Creekside Compute

Models served by Creekside Compute

Model name

9 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
Gemma 4 31B FP8 ZDR google/gemma-4-31b-it:creekside	115k	$0.0954/M	$0.278/M	$0.0112/M	N/A	N/A
Gemma 4 31B (Thinking) FP8 ZDR google/gemma-4-31b-it:thinking:creekside	115k	$0.0954/M	$0.278/M	$0.0112/M	N/A	N/A
Muse Glimmer 30B NVFP4 ZDR meta/muse-glimmer-30b:creekside	131k	$0.299/M	$1.20/M	$0.0399/M	N/A	N/A
Qwen 3.6 35B A3B FP8 ZDR Qwen/Qwen3.6-35B-A3B:creekside	1.0M	$0.0399/M	$0.299/M	$0.015/M	N/A	N/A
Qwen 3.6 35B A3B Thinking FP8 ZDR Qwen/Qwen3.6-35B-A3B:thinking:creekside	1.0M	$0.0399/M	$0.299/M	$0.015/M	N/A	N/A
Qwen 3.8 27B Uncensored FP8 ZDR qwen/qwen3.8-27b-uncensored:creekside	1.0M	$0.773/M	$2.44/M	$0.14/M	N/A	N/A
Qwen 3.8 27B Uncensored Thinking FP8 ZDR qwen/qwen3.8-27b-uncensored:thinking:creekside	1.0M	$0.773/M	$2.44/M	$0.14/M	N/A	N/A
Qwen3.8 27B FP8 ZDR qwen3.8-27b:creekside	1.0M	$0.0229/M	$0.309/M	$0.0126/M	N/A	N/A
Qwen3.8 27B Thinking FP8 ZDR qwen3.8-27b:thinking:creekside	1.0M	$0.0229/M	$0.309/M	$0.0126/M	N/A	N/A

Gemma 4 31B

FP8

ZDR

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

Context

115k

Input /M

$0.0954/M

Output /M

$0.278/M

Cache read /M

$0.0112/M

TTFT

N/A

Throughput

N/A

Gemma 4 31B (Thinking)

FP8

ZDR

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

Context

115k

Input /M

$0.0954/M

Output /M

$0.278/M

Cache read /M

$0.0112/M

TTFT

N/A

Throughput

N/A

Muse Glimmer 30B

NVFP4

ZDR

meta/muse-glimmer-30b:creekside

Context

131k

Input /M

$0.299/M

Output /M

$1.20/M

Cache read /M

$0.0399/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B

FP8

ZDR

Qwen/Qwen3.6-35B-A3B:creekside

Context

1.0M

Input /M

$0.0399/M

Output /M

$0.299/M

Cache read /M

$0.015/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B Thinking

FP8

ZDR

Qwen/Qwen3.6-35B-A3B:thinking:creekside

Context

1.0M

Input /M

$0.0399/M

Output /M

$0.299/M

Cache read /M

$0.015/M

TTFT

N/A

Throughput

N/A

Qwen 3.8 27B Uncensored

FP8

ZDR

qwen/qwen3.8-27b-uncensored:creekside

Context

1.0M

Input /M

$0.773/M

Output /M

$2.44/M

Cache read /M

$0.14/M

TTFT

N/A

Throughput

N/A

Qwen 3.8 27B Uncensored Thinking

FP8

ZDR

qwen/qwen3.8-27b-uncensored:thinking:creekside

Context

1.0M

Input /M

$0.773/M

Output /M

$2.44/M

Cache read /M

$0.14/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B

FP8

ZDR

qwen3.8-27b:creekside

Context

1.0M

Input /M

$0.0229/M

Output /M

$0.309/M

Cache read /M

$0.0126/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B Thinking

FP8

ZDR

qwen3.8-27b:thinking:creekside

Context

1.0M

Input /M

$0.0229/M

Output /M

$0.309/M

Cache read /M

$0.0126/M

TTFT

N/A

Throughput

N/A

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 Creekside Compute via the API

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

curl https://api.nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31b-it:creekside",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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