LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
ev

EVA-Qwen2.5-32B-v0.2

eva-unit-01·eva-unit-01/eva-qwen2.5-32b-v0.2·GA·Open weights·v0 series
A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$0.80 / $0.80
Blended $0.80
Context
16,384
Output limit
8,192
Knowledge cutoff
—
Released / updated
2025-07-26 / 2025-07-26
Capabilities
ReasoningTool useStructured output? TemperatureAttachments
Modalities
Text

EVA-Qwen2.5-32B-v0.2 by eva-unit-01 is currently listed from a single provider. No official API price is listed for it; the prices below come from third-party channels.

The context window is 16,384 tokens, with an output limit of 8,192 tokens. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Available at 1 providers1 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
    $0.80 / $0.80
    Cache read $0.40Context 16,384Output limit 8,192
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPT
EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2
Gateway$0.80$0.80$0.40—16,3848,192

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1NanoGPT$151.81
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.80

Price history accumulates from each data sync; currently only 1 sample(s) (2026-11-04). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

huAmpersand v0.1same series—Embed v1 0.6bsame series—
Data partly from models.dev (MIT)