Models / Uncensored / Cantina Security

Apex Flash 1 Abliterated API pricing

$0.68 in, $2.32 out per million tokens.

apex-flash-1-abliteratedmanaged routeOpenAI SDK

Price · per million tokens, USD

Get a key
TokensCantina Security list priceUplinkSwitchSaving
Input—$0.68—
Cached input—$0.36—
Output—$2.32—
No list price on record. Prices read from the live catalog on 2026-11-16; the page follows the catalog.
Real-model check: Steady since Nov 4

Apex Flash 1 Abliterated specs

Context window
262,144 tokens
Input
text and image

Apex Flash 1 Abliterated: an uncensored build · what the catalog states

Apex Flash 1 Abliterated is an abliterated build: the refusal direction was removed from the weights, so it answers prompts the stock model declines, with nothing added to your prompt. No model card or weights are published for this build, so this page states what the catalog does. It is served as apex-flash-1-abliterated at $0.68 input and $2.32 output per million tokens, one of 161 builds in the uncensored LLM API, on the same key as every other model.

Apex Flash 1 Abliterated
DeveloperCantina Security
Kindabliterated (refusal direction removed from the weights)
Weightsnot published for this build
Context window here262,144 tokens
Inputtext and image

From the live catalog.

curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"apex-flash-1-abliterated","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

What abliterated means for Apex Flash 1 Abliterated · the daily real-model check is the live evidence

The direction in the model’s activations that makes it refuse was found and projected out of the weights, with no retraining: the model keeps what the stock build knows and stops declining. Nothing rides along with your prompt and no jailbreak preamble is billed. What it does with your prompts is the model's own call, so run them through it in your tool.

The daily real-model check is the live evidence: it confirms the model answering apex-flash-1-abliterated is the one we serve, checked every day.

Apex Flash 1 Abliterated next to the other uncensored models · per million tokens, live

