Models / Uncensored / Anthracite
Magnum v4 72B API pricing
$6.018 in, $8.976 out per million tokens.
Price · per million tokens, USD
| Tokens | Anthracite list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $6.018 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $8.976 | — |
Magnum v4 72B specs
- Context window
- 16,384 tokens
- Input
- text
Magnum v4 72B: Anthracite’s Claude-style roleplay model · Qwen2.5 72B Instruct, tuned for prose, per token
Magnum v4 72B is Anthracite's 72B model in a series built to replicate the prose of Claude 3 Sonnet and Opus, fine-tuned on top of Qwen2.5 72B Instruct (its card). The card says it started as an experiment on the instruct model, code-named magnum-alter, and became the model that started the v4 family. It ships SillyTavern instruct and context templates. It is served as magnum-v4-72b at $6.018 input and $8.976 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.
| Magnum v4 72B | |
|---|---|
| Base model | Qwen2.5 72B Instruct |
| Made by | Anthracite |
| Method | Fine-tune on top of the instruct model |
| License on the card | apache-2.0 |
| Context window here | 16,384 tokens |
| Downloads, 30 days to 2026-10-20 | 853 |
| Card | anthracite-org/magnum-v4-72b |
From the Hugging Face card and its API record, read 2026-10-20.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"magnum-v4-72b","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Magnum v4 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 Magnum v4 72B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $6.018 input and $8.976 output per million tokens, that is $12.036 + $4.488 = $16.52, paid from prepaid credit with no subscription.
Magnum v4 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="magnum-v4-72b",
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: 'magnum-v4-72b',
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":"magnum-v4-72b","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.
Magnum v4 72B questions
- What is Magnum v4 72B?
- Magnum v4 72B is a model from Anthracite, with a 16,384-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as magnum-v4-72b.
- How much does the Magnum v4 72B API cost?
- $6.018 per million input tokens and $8.976 per million output tokens.
- Is Magnum v4 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 $0.0105.
- What is the Magnum v4 72B context window?
- Magnum v4 72B has a 16,384-token context window. It takes text input.
- What is the Magnum v4 72B model id?
- magnum-v4-72b. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Magnum v4 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 Magnum v4 72B 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 Magnum v4 72B?
- Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Magnum v4 72B's latest result: Same fingerprint since Oct 20.
- Is there a Magnum v4 72B API?
- Yes: magnum-v4-72b on the OpenAI format at https://api.uplinkswitch.com/v1, $6.018 input and $8.976 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 Magnum v4 72B based on?
- Qwen’s Qwen2.5 72B Instruct. Anthracite fine-tuned it to write like Claude 3 Sonnet and Opus, per its card.
- What license does Magnum v4 72B have?
- The card lists Apache-2.0.
- What does Magnum v4 72B cost per 100 messages?
- $1.6524 for 100 chat turns of 2,000 input and 500 output tokens each, at $6.018 input and $8.976 output per million tokens, from prepaid credit with no subscription.
- What is Magnum v4 72B good at?
- Prose. The Magnum series is trained to replicate the writing of Claude 3 Sonnet and Opus, so roleplay and story writing are what it is for; its card ships SillyTavern templates.
- Magnum v4 72B or Magnum Diamond 24B?
- v4 72B is the larger Qwen2.5 model; Diamond is the 24B Mistral Small tune with the same goal. Magnum v4 72B is $6.018 / $8.976 per million tokens in / out, $16.52 for 1,000 chat turns; Magnum Diamond 24B is $1.479 / $1.479 per million tokens in / out, $3.70 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.