Kitani

GLB

51 models available

NanoGPT requires zero data retention for Kitani routes serving Qwen 3.8 27B, GLM 5.3, Kimi K3, DeepSeek V4.1 Flash, GLM 5.3 Flash Uncensored, MiMo V2.6 Flash RL, and MiMo V2.6 Pro RL, including applicable thinking variants. Prompts and outputs are not retained or used for training; usage and billing metadata are retained. Kitani documents a 503 response when no qualified ZDR deployment is available. Its catalog reports encrypted inference transport (TLS) for the reviewed DeepSeek V4.1 Flash, uncensored, and MiMo RL routes. This is not a provider-wide ZDR commitment.

Some routes not ZDR

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

Not ZDR

Aion-RP Llama 3.1 8B, Cogito v1 Preview Qwen 32B, Gemma 3 27B, Gemma 4 26B A4B, Gemma 4 31B, Granite 4.2 8B, Qwen 2.5 32B Abliterated, Veiled Calla 12B

ZDR

Artemis 31B v1.2, Assistant Pepe 32B, Chimera X, DeepSeek V4 Pro 0813, DeepSeek V4 Pro 0813 (Thinking), DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic, DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash 1017 (Thinking), EVA-Qwen2.5-32B-v0.2, Gemma 3 12B IT, Gemma 3 4B IT, Gemma 4 12B Instruct, Gemma 4 31B Gembrain uncensored heretic, Gemma 4 31B Gembrain X Core, Gemma 4 31B MeroMero v2, Gemma 4 31B Split-Untied, Gemsicle, GLM 5.2, GLM 5.2 (Thinking), GLM 5.3, GLM 5.3 (Thinking), GLM 5.3 Flash, GPT OSS Safeguard 20B, GrayLine Qwen3 8B, Kimi K2.6, Kimi K2.6 Thinking, LFM2.5 2.6B, Llama 3.1 8B, Llama 3.2 3B Instruct, Ministral 14B, Ministral 3B, Ministral 8B, Mistral Nemo, Mistral Small 3 24B (2501), Mistral Small 3.2 24B (2506), Neural Daredevil 8B abliterated, Phi 4 Mini, Qwen 3.8 27B Antislop, Qwen 3.8 27B Queen, Qwen 3.8 27B Swift, Qwen 3.8 27B Uncensored, Qwen 3.8 27B Uncensored Thinking, The Drummer Cydonia 24B v4.3

Broader provider policy: Not ZDR. The labels beside individual models apply only to those routes.

