Gerra

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 Gerra

Model name

25 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4 Flash FP8 deepseek/deepseek-v4-flash:gerra	262k	$0.142/M	$0.285/M	$0.0356/M	N/A	N/A
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:gerra	262k	$1.10/M	$2.19/M	$0.274/M	N/A	N/A
GLM 4.7 Flash FP8 z-ai/glm-4.7-flash:gerra	203k	$0.0726/M	$0.415/M	$0.0182/M	N/A	N/A
GLM 4.7 Flash (Thinking) FP8 z-ai/glm-4.7-flash:thinking:gerra	203k	$0.0726/M	$0.415/M	$0.0182/M	N/A	N/A
GLM 5.1 FP8 z-ai/glm-5.1:gerra	203k	$0.748/M	$2.59/M	$0.187/M	N/A	N/A
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:gerra	203k	$0.748/M	$2.59/M	$0.187/M	N/A	N/A
GLM 5.2 FP8 z-ai/glm-5.2:gerra	262k	$0.436/M	$1.37/M	$0.129/M	N/A	N/A
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:gerra	262k	$0.436/M	$1.37/M	$0.129/M	N/A	N/A
GPT OSS 120B FP8 openai/gpt-oss-120b:gerra	131k	$0.349/M	$0.748/M	$0.0873/M	N/A	N/A
Kimi K2.6 FP8 moonshotai/kimi-k2.6:gerra	262k	$0.519/M	$2.70/M	$0.214/M	N/A	N/A
Kimi K2.6 Thinking FP8 moonshotai/kimi-k2.6:thinking:gerra	262k	$0.519/M	$2.70/M	$0.214/M	N/A	N/A
Kimi K2.7 Code FP8 moonshotai/kimi-k2.7-code:gerra	262k	$0.986/M	$4.15/M	$0.246/M	N/A	N/A
Llama 3.3 70B Instruct FP8 meta-llama/llama-3.3-70b-instruct:gerra	131k	$0.0499/M	$0.229/M	$0.0125/M	N/A	N/A
MiniMax M2.5 FP8 minimax/minimax-m2.5:gerra	205k	$0.311/M	$1.25/M	$0.0778/M	N/A	N/A
MiniMax M3 FP8 minimax/minimax-m3:gerra	262k	$0.311/M	$1.25/M	$0.0778/M	N/A	N/A
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:gerra	262k	$0.311/M	$1.25/M	$0.0778/M	N/A	N/A
Nvidia Nemotron 3 Super 120B FP8 nvidia/nemotron-3-super-120b-a12b:gerra	262k	$0.0499/M	$0.249/M	$0.0125/M	N/A	N/A
Nvidia Nemotron 3 Super 120B Thinking FP8 nvidia/nemotron-3-super-120b-a12b:thinking:gerra	262k	$0.0499/M	$0.249/M	$0.0125/M	N/A	N/A
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B:gerra	262k	$0.116/M	$0.83/M	$0.0748/M	N/A	N/A
Qwen 3.6 35B A3B Thinking FP8 Qwen/Qwen3.6-35B-A3B:thinking:gerra	262k	$0.116/M	$0.83/M	$0.0748/M	N/A	N/A
Qwen3 Coder Next qwen/qwen3-coder-next:gerra	262k	$0.286/M	$1.50/M	$0.0838/M	N/A	N/A
Qwen3.5 122B A10B qwen3.5-122b-a10b:gerra	262k	$0.454/M	$3.63/M	$0.396/M	N/A	N/A
Qwen3.5 122B A10B Thinking qwen3.5-122b-a10b:thinking:gerra	262k	$0.454/M	$3.63/M	$0.396/M	N/A	N/A
Qwen3.5 397B FP8 qwen/qwen3.5-397b-a17b:gerra	256k	$0.571/M	$3.63/M	$0.143/M	N/A	N/A
Qwen3.5 397B Thinking FP8 qwen/qwen3.5-397b-a17b-thinking:gerra	256k	$0.571/M	$3.63/M	$0.143/M	N/A	N/A

DeepSeek V4 Flash

FP8

deepseek/deepseek-v4-flash:gerra

Context

262k

Input /M

$0.142/M

Output /M

$0.285/M

Cache read /M

$0.0356/M

TTFT

N/A

Throughput

N/A

DeepSeek V4 Pro

FP8

deepseek/deepseek-v4-pro:gerra

Context

262k

Input /M

$1.10/M

Output /M

$2.19/M

Cache read /M

$0.274/M

TTFT

N/A

Throughput

N/A

GLM 4.7 Flash

FP8

z-ai/glm-4.7-flash:gerra

Context

203k

Input /M

$0.0726/M

Output /M

$0.415/M

Cache read /M

$0.0182/M

TTFT

N/A

Throughput

N/A

GLM 4.7 Flash (Thinking)

