TokenPricing

Raon-1 mini preview

Calculate
Caching
Official pricing
$0.00 / $0.00
Input / Output · KRAFTON official API
Lowest input
$0.00
KRAFTON official API
Context
262.1K

Raon-1 mini preview · Specifications

Specifications
Availability / pricingRaon-1 mini preview
Total parameters (billions)28.8
Active parameters (billions)4.3
Self-hosting hardware · NVIDIA RTX 5090 (32 GB VRAM; NVFP4)Publisher-reported · 2026-10-26
Self-hosting hardware · Single NVIDIA B300 · GSM8K · concurrency 1646.3 tok/s · vLLM 0.28.0 · MXFP8 · DFlash2 · block 8 (7 draft) · max 4096 new tokens · 128 prompts · Publisher-reported · 2026-10-26
API model IDraon-1-mini-preview
Input modalitiestext
Output modalitiestext
Official source · checked2026-10-26
[2]

Provider pricing

1
Newest pricing check Oct 26, 2026.
Raon-1 mini preview pricing, speed and uptime by provider
ProviderInputOutputCache readBlendActions
KRKRAFTON official API$0.00$0.00$0.00$0.00

Questions about Raon-1 mini preview pricing

Sources & notes

  1. [1]
    KRAFTON official API pricingChecked:
  2. [2]
    Publisher-reported · 2026-10-26 · 646.3 tok/s · vLLM 0.28.0 · MXFP8 · DFlash2 · block 8 (7 draft) · max 4096 new tokens · 128 prompts · Publisher-reported · 2026-10-26 · Official source · checkedChecked:

Transparent pricing. Useful comparisons.

Token pricing units

Pricing is in USD per 1 million tokens for standard, global, default-group API usage. Input, output and cache reads stay separate. Missing pricing remains unknown; a reported zero stays zero.

Traceable pricing sources

Each offer links to the page where its pricing was published. The first row is that model’s base rate. Other rows are additional published provider pricing. A published listing is not an independent endorsement. Only active, standard base token rates are included.

TokenPricing dataset license All rights reserved in the TokenPricing dataset compilation. Third-party pricing and model information remain subject to their source terms.

Pricing conditions

This table excludes batch, region-specific, VIP-group and token-tier offers. Taxes, cache writes, storage, image/audio billing and per-request tools may add charges. Capabilities are reported metadata, not a performance benchmark.