Models / Uncensored / Qwen (community tune)
Qwen3.8 27B Novelist API pricing
$0.35 in, $2.10 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | Qwen (community tune) list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $0.35 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $2.10 | — |
Qwen3.8 27B Novelist specs
- Context window
- 262,144 tokens
- Max output
- 32,768 tokens
- Input
- text and image
Qwen3.8 27B Novelist: a literary writer for roleplay and fiction · Dxniz’s Novelist 1.0, English and Turkish
Qwen3.8 27B Novelist is Dxniz's Novelist 1.0, a 27B literary writer on Qwen's Qwen3.8 27B for roleplay and fiction in English and Turkish (its card, created 2026-08-15). The card says it is trained to stay in the scene: hold a character's voice and point of view, treat a requested word count as part of the task, and leave what the user already wrote unchanged. Its recipe is a rank-64 LoRA, SFT on roleplay and fiction chats, then GRPO with rewards for length, craft and less repetition. It is served as qwen3.8-27b-novelist at $0.35 input and $2.10 output per million tokens, one of 146 builds in the uncensored LLM API, on the same key as every other model. Added 2026-10-20.
| Qwen3.8 27B Novelist | |
|---|---|
| Base model | Qwen3.8 27B |
| Made by | Dxniz |
| Method | LoRA SFT on roleplay and fiction, then GRPO, merged |
| License on the card | apache-2.0 |
| Context window here | 262,144 tokens |
| Downloads, 30 days to 2026-10-20 | 142 |
| Card | Dxniz/Novelist1.0-27b |
From the Hugging Face card and its API record, read 2026-10-20.
For stories the card recommends thinking off with temperature 0.7, top_p 0.8, top_k 20, min_p 0 and presence_penalty 1.5.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"qwen3.8-27b-novelist","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Qwen3.8 27B Novelist 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 Qwen3.8 27B Novelist: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.35 input and $2.10 output per million tokens, that is $0.70 + $1.05 = $1.75, paid from prepaid credit with no subscription.
Qwen3.8 27B Novelist 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="qwen3.8-27b-novelist",
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: 'qwen3.8-27b-novelist',
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":"qwen3.8-27b-novelist","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 Qwen (community tune)
Qwen3.8 27B Novelist questions
- What is Qwen3.8 27B Novelist?
- Qwen3.8 27B Novelist is a model from Qwen (community tune), with a 262,144-token context window, taking text and image input. Through UplinkSwitch it answers the OpenAI SDK on one key as qwen3.8-27b-novelist.
- How much does the Qwen3.8 27B Novelist API cost?
- $0.35 per million input tokens and $2.10 per million output tokens.
- Is Qwen3.8 27B Novelist 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 $0.0014.
- What is the Qwen3.8 27B Novelist context window?
- Qwen3.8 27B Novelist has a 262,144-token context window, with up to 32,768 output tokens per request. It takes text and image input.
- What is the Qwen3.8 27B Novelist model id?
- qwen3.8-27b-novelist. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Qwen3.8 27B Novelist 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 Qwen3.8 27B Novelist and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is it the real Qwen3.8 27B Novelist?
- Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Qwen3.8 27B Novelist's latest result: Same fingerprint since Oct 20.
- Is there a Qwen3.8 27B Novelist API?
- Yes: qwen3.8-27b-novelist on the OpenAI format at https://api.uplinkswitch.com/v1, $0.35 input and $2.10 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 Qwen3.8 27B Novelist based on?
- Qwen’s Qwen3.8 27B. Dxniz trained a rank-64 LoRA with SFT on roleplay and fiction chats, then GRPO, and merged it into 16-bit weights, per the Novelist 1.0 card.
- What license does Qwen3.8 27B Novelist have?
- The card lists Apache-2.0, the license of its Qwen3.8 27B base.
- What does Qwen3.8 27B Novelist cost per 100 messages?
- $0.175 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.35 input and $2.10 output per million tokens, from prepaid credit with no subscription.
- How do I prompt Qwen3.8 27B Novelist?
- Its card asks for a situation and a constraint rather than a vibe: who is speaking, where, what must or must not happen, plus length, tense and point of view. A word count such as Write 600 words is treated as part of the task.
- Qwen3.8 27B Novelist or Qwen3.8 27B Hemingway?
- Novelist is trained for fiction and roleplay; Hemmingway-1 for everyday writing such as messages and emails. Qwen3.8 27B Novelist is $0.35 / $2.10 per million tokens in / out, $1.75 for 1,000 chat turns; Qwen3.8 27B Hemingway is $0.875 / $5.25 per million tokens in / out, $4.38 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.