Models / Uncensored / Steelskull
Electra R1 70B API pricing
$2.45 in, $2.45 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | Steelskull list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $2.45 | — |
| Cached input | Billed at the input rate. | ||
| Output | — | $2.45 | — |
Electra R1 70B specs
- Context window
- 32,768 tokens
- Input
- text
Electra R1 70B: Steelskull’s SCE merge on an R1 base · the sixth iteration of the series, per token
Electra R1 70B is Steelskull's SCE merge of Llama 3.3 70B roleplay models on a custom DeepSeek R1 Distill base, Hydroblated-R1-70B v4.4 (its card, created 2025-03-02, version 0.6.A). The card lists EVA LLaMA 3.33 v0.0, Wayfarer Large, Euryale v2.3, Cirrus x1, Hanami x1 and Anubis v1 as its components, and calls it the sixth iteration of the series, made from user feedback on more than ten earlier models from Nevoria to Cu-Mai. For reasoning it suggests starting the reply with a <think> block. It is served as electra-r1-70b at $2.45 input and $2.45 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.
| Electra R1 70B | |
|---|---|
| Base model | Llama 3.3 70B |
| Made by | Steelskull |
| Method | SCE merge on a custom R1 Distill base |
| License on the card | other (eva-llama3.3) |
| Context window here | 32,768 tokens |
| Downloads, 30 days to 2026-10-20 | 56 |
| Card | Steelskull/L3.3-Electra-R1-70b |
From the Hugging Face card and its API record, read 2026-10-20.
The card’s sampler settings: temperature 1.0 (or dynamic 0.8 to 1.05), min_p 0.025 to 0.03, and DRY multiplier 0.8, base 1.74, length 4 to 6.
curl https://api.uplinkswitch.com/v1/chat/completions \
-H "authorization: Bearer sk-uplink-live-..." \
-H "content-type: application/json" \
-d '{"model":"electra-r1-70b","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'Electra 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 Electra R1 70B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $2.45 input and $2.45 output per million tokens, that is $4.90 + $1.225 = $6.13, paid from prepaid credit with no subscription.
Electra 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="electra-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: 'electra-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":"electra-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
Electra R1 70B questions
- What is Electra R1 70B?
- Electra 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 electra-r1-70b.
- How much does the Electra R1 70B API cost?
- $2.45 per million input tokens and $2.45 per million output tokens.
- Is Electra 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 $0.0037.
- What is the Electra R1 70B context window?
- Electra R1 70B has a 32,768-token context window. It takes text input.
- What is the Electra R1 70B model id?
- electra-r1-70b. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
- How do I get a Electra 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 Electra 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 Electra R1 70B API?
- Yes: electra-r1-70b on the OpenAI format at https://api.uplinkswitch.com/v1, $2.45 input and $2.45 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 Electra R1 70B based on?
- A custom DeepSeek R1 Distill base (TheSkullery’s Hydroblated-R1-70B v4.4), merged with SCE with EVA LLaMA 3.33 v0.0, Wayfarer Large 70B, Euryale v2.3, Cirrus x1, Hanami x1, Anubis v1 and Negative_LLAMA, per its card.
- What license does Electra R1 70B have?
- The card’s license tag is other, with the license named eva-llama3.3.
- What does Electra R1 70B cost per 100 messages?
- $0.6125 for 100 chat turns of 2,000 input and 500 output tokens each, at $2.45 input and $2.45 output per million tokens, from prepaid credit with no subscription.
- Does Electra R1 70B reason?
- When prompted to: its card suggests starting the reply with a <think> block and formatting the reasoning between <think> and </think>. Leave room in max_tokens for it with electra-r1-70b.
- Electra R1 70B or Nevoria R1 70B?
- Both are Steelskull’s Llama 3.3 merges with R1 in them; Electra R1 is the later SCE merge on a custom R1 Distill base (card created 2025-03-02, Nevoria R1 2025-01-23). Electra R1 70B is $2.45 / $2.45 per million tokens in / out, $6.13 for 1,000 chat turns; Nevoria R1 70B is $1.7255 / $1.7255 per million tokens in / out, $4.31 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.