Aion

6 models available

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 Aion

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
Aion 2.0	131k	$0.84/M	$1.68/M	$0.21/M	4.8%	1.5s	60.8 tps
Aion 3.0	131k	$3.15/M	$6.30/M	$0.787/M	76.2%	2s	50 tps
Aion 3.0 Mini	131k	$0.735/M	$1.47/M	$0.189/M	29.9%	1.9s	62.2 tps
Aion 3.5	262k	$3.15/M	$6.30/M	$0.787/M	59.3%	2.3s	50 tps
Aion 3.5 Mini	262k	$0.735/M	$1.47/M	$0.189/M	34.9%	1.5s	57 tps
Aion-RP Llama 3.1 8B	33k	$0.84/M	$1.68/M	N/A	0%	4.2s	37.1 tps

Aion 2.0

Context: 131k
Input /M: $0.84/M
Output /M: $1.68/M
Cache read /M: $0.21/M
Cache hit: 4.8%
TTFT: 1.5s
Throughput: 60.8 tps

Aion 3.0

Context: 131k
Input /M: $3.15/M
Output /M: $6.30/M
Cache read /M: $0.787/M
Cache hit: 76.2%
TTFT: 2s
Throughput: 50 tps

Aion 3.0 Mini

Context: 131k
Input /M: $0.735/M
Output /M: $1.47/M
Cache read /M: $0.189/M
Cache hit: 29.9%
TTFT: 1.9s
Throughput: 62.2 tps

Aion 3.5

Context: 262k
Input /M: $3.15/M
Output /M: $6.30/M
Cache read /M: $0.787/M
Cache hit: 59.3%
TTFT: 2.3s
Throughput: 50 tps

Aion 3.5 Mini

Context: 262k
Input /M: $0.735/M
Output /M: $1.47/M
Cache read /M: $0.189/M
Cache hit: 34.9%
TTFT: 1.5s
Throughput: 57 tps

Aion-RP Llama 3.1 8B

Context: 33k
Input /M: $0.84/M
Output /M: $1.68/M
Cache read /M: N/A
Cache hit: 0%
TTFT: 4.2s
Throughput: 37.1 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 Aion via the API

Call a model served by Aion 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": "aion-labs/aion-2.0:aionlabs",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :aionlabs to the model ID, set "provider": "aionlabs" in the request body, or send an X-Provider: aionlabs 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.

Aion terms of use Aion privacy policy

Model

Context

Input /M

Output /M

Cache read /M

Cache hit

TTFT

Throughput

Aion 2.0

131k

$0.84/M

$1.68/M

$0.21/M

4.8%

1.5s

60.8 tps

Aion 3.0

131k

$3.15/M

$6.30/M

$0.787/M

76.2%

50 tps

Aion 3.0 Mini

131k

$0.735/M

$1.47/M

$0.189/M

29.9%

1.9s

62.2 tps

Aion 3.5

262k

$3.15/M

$6.30/M

$0.787/M

59.3%

2.3s

50 tps

Aion 3.5 Mini

262k

$0.735/M

$1.47/M

$0.189/M

34.9%

1.5s

57 tps

Aion-RP Llama 3.1 8B

33k

$0.84/M

$1.68/M

N/A

4.2s

37.1 tps

Using Aion via the API

Call a model served by Aion 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": "aion-labs/aion-2.0:aionlabs",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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