UplinkSwitch

    • Models / Uncensored / EVA-UNIT-01

    EVA LLaMA 3.33 70B API pricing

    $6.018 in, $6.018 out per million tokens.

    eva-llama-3.33-70bmanaged routeOpenAI SDK

    Price · per million tokens, USD

    TokensEVA-UNIT-01 list priceUplinkSwitchSaving
    Input—$6.018—
    Cached inputBilled at the input rate.
    Output—$6.018—
    No list price on record. Same price on every host.
    Real-model check: Same fingerprint since Oct 20, no answer since Oct 20

    EVA LLaMA 3.33 70B specs

    Context window
    32,768 tokens
    Input
    text

    EVA LLaMA 3.33 70B: a full fine-tune for roleplay and stories · version 0.1, Llama 3.3 70B Instruct

    EVA LLaMA 3.33 70B v0.1 is EVA-UNIT-01's roleplay and story-writing specialist, a full-parameter fine-tune of Llama 3.3 70B Instruct on the Celeste 70B 0.1 data mix (its card). Version 0.1 is a DELLA linear merge of v0.0 with a checkpoint from another run, which the card says reduced overfitting and repetition and improved long context recall. It is served as eva-llama-3.33-70b at $6.018 input and $6.018 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 LLaMA 3.33 70B
    Base modelLlama 3.3 70B Instruct
    Made byEVA-UNIT-01
    MethodFull-parameter fine-tune, DELLA merge
    License on the cardother (EVA Llama 3.3)
    Context window here32,768 tokens
    Downloads, 30 days to 2026-10-2053
    CardEVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1

    From the Hugging Face card and its API record, read 2026-10-20.

    curl
    curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"eva-llama-3.33-70b","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

    EVA LLaMA 3.33 70B next to the other uncensored models · per million tokens, live

    ModelHere, in / out1,000 chat turns
    GLM-5.3 Flash Uncensored$0.084 / $0.084$0.21
    GLM-5.3 Uncensored$0.1746 / $0.1746$0.44
    GLM-4.7 Flash Uncensored$0.12 / $0.60$0.54
    MythoMax L2 13B$0.303 / $0.303$0.76
    Roleplay Uncensored$0.30 / $0.60$0.90
    Cydonia 24B v4.3$0.363 / $0.45$0.95
    Gemma 4 26B-A4B Uncensored$0.27 / $1.26$1.17
    Gemma 4 31B DarkIdol$0.30 / $1.35$1.28
    Gemma 4 26B-A4B ChimeraX Heretic$0.363 / $1.14$1.30
    Gemma 4 26B-A4B DarkSoul$0.363 / $1.14$1.30
    Qwen3.8 27B DarkIdol$0.30 / $1.80$1.50
    GLM-5.3 Flash Abliterated$0.66 / $0.66$1.65
    GLM-5.3 Flash Apex Abliterated$0.45 / $1.50$1.65
    DeepSeek V4 Pro Uncensored$0.75 / $0.75$1.88
    Dolphin Mistral 24B Venice Edition$0.50 / $2.25$2.13
    Gemma 4 31B Dark Gemistry$0.918 / $0.918$2.30
    Gemma 4 31B Gembrain Heretic$0.918 / $0.918$2.30
    Gemma 4 31B SDFT Heretic RP$0.918 / $0.918$2.30
    Euryale 70B v2.2$0.918 / $1.071$2.37
    Cydonia 24B v4.1$0.90 / $1.50$2.55
    DeepSeek V4.1 Flash Abliterated$1.05 / $1.05$2.63
    Hermes 3 Llama 3.1 70B$1.224 / $1.224$3.06
    NeuralDaredevil 8B Abliterated$1.32 / $1.32$3.30
    Hermes 4 405B$0.90 / $3.60$3.60
    Euryale 70B v2.3$1.479 / $1.479$3.70
    Magnum Diamond 24B$1.479 / $1.479$3.70
    UnslopNemo 12B v4.1$1.479 / $1.479$3.70
    The Omega Directive 24B v2.0$1.50 / $1.50$3.75
    Qwen3.8 27B Obliterated$0.75 / $5.25$4.13
    Qwen3.8 27B Uncensored$1.25 / $3.75$4.38
    ReMM SLERP L2 13B$1.527 / $2.835$4.47
    Chat Uncensored$1.50 / $3.00$4.50
    DeepSeek R1 Distill Llama 70B Abliterated$2.10 / $2.10$5.25
    Llama 3 70B Abliterated v3.5$2.10 / $2.10$5.25
    Llama 3.3 70B Abliterated$2.10 / $2.10$5.25
    MiMo V2.6 Flash Abliterated$1.50 / $4.50$5.25
    MiMo V2.6 Flash Uncensored$1.50 / $4.50$5.25
    Qwen2.5 32B Abliterated$2.10 / $2.10$5.25
    QwQ 32B Uncensored$1.98 / $3.00$5.46
    GLM-5.3 Abliterated$2.25 / $2.25$5.63
    EVA Qwen2.5 72B$2.397 / $2.397$5.99
    Gemma 31B Heretic Uncensored$1.50 / $8.25$7.13
    Aion RP Llama 3.1 8B$2.40 / $4.80$7.20
    Lumimaid v0.2 70B$3.00 / $4.50$8.25
    DeepSeek R1 Distill Qwen 32B Abliterated$4.20 / $4.20$10.50
    Code Pro Uncensored$4.50 / $9.00$13.50
    GLM-5.3 Flash Code Uncensored$6.00 / $6.00$15.00
    EVA LLaMA 3.33 70B$6.018 / $6.018$15.05
    Magnum v4 72B$6.018 / $8.976$16.52

