Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
All providers
Creekside Compute

Creekside Compute

GLB
9 models available
All available routes ZDR

Privacy can differ by model. See each model’s label.

Models served by Creekside Compute

9 models

ModelContextInput /MOutput /MCache read /MCache hitTTFTThroughput
Gemma 4 31B
NVFP4
ZDR
115k$0.0954/M$0.278/M$0.0112/M16.2%1.1s92.7 tps
Gemma 4 31B (Thinking)
NVFP4
ZDR
115k$0.0954/M$0.278/M$0.0112/M7.5%2.5s93.6 tps
Muse Glimmer 30B
NVFP4
ZDR
131k$0.299/M$1.20/M$0.0399/M11.7%0.7s57.6 tps
Qwen 3.6 35B A3B
FP8
ZDR
1.0M$0.0399/M$0.299/M$0.015/M11.3%1.2s298.3 tps
Qwen 3.6 35B A3B Thinking
FP8
ZDR
1.0M$0.0399/M$0.299/M$0.015/M11.3%1.2s298.3 tps
Qwen 3.8 27B Uncensored
NVFP4
ZDR
1.0M$0.0194/M$0.194/M$0.0194/M76.1%3.1s106.5 tps
Qwen 3.8 27B Uncensored Thinking
NVFP4
ZDR
1.0M$0.0194/M$0.194/M$0.0194/M99.4%2.2s99.2 tps
Qwen3.8 27B
NVFP4
ZDR
1.0M$0.0229/M$0.309/M$0.0126/M84.2%2.2s141.7 tps
Qwen3.8 27B Thinking
NVFP4
ZDR
1.0M$0.0229/M$0.309/M$0.0126/M68.6%3.9s141.8 tps
Gemma 4 31B
NVFP4
ZDR
Context
115k
Input /M
$0.0954/M
Output /M
$0.278/M
Cache read /M
$0.0112/M
Cache hit
16.2%
TTFT
1.1s
Throughput
92.7 tps
Gemma 4 31B (Thinking)
NVFP4
ZDR
Context
115k
Input /M
$0.0954/M
Output /M
$0.278/M
Cache read /M
$0.0112/M
Cache hit
7.5%
TTFT
2.5s
Throughput
93.6 tps
Muse Glimmer 30B
NVFP4
ZDR
Context
131k
Input /M
$0.299/M
Output /M
$1.20/M
Cache read /M
$0.0399/M
Cache hit
11.7%
TTFT
0.7s
Throughput
57.6 tps
Qwen 3.6 35B A3B
FP8
ZDR
Context
1.0M
Input /M
$0.0399/M
Output /M
$0.299/M
Cache read /M
$0.015/M
Cache hit
11.3%
TTFT
1.2s
Throughput
298.3 tps
Qwen 3.6 35B A3B Thinking
FP8
ZDR
Context
1.0M
Input /M
$0.0399/M
Output /M
$0.299/M
Cache read /M
$0.015/M
Cache hit
11.3%
TTFT
1.2s
Throughput
298.3 tps
Qwen 3.8 27B Uncensored
NVFP4
ZDR
Context
1.0M
Input /M
$0.0194/M
Output /M
$0.194/M
Cache read /M
$0.0194/M
Cache hit
76.1%
TTFT
3.1s
Throughput
106.5 tps
Qwen 3.8 27B Uncensored Thinking
NVFP4
ZDR
Context
1.0M
Input /M
$0.0194/M
Output /M
$0.194/M
Cache read /M
$0.0194/M
Cache hit
99.4%
TTFT
2.2s
Throughput
99.2 tps
Qwen3.8 27B
NVFP4
ZDR
Context
1.0M
Input /M
$0.0229/M
Output /M
$0.309/M
Cache read /M
$0.0126/M
Cache hit
84.2%
TTFT
2.2s
Throughput
141.7 tps
Qwen3.8 27B Thinking
NVFP4
ZDR
Context
1.0M
Input /M
$0.0229/M
Output /M
$0.309/M
Cache read /M
$0.0126/M
Cache hit
68.6%
TTFT
3.9s
Throughput
141.8 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 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

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.

Creekside Compute terms of useCreekside Compute privacy policy