ModelHere, in / out1,000 chat turns
GLM-5.3 Flash Uncensored$0.1053 / $0.3685$0.39
Manta Flash 1.0$0.07 / $0.56$0.42
Manta Mini 1.0$0.07 / $0.56$0.42
Gemma 4 12B Starry Ocean$0.175 / $0.875$0.79
Gemma 4 12B StationKeeper$0.175 / $0.875$0.79
Magidonia 24B v4.3$0.3535 / $0.4235$0.92
GLM-5.3 Uncensored$0.282 / $0.846$0.99
MythoMax L2 13B$0.404 / $0.404$1.01
Cydonia 24B v2$0.4012 / $0.4828$1.04
Gemma 4 31B Split-Untied$0.35 / $1.05$1.22
Cydonia 24B v4.3$0.484 / $0.60$1.27
Manta Pro 1.0$0.21 / $1.75$1.30
Artemis v1.1$0.35 / $1.575$1.49
Gemma 4 31B Gembrain$0.35 / $1.575$1.49
Gemma 4 31B Isometry$0.35 / $1.575$1.49
Gemma 4 31B Scarlet$0.35 / $1.575$1.49
Gemma 4 31B Fabled$0.35 / $1.575$1.49
Gemma 4 31B Gemsicle$0.35 / $1.575$1.49
Gemma 4 31B MeroMero v2$0.35 / $1.575$1.49
Gemma 4 31B Novelist$0.35 / $1.575$1.49
Gemma 4 26B-A4B ChimeraX$0.42 / $1.33$1.51
Gemma 4 26B-A4B Luminous Mirror$0.42 / $1.33$1.51
Gemma 4 26B-A4B MeroMero$0.42 / $1.33$1.51
Gemma 4 26B-A4B Moonlight Dusk$0.42 / $1.33$1.51
Gemma 4 26B-A4B Musica$0.42 / $1.33$1.51
Gemma 4 26B-A4B Opus Distill$0.42 / $1.33$1.51
Gemma 4 26B-A4B Shadow Siren$0.42 / $1.33$1.51
Gemma 4 26B A4B Cybersecurity$0.4224 / $1.3376$1.51
Gemma 4 31B GemBrain Heretic$0.40 / $1.76$1.68
Gemma 4 31B MeroMero$0.40 / $1.76$1.68
Gemma 4 26B A4B ChimeraX$0.48 / $1.48$1.70
Gemma 4 26B A4B DarkSoul$0.48 / $1.48$1.70
Gemma 4 26B A4B Luminous$0.48 / $1.48$1.70
Gemma 4 26B A4B MeroMero$0.48 / $1.48$1.70
Gemma 4 26B A4B Moonlight$0.48 / $1.48$1.70
Gemma 4 26B A4B Musica$0.48 / $1.48$1.70
Gemma 4 26B A4B OpusDistill$0.48 / $1.48$1.70
Gemma 4 26B A4B ShadowSiren$0.48 / $1.48$1.70
Gemma 4 31B DarkIdol$0.40 / $1.80$1.70
Gemma 4 26B-A4B ChimeraX Heretic$0.484 / $1.52$1.73
Gemma 4 26B-A4B DarkSoul$0.484 / $1.52$1.73
Qwen3.8 27B Antislop$0.35 / $2.10$1.75
Qwen3.8 27B Fimi$0.35 / $2.10$1.75
Qwen3.8 27B Kimiko$0.35 / $2.10$1.75
Qwen3.8 27B Kiwen$0.35 / $2.10$1.75
Qwen3.8 27B Novelist$0.35 / $2.10$1.75
Qwen3.8 27B Synthia$0.35 / $2.10$1.75
Stheno 8B v3.2$0.7035 / $0.7035$1.76
GLM-5.3 Flash Cybersecurity$0.5093 / $1.6975$1.87
GLM-5.3 Flash Abliterated$0.4656 / $1.94$1.90
Qwen3.8 27B Cybersecurity$0.40 / $2.40$2.00
Qwen3.8 27B DarkIdol$0.40 / $2.40$2.00
Dolphin Mistral 24B Venice Edition$0.50 / $2.25$2.13
Deepseek V4.1 Flash Uncensored$0.5412 / $2.1647$2.16
Uncensored AI Roleplay$0.60 / $2.34$2.37
Apex Flash 1 Abliterated$0.68 / $2.32$2.52
DeepSeek V4.1 Flash Abliterated$0.8488 / $1.6975$2.55
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted$1.0389 / $1.0389$2.60
Gemma 4 26B-A4B Uncensored$0.60 / $2.80$2.60
Veiled Calla 12B$1.05 / $1.05$2.63
Gemma 4 31B Agares v1$1.071 / $1.071$2.68
Gemma 4 31B Animus V14.1$1.071 / $1.071$2.68
Gemma 4 31B AssGuard$1.071 / $1.071$2.68
Gemma 4 31B Garnet V2$1.071 / $1.071$2.68
Gemma 4 31B Gembrain X Core$1.071 / $1.071$2.68
Gemma 4 31B Isometry RP$1.071 / $1.071$2.68
Gemma 4 31B K1 v5$1.071 / $1.071$2.68
Gemma 4 31B StyleTune$1.071 / $1.071$2.68
Qwen3.5 27B Blossom V6.4 Derestricted$1.071 / $1.071$2.68
Qwen3.5 27B BlueStar v3 Derestricted$1.071 / $1.071$2.68
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite$1.071 / $1.071$2.68
Qwen3.5 27B Queen Derestricted$1.071 / $1.071$2.68
Gemma 4 31B Queen$1.071 / $1.071$2.68
Anubis 70B v1.1$1.085 / $1.085$2.71
Jailbreak-Free Assistant$0.75 / $2.50$2.75
DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic$1.12 / $1.12$2.80
DeepSeek V4 Pro Uncensored$0.97 / $1.94$2.91
DeepSeek V4.1 Flash 1017 Abliterated$0.7275 / $3.0313$2.97
Uncensored AI Novelist$0.75 / $3.00$3.00
Gemma 4 31B Gembrain Heretic$1.224 / $1.224$3.06