    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 LLaMA 3.33 70B: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $6.018 input and $6.018 output per million tokens, that is $12.036 + $3.009 = $15.05, paid from prepaid credit with no subscription.

    EVA LLaMA 3.33 70B API · base URL and key

    Python · OpenAI SDK
    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-llama-3.33-70b",
    messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)
    TypeScript · OpenAI SDK
    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-llama-3.33-70b',
  messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);
    curl
    curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"eva-llama-3.33-70b","messages":[{"role":"user","content":"Hello"}]}'
    Guides: SillyTavern, Janitor AI, Chub AI, SDKs.

    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 LLaMA 3.33 70B questions

    What is EVA LLaMA 3.33 70B?
    EVA LLaMA 3.33 70B is a model from EVA-UNIT-01, with a 32,768-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as eva-llama-3.33-70b.
    How much does the EVA LLaMA 3.33 70B API cost?
    $6.018 per million input tokens and $6.018 per million output tokens.
    Is EVA LLaMA 3.33 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 $0.009.
    What is the EVA LLaMA 3.33 70B context window?
    EVA LLaMA 3.33 70B has a 32,768-token context window. It takes text input.
    What is the EVA LLaMA 3.33 70B model id?
    eva-llama-3.33-70b. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
    How do I get a EVA LLaMA 3.33 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 EVA LLaMA 3.33 70B 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 EVA LLaMA 3.33 70B?
    Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. EVA LLaMA 3.33 70B's latest result: Same fingerprint since Oct 20, no answer since Oct 20.
    Is there a EVA LLaMA 3.33 70B API?
    Yes: eva-llama-3.33-70b on the OpenAI format at https://api.uplinkswitch.com/v1, $6.018 input and $6.018 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 LLaMA 3.33 70B based on?
    Meta’s Llama 3.3 70B Instruct, fully fine-tuned by EVA-UNIT-01, then merged (DELLA linear) with a checkpoint from another run, per its card.
    What license does EVA LLaMA 3.33 70B have?
    The card’s license tag is other, named eva-llama3.3.
    What does EVA LLaMA 3.33 70B cost per 100 messages?
    $1.5045 for 100 chat turns of 2,000 input and 500 output tokens each, at $6.018 input and $6.018 output per million tokens, from prepaid credit with no subscription.
    EVA LLaMA 3.33 70B or EVA Qwen2.5 72B?
    Same team and data: one is a full fine-tune of Llama 3.3 70B Instruct, the other of Qwen2.5 72B. EVA LLaMA 3.33 70B is $6.018 / $6.018 per million tokens in / out, $15.05 for 1,000 chat turns; EVA Qwen2.5 72B is $2.397 / $2.397 per million tokens in / out, $5.99 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.
    Every uncensored model: Uncensored LLM API. Read: Best AI for roleplay.
    Get a key · All models