FP8

z-ai/glm-4.7-flash:thinking:gerra

Context

203k

Input /M

$0.0726/M

Output /M

$0.415/M

Cache read /M

$0.0182/M

TTFT

N/A

Throughput

N/A

GLM 5.1

FP8

z-ai/glm-5.1:gerra

Context

203k

Input /M

$0.748/M

Output /M

$2.59/M

Cache read /M

$0.187/M

TTFT

N/A

Throughput

N/A

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:gerra

Context

203k

Input /M

$0.748/M

Output /M

$2.59/M

Cache read /M

$0.187/M

TTFT

N/A

Throughput

N/A

GLM 5.2

FP8

z-ai/glm-5.2:gerra

Context

262k

Input /M

$0.436/M

Output /M

$1.37/M

Cache read /M

$0.129/M

TTFT

N/A

Throughput

N/A

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:gerra

Context

262k

Input /M

$0.436/M

Output /M

$1.37/M

Cache read /M

$0.129/M

TTFT

N/A

Throughput

N/A

GPT OSS 120B

FP8

openai/gpt-oss-120b:gerra

Context

131k

Input /M

$0.349/M

Output /M

$0.748/M

Cache read /M

$0.0873/M

TTFT

N/A

Throughput

N/A

Kimi K2.6

FP8

moonshotai/kimi-k2.6:gerra

Context

262k

Input /M

$0.519/M

Output /M

$2.70/M

Cache read /M

$0.214/M

TTFT

N/A

Throughput

N/A

Kimi K2.6 Thinking

FP8

moonshotai/kimi-k2.6:thinking:gerra

Context

262k

Input /M

$0.519/M

Output /M

$2.70/M

Cache read /M

$0.214/M

TTFT

N/A

Throughput

N/A

Kimi K2.7 Code

FP8

moonshotai/kimi-k2.7-code:gerra

Context

262k

Input /M

$0.986/M

Output /M

$4.15/M

Cache read /M

$0.246/M

TTFT

N/A

Throughput

N/A

Llama 3.3 70B Instruct

FP8

meta-llama/llama-3.3-70b-instruct:gerra

Context

131k

Input /M

$0.0499/M

Output /M

$0.229/M

Cache read /M

$0.0125/M

TTFT

N/A

Throughput

N/A

MiniMax M2.5

FP8

minimax/minimax-m2.5:gerra

Context

205k

Input /M

$0.311/M

Output /M

$1.25/M

Cache read /M

$0.0778/M

TTFT

N/A

Throughput

N/A

MiniMax M3

FP8

minimax/minimax-m3:gerra

Context

262k

Input /M

$0.311/M

Output /M

$1.25/M

Cache read /M

$0.0778/M

TTFT

N/A

Throughput

N/A

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:gerra

Context

262k

Input /M

$0.311/M

Output /M

$1.25/M

Cache read /M

$0.0778/M

TTFT

N/A

Throughput

N/A

Nvidia Nemotron 3 Super 120B

FP8

nvidia/nemotron-3-super-120b-a12b:gerra

Context

262k

Input /M

$0.0499/M

Output /M

$0.249/M

Cache read /M

$0.0125/M

TTFT

N/A

Throughput

N/A

Nvidia Nemotron 3 Super 120B Thinking

FP8

nvidia/nemotron-3-super-120b-a12b:thinking:gerra

Context

262k

Input /M

$0.0499/M

Output /M

$0.249/M

Cache read /M

$0.0125/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B

FP8

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

Context

262k

Input /M

$0.116/M

Output /M

$0.83/M

Cache read /M

$0.0748/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B Thinking

FP8

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

Context

262k

Input /M

$0.116/M

Output /M

$0.83/M

Cache read /M

$0.0748/M

TTFT

N/A

Throughput

N/A

Qwen3 Coder Next

qwen/qwen3-coder-next:gerra

Context

262k

Input /M

$0.286/M

Output /M

$1.50/M

Cache read /M

$0.0838/M

TTFT

N/A

Throughput

N/A

Qwen3.5 122B A10B

qwen3.5-122b-a10b:gerra

Context

262k

Input /M

$0.454/M

Output /M

$3.63/M

Cache read /M

$0.396/M

TTFT

N/A

Throughput

N/A

Qwen3.5 122B A10B Thinking

qwen3.5-122b-a10b:thinking:gerra

Context

262k

Input /M

$0.454/M

Output /M

$3.63/M

Cache read /M

$0.396/M

TTFT

N/A

Throughput

N/A

Qwen3.5 397B

FP8

qwen/qwen3.5-397b-a17b:gerra

Context

256k

Input /M

$0.571/M

Output /M

$3.63/M

Cache read /M

$0.143/M

TTFT

N/A

Throughput

N/A

Qwen3.5 397B Thinking

FP8

qwen/qwen3.5-397b-a17b-thinking:gerra

Context

256k

Input /M

$0.571/M

Output /M

$3.63/M

Cache read /M

$0.143/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 Gerra via the API

Call a model served by Gerra 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": "deepseek/deepseek-v4-flash:gerra",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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