Gemma 4 31B Dark Gemistry$1.224 / $1.224$3.06
Gemma 4 31B SDFT Heretic RP$1.224 / $1.224$3.06
Anubis 70B v1$1.24 / $1.24$3.10
Euryale 70B v2.2$1.224 / $1.428$3.16
GLM-5.3 Flash Apex Abliterated$0.80 / $3.20$3.20
DeepSeek V4.1 Flash 1017 Uncensored Thinking$0.8003 / $3.201$3.20
Uplink Red Team (Flash)$0.90 / $3.00$3.30
DeepSeek V4.1 Flash 0910 Uncensored$0.825 / $3.30$3.30
DeepSeek V4.1 Flash 0910 Uncensored Thinking$0.825 / $3.30$3.30
DeepSeek V4.1 Flash 1017 Uncensored$0.825 / $3.30$3.30
DeepSeek V4.1 Flash Uncensored Thinking$0.825 / $3.30$3.30
Uncensored Coding Agent$0.90 / $3.00$3.30
DeepSeek V4.1 Flash 1017 Heretic$0.825 / $3.30$3.30
DeepSeek V4.1 Flash 1017 Heretic Thinking$0.825 / $3.30$3.30
Cydonia 24B v4.1$1.20 / $2.00$3.40
Qwen3.8 Max Uncensored$1.00 / $3.00$3.50
DeepSeek V4 Pro Abliterated$1.00 / $4.00$4.00
Qwen3.8 27B Uncensored$1.2125 / $3.6375$4.24
Cu-Mai R1 70B$1.7255 / $1.7255$4.31
Hanami 70B x1$1.7255 / $1.7255$4.31
Mag Mell R1 12B$1.7255 / $1.7255$4.31
NemoMix Unleashed 12B$1.7255 / $1.7255$4.31
Starcannon Unleashed 12B v1.0$1.7255 / $1.7255$4.31
MiMo V2.6 Flash Uncensored Thinking$1.25 / $3.75$4.38
Qwen 2.5 32B Abliterated$1.75 / $1.75$4.38
Qwen3.8 27B Abliterated$1.25 / $3.75$4.38
Qwen3.8 27B Abliterated (Huihui)$1.25 / $3.75$4.38
Qwen3.8 27B Fable$0.875 / $5.25$4.38
Qwen3.8 27B Hemingway$0.875 / $5.25$4.38
Qwen3.8 27B Queen$0.875 / $5.25$4.38
NeuralDaredevil 8B Abliterated$1.76 / $1.76$4.40
MiMo V2.6 Pro Uncensored$1.4768 / $2.9537$4.43
Rocinante 12B v1.1$1.632 / $2.38$4.45
Qwen3.8 27B Obliterated$0.582 / $7.27$4.80
Euryale 70B v2.3$1.972 / $1.972$4.93
Magnum Diamond 24B$1.972 / $1.972$4.93
UnslopNemo 12B v4.1$1.972 / $1.972$4.93
The Omega Directive 24B v2.0$2.00 / $2.00$5.00
Qwen3.8 27B Uncensored (Hotdogs)$1.00 / $6.00$5.00
Kimi K3.1 Pro Uncensored$1.164 / $5.82$5.24
DeepSeek V4.1 Flash Abliterated Fast$1.75 / $3.50$5.25
Skyfall 36B v2$1.925 / $2.80$5.25
Nemotron 3 Ultra 550B Uncensored$1.0913 / $6.402$5.38
GLM-4.6 Derestricted v5$1.40 / $5.25$5.43
ReMM SLERP L2 13B$2.036 / $3.78$5.96
Uplink Red Team (Pro)$1.50 / $6.00$6.00
OrcaCyber MiniMax M3.1 Flash$2.00 / $4.00$6.00
OrcaCyber MiniMax M3.1 Flash$2.00 / $4.00$6.00
OrcaCyber Qwen3.8 Flash Next$2.00 / $4.00$6.00
OrcaCyber Qwen3.8 Flash Next$2.00 / $4.00$6.00
Kimi K2.6 Uncensored$1.17 / $7.34$6.01
Wayfarer Large 70B$2.4535 / $2.4535$6.13
GLM-5.3 Abliterated$2.1825 / $4.365$6.55
DeepSeek R1 Distill Llama 70B Abliterated$2.80 / $2.80$7.00
Llama 3 70B Abliterated v3.5$2.80 / $2.80$7.00
Llama 3.3 70B Abliterated$2.80 / $2.80$7.00
MiMo V2.6 Flash Abliterated$2.00 / $6.00$7.00
MiMo V2.6 Flash Uncensored$2.00 / $6.00$7.00
Gemma 31B Heretic Uncensored$1.50 / $8.25$7.13
Abliterated Large Flash$2.50 / $5.00$7.50
Abliterated Model$2.50 / $7.50$8.75
Qwen 3.8 27B Uncensored Fast$2.50 / $7.50$8.75
Qwen 3.8 27B Uncensored Thinking$2.50 / $7.50$8.75
Aion RP Llama 3.1 8B$3.20 / $6.40$9.60
Inkling Uncensored$2.13 / $12.1403$10.33
DansPE 1.3 24B$2.908 / $11.632$11.63
DeepSeek R1 Distill Qwen 32B Abliterated$5.60 / $5.60$14.00
GLM-5.3 Flash Code Uncensored$6.00 / $6.00$15.00
No Filter AI$5.85 / $7.80$15.60
Uncensored AI Assistant$5.85 / $7.80$15.60
Uncensored Chatbot$5.85 / $7.80$15.60
Unfiltered AI$5.85 / $7.80$15.60
Cyber Frontier$5.25 / $15.75$18.38
Abliterated Model Large V2$7.4996 / $12.4997$21.25
Abliterated Model Large$7.50 / $12.50$21.25
Magnum v4 72B$8.0243 / $11.9684$22.03
OrcaCyber Zero 1.5$7.50 / $18.75$24.38
Kimi K3 Uncensored$5.745 / $28.68$25.83
Uncensored AI Chat$11.70 / $15.60$31.20
Uncensored Code Assistant$11.70 / $15.60$31.20
Unrestricted AI$11.70 / $15.60$31.20

