Reka Flash 3 API

rekaai/reka-flash-3
Reka Flash 3 on AIMLAPI.
Context
64K tokens
Input
$0.1058 / 1M tokens
Output
$0.2116 / 1M tokens
Released
Mar 12, 2025

Overview

What is Reka Flash 3 API?

Reka Flash 3 is available through AIMLAPI.

Technical Specifications
- Supported inputs: Image, Text
- Output: Text
- Context window: 65,536 tokens / Max output: 65,536 tokens
- Endpoint: /chat/completions

Performance Benchmarks
[embed]

Reka Flash 3 API Pricing
- Input: $0.13 / 1M tokens
- Output: $0.26 / 1M tokens

Where to Use Reka Flash 3

Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.

Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.

Complex reasoning
Extended reasoning improves reliability on multi-step math, logic, and technical analysis.

Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.

Code Sample
[embed]

Uptime and performance

  • Uptime (7d): 100%

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Reka Flash 3 is documented as a good foundation for applications that require low latency or on-device deployment.

It is also described as powering Nexus, a platform for organizations to create and manage AI workers, with those workers able to browse the web, execute code, and analyze internal files such as documents, images, videos, and audio.

Another documented use case is general chat, coding, instruction following, and function calling.

It is also recommended for knowledge-related tasks when paired with web search, since the model is described as not the best choice for knowledge-intensive tasks on its own.

How to use Reka Flash 3 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to rekaai/reka-flash-3.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "rekaai/reka-flash-3",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "rekaai/reka-flash-3",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"rekaai/reka-flash-3","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Reka Flash 3 API Pricing

TypePrice
Input
$0.1058 / 1M tokens
Output
$0.2116 / 1M tokens

Reka Flash 3 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
LiveCodeBench
43.5%
Contamination-free competitive programming problemsSourceJuly 12, 2026
MMLU-Pro
65%
Multi-discipline knowledge + reasoning (harder MMLU)SourceJuly 12, 2026
GPQA Diamond
53.5%
Google-proof graduate science questions (hardest subset)SourceJuly 12, 2026
Intelligence
5.6
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Math
33.7
Composite score across standardised mathematics evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Reka Flash 3 vs other models

ModelInputOutputContextBest for
Reka Flash 3
This page
$0.1058 / 1M tokens
$0.2116 / 1M tokens
64K tokens
Reasoning + agents
$5 / 1M tokens
$30 / 1M tokens
1M tokens
Reasoning + agents
$2 / 1M tokens
$10 / 1M tokens
1M tokens
Balanced coding + agents
$3 / 1M tokens
$15 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$1.5 / 1M tokens
$9 / 1M tokens
1M tokens
Reasoning + agents

Frequently asked questions

Reka Flash 3 has a 65,536 tokens context window and can return up to 65,536 tokens.

Reka Flash 3 takes image, text as input and returns text.

Use rekaai/reka-flash-3 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Reka Flash 3 is priced at input $0.13754 / 1M tokens, output $0.27508 / 1M tokens.

Yes, Reka Flash 3 can stream responses as they are generated.

Yes, Reka Flash 3 accepts image input alongside text.

Yes, Reka Flash 3 supports function calling as one of its capabilities.

Yes, it supports parallel tool calls along with general tool use.

Start building with Reka Flash 3

Get API Key
1000+ models, one API.