Models / Uncensored / EVA-UNIT-01
EVA Qwen2.5 72B API pricing
$2.397 in, $2.397 out per million tokens.
Price · per million tokens, USD
| Tokens | EVA-UNIT-01 list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $2.397 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $2.397 | — |
EVA Qwen2.5 72B specs
- Context window
- 16,384 tokens
- Input
- text
EVA Qwen2.5 72B: a full fine-tune for roleplay and stories · version 0.2, Celeste data mix, per token
EVA Qwen2.5 72B v0.2 is EVA-UNIT-01's roleplay and story-writing specialist, a full-parameter fine-tune of Qwen2.5 72B on synthetic and natural data (its card). It expands the Celeste 70B 0.1 data mix. Version 0.2 tuned the training settings and raised the sequence length, which the card says improved instruction following deep into the context and cut repetition. It is served as eva-qwen2.5-72b at $2.397 input and $2.397 output per million tokens, one of 49 builds in the uncensored LLM API, on the same key as every other model. Added 2026-10-20.
| EVA Qwen2.5 72B | |
|---|---|
| Base model | Qwen2.5 72B |
| Made by | EVA-UNIT-01 |
| Method | Full-parameter fine-tune |
| License on the card | other (Qwen) |
| Context window here | 16,384 tokens |
| Downloads, 30 days to 2026-10-20 | 106 |
| Card | EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2 |
From the Hugging Face card and its API record, read 2026-10-20.
The card recommends temperature 0.8, with the ChatML template.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"eva-qwen2.5-72b","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'EVA Qwen2.5 72B next to the other uncensored models · per million tokens, live
A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.
Worked for EVA Qwen2.5 72B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $2.397 input and $2.397 output per million tokens, that is $4.794 + $1.1985 = $5.99, paid from prepaid credit with no subscription.
EVA Qwen2.5 72B API · base URL and key
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="eva-qwen2.5-72b",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'eva-qwen2.5-72b',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"eva-qwen2.5-72b","messages":[{"role":"user","content":"Hello"}]}'What would it cost? · paste a prompt, priced before you send it
Input is counted at about 4 characters per token.
Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.
More from EVA-UNIT-01
EVA Qwen2.5 72B questions
- What is EVA Qwen2.5 72B?
- EVA Qwen2.5 72B is a model from EVA-UNIT-01, with a 16,384-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as eva-qwen2.5-72b.
- How much does the EVA Qwen2.5 72B API cost?
- $2.397 per million input tokens and $2.397 per million output tokens.
- Is EVA Qwen2.5 72B free?
- It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0036.
- What is the EVA Qwen2.5 72B context window?
- EVA Qwen2.5 72B has a 16,384-token context window. It takes text input.
- What is the EVA Qwen2.5 72B model id?
- eva-qwen2.5-72b. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a EVA Qwen2.5 72B API key?
- Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls EVA Qwen2.5 72B and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a EVA Qwen2.5 72B API?
- Yes: eva-qwen2.5-72b on the OpenAI format at https://api.uplinkswitch.com/v1, $2.397 input and $2.397 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.
- What is EVA Qwen2.5 72B based on?
- Qwen’s Qwen2.5 72B, fully fine-tuned by EVA-UNIT-01 on an expanded Celeste 70B 0.1 data mix, per its card.
- What license does EVA Qwen2.5 72B have?
- The card’s license tag is other, named qwen: the Qwen license of its Qwen2.5 72B base.
- What does EVA Qwen2.5 72B cost per 100 messages?
- $0.5993 for 100 chat turns of 2,000 input and 500 output tokens each, at $2.397 input and $2.397 output per million tokens, from prepaid credit with no subscription.
- What settings does EVA Qwen2.5 72B use?
- Its card recommends temperature 0.8 and the ChatML template, which the API applies to the messages you send.
- EVA Qwen2.5 72B or EVA LLaMA 3.33 70B?
- Same team and data: one is a full fine-tune of Qwen2.5 72B, the other of Llama 3.3 70B Instruct. EVA Qwen2.5 72B is $2.397 / $2.397 per million tokens in / out, $5.99 for 1,000 chat turns; EVA LLaMA 3.33 70B is $6.018 / $6.018 per million tokens in / out, $15.05 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.