Models / Uncensored / Steelskull
Cu-Mai R1 70B API pricing
$1.7255 in, $1.7255 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | Steelskull list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $1.7255 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $1.7255 | — |
Cu-Mai R1 70B specs
- Context window
- 32,768 tokens
- Input
- text
Cu-Mai R1 70B: Steelskull’s Llama 3.3 merge, Version A · its own prose flavor, per token
Cu-Mai R1 70B is Steelskull's SCE merge on his custom Hydroblated-R1 base, DS-Hydroblated-R1-70B v4.1 (its card, created 2025-02-15). The name plays on San-Mai, for copper-steel Damascus: it is Version A of a three-model series with San-Mai and Mokume-Gane, kept as grounded as San-Mai with its own flavor of prose. The card lists EVA LLaMA 3.33, Euryale v2.3, Cirrus x1, Hanami x1, Anubis v1 and Negative_LLAMA as its components. It is served as cu-mai-r1-70b at $1.7255 input and $1.7255 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.
| Cu-Mai R1 70B | |
|---|---|
| Base model | Llama 3.3 70B |
| Made by | Steelskull |
| Method | SCE merge on a custom Hydroblated-R1 base |
| License on the card | llama3.3 |
| Context window here | 32,768 tokens |
| Downloads, 30 days to 2026-10-20 | 40 |
| Card | Steelskull/L3.3-Cu-Mai-R1-70b |
From the Hugging Face card and its API record, read 2026-10-20.
The card’s sampler settings: temperature 1 to 1.05, min_p 0.02, and optional DRY multiplier 0.8, base 1.75, length 4.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"cu-mai-r1-70b","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Cu-Mai R1 70B 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 Cu-Mai R1 70B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $1.7255 input and $1.7255 output per million tokens, that is $3.451 + $0.8628 = $4.31, paid from prepaid credit with no subscription.
Cu-Mai R1 70B 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="cu-mai-r1-70b",
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: 'cu-mai-r1-70b',
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":"cu-mai-r1-70b","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 Steelskull
Cu-Mai R1 70B questions
- What is Cu-Mai R1 70B?
- Cu-Mai R1 70B is a model from Steelskull, with a 32,768-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as cu-mai-r1-70b.
- How much does the Cu-Mai R1 70B API cost?
- $1.7255 per million input tokens and $1.7255 per million output tokens.
- Is Cu-Mai R1 70B 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 $0.0026.
- What is the Cu-Mai R1 70B context window?
- Cu-Mai R1 70B has a 32,768-token context window. It takes text input.
- What is the Cu-Mai R1 70B model id?
- cu-mai-r1-70b. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Cu-Mai R1 70B 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 Cu-Mai R1 70B and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
- Is there a Cu-Mai R1 70B API?
- Yes: cu-mai-r1-70b on the OpenAI format at https://api.uplinkswitch.com/v1, $1.7255 input and $1.7255 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 Cu-Mai R1 70B based on?
- A custom Hydroblated-R1 base (TheSkullery’s L3.1x3.3-DS-Hydroblated-R1-70B v4.1), merged with SCE with EVA LLaMA 3.33, Euryale v2.3, Cirrus x1, Hanami x1, Anubis v1 and Negative_LLAMA, per its card.
- What license does Cu-Mai R1 70B have?
- The card lists the Llama 3.3 license (llama3.3).
- What does Cu-Mai R1 70B cost per 100 messages?
- $0.4314 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.7255 input and $1.7255 output per million tokens, from prepaid credit with no subscription.
- Cu-Mai R1 70B or Electra R1 70B?
- Both are Steelskull’s SCE merges on a custom Hydroblated-R1 base: Cu-Mai is Version A of the San-Mai series (card created 2025-02-15); Electra R1 came later (2025-03-02), built on feedback from the models before it, Cu-Mai among them. Cu-Mai R1 70B is $1.7255 / $1.7255 per million tokens in / out, $4.31 for 1,000 chat turns; Electra R1 70B is $2.45 / $2.45 per million tokens in / out, $6.13 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.