Abliteration.ai

4 models available

Abliteration.ai states that API prompts and completions are processed transiently, are not stored, and are not used for training.

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by Abliteration.ai

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
Abliterated Large Flash FP8	1.0M	$1.05/M	$2.10/M	$0.105/M	97.8%	2.5s	418.5 tps
Abliterated Model BF16	262k	$1.05/M	$3.15/M	$0.105/M	1.6%	5.1s	216.3 tps
Abliterated Model Large FP8	1M	$3.15/M	$5.25/M	$0.315/M	97.8%	4.4s	116.1 tps
Abliterated Model Large V2 FP8	1M	$3.15/M	$5.25/M	$0.315/M	98.2%	3.7s	160.4 tps

Abliterated Large Flash

FP8

Context: 1.0M
Input /M: $1.05/M
Output /M: $2.10/M
Cache read /M: $0.105/M
Cache hit: 97.8%
TTFT: 2.5s
Throughput: 418.5 tps

Abliterated Model

BF16

Context: 262k
Input /M: $1.05/M
Output /M: $3.15/M
Cache read /M: $0.105/M
Cache hit: 1.6%
TTFT: 5.1s
Throughput: 216.3 tps

Abliterated Model Large

FP8

Context: 1M
Input /M: $3.15/M
Output /M: $5.25/M
Cache read /M: $0.315/M
Cache hit: 97.8%
TTFT: 4.4s
Throughput: 116.1 tps

Abliterated Model Large V2

FP8

Context: 1M
Input /M: $3.15/M
Output /M: $5.25/M
Cache read /M: $0.315/M
Cache hit: 98.2%
TTFT: 3.7s
Throughput: 160.4 tps

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Abliteration.ai via the API

Call a model served by Abliteration.ai using its displayed model ID, including the provider suffix when selection is supported.

cURL

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "abliteration-ai/abliterated-model-large-flash:abliteration",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :abliteration to the model ID, set "provider": "abliteration" in the request body, or send an X-Provider: abliteration header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

See the API documentation for provider preferences, price-aware routing, and error behavior.

Abliteration.ai terms of use Abliteration.ai privacy policy

Model

Context

Input /M

Output /M

Cache read /M

Cache hit

TTFT

Throughput

Abliterated Large Flash

FP8

1.0M

$1.05/M

$2.10/M

$0.105/M

97.8%

2.5s

418.5 tps

Abliterated Model

BF16

262k

$1.05/M

$3.15/M

$0.105/M

1.6%

5.1s

216.3 tps

Abliterated Model Large

FP8

$3.15/M

$5.25/M

$0.315/M

97.8%

4.4s

116.1 tps

Abliterated Model Large V2

FP8

$3.15/M

$5.25/M

$0.315/M

98.2%

3.7s

160.4 tps

Using Abliteration.ai via the API

Call a model served by Abliteration.ai using its displayed model ID, including the provider suffix when selection is supported.

cURL

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "abliteration-ai/abliterated-model-large-flash:abliteration",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.