Munito

Munito AI France SAS states that inference content is processed transiently without storage or training use. NanoGPT uses its EU endpoint with storage and overflow disabled. Munito commits to EU request-content processing and France API/TLS termination; account, billing and support records have separate locations and retention policies.

Models served by Munito

Model name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4 Flash 0731 FP8 ZDR deepseek/deepseek-v4-flash-0731:munito	1.0M	$0.0381/M	$0.097/M	$0.00762/M	N/A	N/A
DeepSeek V4 Flash 0731 (Thinking) FP8 ZDR deepseek/deepseek-v4-flash-0731:thinking:munito	1.0M	$0.0381/M	$0.097/M	$0.00762/M	N/A	N/A
DeepSeek V4.1 Flash 1017 (Thinking) FP8 ZDR deepseek/deepseek-v4.1-flash-1017:thinking:munito	1.0M	$0.063/M	$0.252/M	$0.0013/M	N/A	N/A
Gemma 4 12B Instruct ZDR gemma-4-12b-it:munito	33k	$0.116/M	$0.347/M	N/A	N/A	N/A
GLM 5.3 Flash NVFP4 ZDR z-ai/glm-5.3-flash:munito	1.0M	$0.0536/M	$0.179/M	$0.0107/M	N/A	N/A
Kolibri 1 NVFP4 ZDR aleph-alpha/kolibri-1:munito	1.0M	$0.168/M	$0.588/M	$0.0987/M	N/A	N/A
Qwen3.8 27B NVFP4 ZDR qwen3.8-27b:munito	262k	$0.0231/M	$0.312/M	$0.0127/M	N/A	N/A
Qwen3.8 27B Thinking NVFP4 ZDR qwen3.8-27b:thinking:munito	262k	$0.0231/M	$0.312/M	$0.0127/M	N/A	N/A

DeepSeek V4 Flash 0731

FP8

ZDR

deepseek/deepseek-v4-flash-0731:munito

Context

1.0M

Input /M

$0.0381/M

Output /M

$0.097/M

Cache read /M

$0.00762/M

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0731 (Thinking)

FP8

ZDR

deepseek/deepseek-v4-flash-0731:thinking:munito

Context

1.0M

Input /M

$0.0381/M

Output /M

$0.097/M

Cache read /M

$0.00762/M

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash 1017 (Thinking)

FP8

ZDR

deepseek/deepseek-v4.1-flash-1017:thinking:munito

Context

1.0M

Input /M

$0.063/M

Output /M

$0.252/M

Cache read /M

$0.0013/M

TTFT

N/A

Throughput

N/A

Gemma 4 12B Instruct

ZDR

gemma-4-12b-it:munito

Context

33k

Input /M

$0.116/M

Output /M

$0.347/M

Cache read /M

N/A

TTFT

N/A

Throughput

N/A

GLM 5.3 Flash

NVFP4

ZDR

z-ai/glm-5.3-flash:munito

Context

1.0M

Input /M

$0.0536/M

Output /M

$0.179/M

Cache read /M

$0.0107/M

TTFT

N/A

Throughput

N/A

Kolibri 1

NVFP4

ZDR

aleph-alpha/kolibri-1:munito

Context

1.0M

Input /M

$0.168/M

Output /M

$0.588/M

Cache read /M

$0.0987/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B

NVFP4

ZDR

qwen3.8-27b:munito

Context

262k

Input /M

$0.0231/M

Output /M

$0.312/M

Cache read /M

$0.0127/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B Thinking

NVFP4

ZDR

qwen3.8-27b:thinking:munito

Context

262k

Input /M

$0.0231/M

Output /M

$0.312/M

Cache read /M

$0.0127/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 Munito via the API

Call a model served by Munito 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": "deepseek/deepseek-v4-flash-0731:munito",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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