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 Apex Flash 1 Abliterated: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.68 input and $2.32 output per million tokens, that is $1.36 + $1.16 = $2.52, paid from prepaid credit with no subscription.

Apex Flash 1 Abliterated API key · base URL and setup

  1. Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
  2. Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
  3. Send apex-flash-1-abliterated as the model. The same key calls every other model in the catalog.
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="apex-flash-1-abliterated",
    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: 'apex-flash-1-abliterated',
  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":"apex-flash-1-abliterated","messages":[{"role":"user","content":"Hello"}]}'

Apex Flash 1 Abliterated settings for SillyTavern and Janitor AI · from the catalog row

SillyTavern API
Chat Completion
Chat Completion Source
Custom (OpenAI-compatible)
Custom Endpoint (Base URL)
https://api.uplinkswitch.com/v1
Model ID
apex-flash-1-abliterated
Context (tokens)
262,144 tokens
Janitor AI proxy URL
https://api.uplinkswitch.com/v1/chat/completions
Janitor AI model
apex-flash-1-abliterated
API key
your sk-uplink- key
SillyTavern and Janitor AI
SillyTavern API             Chat Completion
Chat Completion Source      Custom (OpenAI-compatible)
Custom Endpoint (Base URL)  https://api.uplinkswitch.com/v1
Model ID                    apex-flash-1-abliterated
Context (tokens)            262,144 tokens
Janitor AI proxy URL        https://api.uplinkswitch.com/v1/chat/completions
Janitor AI model            apex-flash-1-abliterated
API key                     your sk-uplink- key
A chat of 100 replies of 300 tokens costs $0.3416 at 4,000 tokens of context and $1.1576 at 16,000, at the live price above: every message resends the context, so size it to what the chat needs.

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.

Apex Flash 1 Abliterated questions

Apex Flash 1 Abliterated is a model from Cantina Security, with a 262,144-token context window, taking text and image input. Through UplinkSwitch it answers the OpenAI SDK on one key as apex-flash-1-abliterated.

$0.68 per million input tokens and $2.32 per million output tokens, with cached input at $0.36.

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 $0.0018.

Apex Flash 1 Abliterated has a 262,144-token context window. It takes text and image input.

apex-flash-1-abliterated. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

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 Apex Flash 1 Abliterated and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.

Every day each model gets the same test prompt, and the results are public on /proof. Apex Flash 1 Abliterated's latest result: Steady since Nov 4.

Yes: apex-flash-1-abliterated on the OpenAI format at https://api.uplinkswitch.com/v1, $0.68 input and $2.32 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.

No base model, parameter count or training notes are published for Apex Flash 1 Abliterated. The catalog lists a 262,144-token context window.

Apex Flash 1 Abliterated is served live on the OpenAI-compatible API at the same base URL and key as every other model, and it answers the prompts a filtered model declines. The daily real-model check at /proof confirms the model answering apex-flash-1-abliterated is the live one.

Yes. The catalog lists text and image input for apex-flash-1-abliterated; send images as image_url parts in the OpenAI chat format.

$0.252 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.68 input and $2.32 output per million tokens, from prepaid credit with no subscription.
Join on Telegram