.3sacross providers

Faster than 94% of the other 780 models on the gateway

Benchmarks

3 published scores from 2 sources, each linked to where it was published.

Published scores

BenchmarkScore
BALROGBALROG29.2%

Apps

Use Reka Flash 3 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Reka Flash 3 FAQ

Short answers, built from the data on this page.

Reka Flash 3 is a model from Reka, released on Mar 10, 2025. 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 32K context length and optimized through reinforcement learning (RLOO), it provides competitive performance comparable to proprietary models within a smaller parameter footprint. Ideal for low-latency, local, or on-device deployments, Reka Flash 3 is compact, supports efficient quantization (down to 11GB at 4-bit precision), and employs explicit reasoning tags (" ") to indicate its internal thought process. Reka Flash 3 is primarily an English model with limited multilingual understanding capabilities. The model weights are released under the Apache 2.0 license.

On the Respan gateway, Reka Flash 3 costs $0.10 per 1M input tokens and $0.20 per 1M output tokens on OpenRouter, after gateway discounts.

Reka Flash 3 is served by OpenRouter.

Reka Flash 3 accepts up to 66K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "reka-flash-3". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Reka Flash 3 has 3 published benchmark scores, including BALROG 29.2%, MMLU-Pro 65%, and WMT'23 (COMET) 83.2. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.