GeniusRelay
Sign upConsole

Qwen: EVA-Qwen2.5-72B-v0.2

eva-qwen2.5-72b-v0.2

CompareAPIGet an API keyGet an API key

EVA-Qwen2.5-72B-v0.2 costs $1.04 per million input tokens and $1.04 per million output tokens, supports 16K context, and is available through the OpenAI-compatible API.

A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-72B 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.

Modalities

Text → Text

Input / output price

$1.04 / $1.04 per 1M

Context

16K · max output 8K

Capabilities

RoleplayOpen weights

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$1.04
Output$1.04
Cached input$0.519

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00395
Per day
$1.97
Per month (30 days)
$59.21

EVA-Qwen2.5-72B-v0.2: input $1.0387/M · output $1.0387/M · cached input $0.5194/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "eva-qwen2.5-72b-v0.2", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to eva-qwen2.5-72b-v0.2.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "eva-qwen2.5-72b-v0.2",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is EVA-Qwen2.5-72B-v0.2 billed?
Input is $1.04 and output is $1.04 per million tokens; cached input is $0.519. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
16K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
EVA-Qwen2.5-72B-v0.2 API pricing · GeniusRelay