io.net

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 io.net

Model name

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
Gemma 4 26B A4B BF16 google/gemma-4-26b-a4b-it:ionet	262k	$0.0945/M	$0.326/M	$0.0431/M	N/A	0.7s	58 tps
Gemma 4 26B A4B (Thinking) BF16 google/gemma-4-26b-a4b-it:thinking:ionet	262k	$0.0945/M	$0.326/M	$0.0431/M	N/A	0.7s	58 tps
Gemma 4 31B google/gemma-4-31b-it:ionet	262k	$0.379/M	$1.15/M	$0.19/M	N/A	1.2s	31 tps
Gemma 4 31B (Thinking) google/gemma-4-31b-it:thinking:ionet	262k	$0.379/M	$1.15/M	$0.19/M	N/A	1.2s	31 tps
GLM 5.3 FP8 z-ai/glm-5.3:ionet	262k	$0.347/M	$3.36/M	$0.326/M	40.6%	2.2s	45 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:ionet	262k	$0.347/M	$3.36/M	$0.326/M	0%	2.2s	45 tps
MiMo V2.6 Flash FP8 xiaomi/mimo-v2.6-flash:ionet	1.0M	$0.105/M	$0.294/M	$0.0032/M	58.6%	1.8s	53 tps

Gemma 4 26B A4B

BF16

google/gemma-4-26b-a4b-it:ionet

Context

262k

Input /M

$0.0945/M

Output /M

$0.326/M

Cache read /M

$0.0431/M

Cache hit

N/A

TTFT

0.7s

Throughput

58 tps

Gemma 4 26B A4B (Thinking)

BF16

google/gemma-4-26b-a4b-it:thinking:ionet

Context

262k

Input /M

$0.0945/M

Output /M

$0.326/M

Cache read /M

$0.0431/M

Cache hit

N/A

TTFT

0.7s

Throughput

58 tps

Gemma 4 31B

google/gemma-4-31b-it:ionet

Context

262k

Input /M

$0.379/M

Output /M

$1.15/M

Cache read /M

$0.19/M

Cache hit

N/A

TTFT

1.2s

Throughput

31 tps

Gemma 4 31B (Thinking)

google/gemma-4-31b-it:thinking:ionet

Context

262k

Input /M

$0.379/M

Output /M

$1.15/M

Cache read /M

$0.19/M

Cache hit

N/A

TTFT

1.2s

Throughput

31 tps

GLM 5.3

FP8

z-ai/glm-5.3:ionet

Context

262k

Input /M

$0.347/M

Output /M

$3.36/M

Cache read /M

$0.326/M

Cache hit

40.6%

TTFT

2.2s

Throughput

45 tps

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:ionet

Context

262k

Input /M

$0.347/M

Output /M

$3.36/M

Cache read /M

$0.326/M

Cache hit

0%

TTFT

2.2s

Throughput

45 tps

MiMo V2.6 Flash

FP8

xiaomi/mimo-v2.6-flash:ionet

Context

1.0M

Input /M

$0.105/M

Output /M

$0.294/M

Cache read /M

$0.0032/M

Cache hit

58.6%

TTFT

1.8s

Throughput

53 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 io.net via the API

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

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b-it:ionet",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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