Cake AI logo

by

NanoGPT logo
Greenference

Greenference

EU
10 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 Greenference

10 models

ModelContextInput /MOutput /MCache read /MCache write /MTTFTThroughput
Gemma 4 31B
FP8
262k$0.16/M$0.44/M$0.06/MFreeN/AN/A
GLM 4.7 Flash
FP8
131k$0.07/M$0.43/M$0.02/MFreeN/AN/A
GLM 4.7 Flash (Thinking)
FP8
131k$0.07/M$0.43/M$0.02/MFreeN/AN/A
GLM 5.3 Flash
FP8
1.0M$0.15/M$0.51/M$0.03/MFreeN/AN/A
GPT OSS 20B
131k$0.0095/M$0.05/M$0.0047/MFreeN/AN/A
Qwen 3.6 27B
INT4
262k$0.16/M$1.42/M$0.08/MFreeN/AN/A
Qwen3 14B
INT4
41k$0.10/M$0.30/M$0.05/MN/AN/AN/A
Qwen3 32B
INT4
41k$0.10/M$0.30/M$0.05/MFreeN/AN/A
Qwen3 8B
FP8
41k$0.47/M$0.47/M$0.23/MFreeN/AN/A
Qwen3.5 9B
NVFP4
262k$0.04/M$0.07/M$0.02/MFreeN/AN/A
Gemma 4 31B
FP8
Context
262k
Input /M
$0.16/M
Output /M
$0.44/M
Cache read /M
$0.06/M
Cache write /M
Free
TTFT
N/A
Throughput
N/A
GLM 4.7 Flash
FP8
Context
131k
Input /M
$0.07/M
Output /M
$0.43/M
Cache read /M
$0.02/M
Cache write /M
Free
TTFT
N/A
Throughput
N/A
GLM 4.7 Flash (Thinking)
FP8
Context
131k
Input /M
$0.07/M
Output /M
$0.43/M
Cache read /M
$0.02/M
Cache write /M
Free
TTFT
N/A
Throughput
N/A
GLM 5.3 Flash
FP8
Context
1.0M
Input /M
$0.15/M
Output /M
$0.51/M
Cache read /M
$0.03/M
Cache write /M
Free
TTFT
N/A
Throughput
N/A
GPT OSS 20B
Context
131k
Input /M
$0.0095/M
Output /M
$0.05/M
Cache read /M
$0.0047/M
Cache write /M
Free
TTFT
N/A
Throughput
N/A
Qwen 3.6 27B
INT4
Context
262k
Input /M
$0.16/M
Output /M
$1.42/M
Cache read /M
$0.08/M
Cache write /M
Free
TTFT
N/A
Throughput
N/A
Qwen3 14B
INT4
Context
41k
Input /M
$0.10/M
Output /M
$0.30/M
Cache read /M
$0.05/M
Cache write /M
N/A
TTFT
N/A
Throughput
N/A
Qwen3 32B
INT4
Context
41k
Input /M
$0.10/M
Output /M
$0.30/M
Cache read /M
$0.05/M
Cache write /M
Free
TTFT
N/A
Throughput
N/A
Qwen3 8B
FP8
Context
41k
Input /M
$0.47/M
Output /M
$0.47/M
Cache read /M
$0.23/M
Cache write /M
Free
TTFT
N/A
Throughput
N/A
Qwen3.5 9B
NVFP4
Context
262k
Input /M
$0.04/M
Output /M
$0.07/M
Cache read /M
$0.02/M
Cache write /M
Free
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 Greenference via the API

Call a model served by Greenference 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": "google/gemma-4-31b-it:greenference",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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

Greenference terms of useGreenference privacy policy