NanoGPT

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

Name: EVA-Qwen2.5-32B-v0.2
Brand: NanoGPT

Canonical ID: nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2

More NanoGPT models More v0 family models

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.

Reasoning: No Tool use: No Open weights

Overview

text

Provider: NanoGPT
Family: v0
Release date: 2025-07-26
Last updated: 2025-07-26
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0.799/1M
Output: $0.799/1M
Cached input: N/A

Context and output

Context window: 16,384
Max output tokens: 8,192
Qualified ID: nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2

Model Summary

EVA-Qwen2.5-32B-v0.2 is a model listing in the NanoGPT provider catalog. It is categorized under the v0 family.

The model supports text modalities across input/output paths. Reported context capacity is 16,384. Pricing is listed at $0.799/1M input and $0.799/1M output.

Same Family: v0

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Ampersand v0.1 vercel/humansand/ampersand-v0.1	Vercel AI Gateway	1,000,000	$0/1M	$0/1M	Reasoning Tools
Embed v1 0.6b vercel/perplexity/pplx-embed-v1-0.6b	Vercel AI Gateway	32,000	N/A	N/A

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

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From NanoGPT

Abliterated Large Flash

Abliterated Model

Abliterated Model Large

Abliterated Model Large V2

Agnes 3.0 Flash

AionLabs: Aion-2.0

AionLabs: Aion 3.0

AionLabs: Aion 3.0 Mini

Same Family: v0