ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Aion-RP 1.0 (8B) vs Qwen2.5-VL 72B Instruct vs Reka Flash 3

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. Aion Labs

    Aion-RP 1.0 (8B)

    Released Feb 4, 2025

    4/100
    • ECI—
    • Price$0.80 / $1.60
    • Context33K
  2. Alibaba (Qwen)

    Qwen2.5-VL 72B Instruct

    Released Jan 26, 2025

    43/100
    • ECI—
    • Price$1.01 / $1.01
    • Context131K
  3. Reka AI

    Reka Flash 3

    Released Mar 10, 2025

    15/100
    • ECI—
    • Price$0.10 / $0.20
    • Context66K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-VL 72B Instruct 43/100, Reka Flash 3 15/100, Aion-RP 1.0 (8B) 4/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceReka Flash 3Reka Flash 3 $0.125 · Aion-RP 1.0 (8B) $1.00 · Qwen2.5-VL 72B Instruct $1.01 per 1M tokens (3:1 blend)
  • Longest contextQwen2.5-VL 72B InstructQwen2.5-VL 72B Instruct 131,072 · Reka Flash 3 65,536 · Aion-RP 1.0 (8B) 32,768 tokens
  • Widest inputsQwen2.5-VL 72B InstructAion-RP 1.0 (8B): Text · Qwen2.5-VL 72B Instruct: Text, Images · Reka Flash 3: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightAion-RP 1.0 (8B)Qwen2.5-VL 72B InstructReka Flash 3
Inputs & features60%05010
Context window40%113222
Specs only100%4/10043/10015/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Aion-RP 1.0 (8B) vs Qwen2.5-VL 72B Instruct vs Reka Flash 3 specifications side by side
SpecificationAion-RP 1.0 (8B)Aion LabsQwen2.5-VL 72B InstructAlibaba (Qwen)Reka Flash 3Reka AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.80$1.01$0.10 (best)
Output$1.60$1.01$0.20 (best)
Cached input———
Blended (3:1)$1.00$1.01$0.125 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 4 providersMedian of 5 providersMedian of 3 providers
Limits
Context window32,768 tokens131,072 tokens (best)65,536 tokens
Max output29,491 tokens8,192 tokens58,982 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingNoYesNo
Structured outputNoNoNo
Availability
WeightsOpenOpenOpen
API model ID———
API providers45 (best)3
ReleasedFeb 4, 2025Jan 26, 2025Mar 10, 2025
Knowledge cutoffDec 31, 2023Apr 2024Jan 31, 2025
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Aion-RP 1.0 (8B)$11.20
  • Qwen2.5-VL 72B Instruct$12.12
  • Reka Flash 3$1.40
04 — Questions

Which should you choose?

Which is better: Aion-RP 1.0 (8B), Qwen2.5-VL 72B Instruct or Reka Flash 3?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-VL 72B Instruct 43/100, Reka Flash 3 15/100, Aion-RP 1.0 (8B) 4/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Aion-RP 1.0 (8B), Qwen2.5-VL 72B Instruct or Reka Flash 3?

Reka Flash 3 is cheaper at $0.10 input / $0.20 output per million tokens (median across 3 API providers). Aion-RP 1.0 (8B) costs $0.80 input / $1.60 output per million tokens (median across 4 API providers); Qwen2.5-VL 72B Instruct costs $1.01 input / $1.01 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.125 per million tokens for Reka Flash 3 versus $1.00 for Aion-RP 1.0 (8B) (8× as much) and $1.01 for Qwen2.5-VL 72B Instruct (8.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Aion-RP 1.0 (8B) has not been scored yet, Qwen2.5-VL 72B Instruct has not been scored yet and Reka Flash 3 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Aion-RP 1.0 (8B), Qwen2.5-VL 72B Instruct and Reka Flash 3 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aion-RP 1.0 (8B) and Reka Flash 3 does not support tool calling, which most coding agents need.

Which has the bigger context window?

Qwen2.5-VL 72B Instruct has the largest context window at 131,072 tokens, against 65,536 for Reka Flash 3 and 32,768 for Aion-RP 1.0 (8B). Maximum output per response: Aion-RP 1.0 (8B) up to 29,491, Qwen2.5-VL 72B Instruct up to 8,192, Reka Flash 3 up to 58,982 tokens.

Which can read images, PDFs, audio or video?

Aion-RP 1.0 (8B) accepts text; Qwen2.5-VL 72B Instruct accepts text and images; Reka Flash 3 accepts text. Qwen2.5-VL 72B Instruct handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights, so you can self-host them.

Which is newer?

Reka Flash 3 is the newest, released Mar 10, 2025. Aion-RP 1.0 (8B) came out Feb 4, 2025; Qwen2.5-VL 72B Instruct came out Jan 26, 2025. Knowledge cutoff: Aion-RP 1.0 (8B) Dec 31, 2023, Qwen2.5-VL 72B Instruct Apr 2024, Reka Flash 3 Jan 31, 2025.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.