Models served by Kitani

51 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
Aion-RP Llama 3.1 8B Not ZDR	8k	$0.819/M	$1.66/M	$0.41/M	N/A	N/A
Artemis 31B v1.2 INT4 ZDR	66k	$0.105/M	$0.472/M	$0.0525/M	N/A	N/A
Assistant Pepe 32B INT4 ZDR	41k	$0.105/M	$0.472/M	$0.0525/M	N/A	N/A
Chimera X INT4 ZDR	66k	$0.105/M	$0.367/M	$0.042/M	N/A	N/A
Cogito v1 Preview Qwen 32B INT4 Not ZDR	8k	$1.87/M	$1.87/M	$0.934/M	N/A	N/A
DeepSeek V4 Pro 0813 ZDR	1.0M	$1.26/M	$3.99/M	$0.0462/M	N/A	N/A
DeepSeek V4 Pro 0813 (Thinking) ZDR	1.0M	$1.26/M	$3.99/M	$0.0462/M	N/A	N/A
DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic BF16 ZDR	33k	$0.294/M	$0.294/M	$0.147/M	N/A	N/A
DeepSeek V4.1 Flash 1017 ZDR	1.0M	$0.263/M	$1.16/M	$0.0063/M	N/A	N/A
DeepSeek V4.1 Flash 1017 (Thinking) ZDR	1.0M	$0.263/M	$1.16/M	$0.0063/M	N/A	N/A
EVA-Qwen2.5-32B-v0.2 INT4 ZDR	8k	$0.818/M	$0.818/M	$0.409/M	N/A	N/A
Gemma 3 12B IT INT4 ZDR	8k	$0.265/M	$0.265/M	$0.132/M	N/A	N/A
Gemma 3 27B INT4 Not ZDR	8k	$0.293/M	$0.293/M	$0.147/M	N/A	N/A
Gemma 3 4B IT INT4 ZDR	8k	$0.19/M	$0.19/M	$0.0948/M	N/A	N/A
Gemma 4 12B Instruct INT4 ZDR	8k	$0.0473/M	$0.242/M	$0.0236/M	N/A	N/A
Gemma 4 26B A4B INT4 Not ZDR	8k	$0.113/M	$0.378/M	$0.0567/M	N/A	N/A
Gemma 4 31B INT4 Not ZDR	8k	$0.0945/M	$0.452/M	$0.0473/M	N/A	N/A
Gemma 4 31B Gembrain uncensored heretic INT4 ZDR	66k	$0.311/M	$0.311/M	$0.0525/M	N/A	N/A
Gemma 4 31B Gembrain X Core INT4 ZDR	66k	$0.311/M	$0.311/M	$0.0525/M	N/A	N/A
Gemma 4 31B MeroMero v2 INT4 ZDR	66k	$0.0945/M	$0.462/M	$0.0473/M	N/A	N/A
Gemma 4 31B Split-Untied ZDR	262k	$0.105/M	$0.315/M	N/A	N/A	N/A
Gemsicle INT4 ZDR	66k	$0.0945/M	$0.462/M	$0.0473/M	N/A	N/A
GLM 5.2 ZDR	262k	$1.47/M	$4.62/M	$0.273/M	N/A	N/A
GLM 5.2 (Thinking) ZDR	262k	$1.47/M	$4.62/M	$0.273/M	N/A	N/A
GLM 5.3 ZDR	1.0M	$1.36/M	$4.46/M	$0.273/M	N/A	N/A
GLM 5.3 (Thinking) ZDR	1.0M	$1.36/M	$4.46/M	$0.273/M	N/A	N/A
GLM 5.3 Flash ZDR	1.0M	$0.157/M	$0.525/M	$0.0315/M	N/A	N/A
GPT OSS Safeguard 20B MXFP4 ZDR	8k	$0.0709/M	$0.294/M	$0.0354/M	N/A	N/A
Granite 4.2 8B Not ZDR	8k	$0.0945/M	$0.142/M	$0.0473/M	N/A	N/A
GrayLine Qwen3 8B ZDR	8k	$0.294/M	$0.294/M	$0.147/M	N/A	N/A
Kimi K2.6 ZDR	262k	$0.998/M	$4.20/M	$0.168/M	N/A	N/A
Kimi K2.6 Thinking ZDR	262k	$0.998/M	$4.20/M	$0.168/M	N/A	N/A
LFM2.5 2.6B ZDR	8k	$0.0945/M	$0.189/M	$0.0473/M	N/A	N/A
Llama 3.1 8B INT4 ZDR	8k	$0.0514/M	$0.0803/M	$0.0257/M	N/A	N/A
Llama 3.2 3B Instruct INT4 ZDR	8k	$0.0289/M	$0.0466/M	$0.0145/M	N/A	N/A
Ministral 14B INT4 ZDR	8k	$0.189/M	$0.189/M	$0.0945/M	N/A	N/A
Ministral 3B INT4 ZDR	8k	$0.0945/M	$0.0945/M	$0.0473/M	N/A	N/A
Ministral 8B INT4 ZDR	8k	$0.142/M	$0.142/M	$0.0709/M	N/A	N/A
Mistral Nemo INT4 ZDR	8k	$0.0948/M	$0.114/M	$0.0474/M	N/A	N/A
Mistral Small 3 24B (2501) INT4 ZDR	8k	$0.109/M	$0.343/M	$0.0546/M	N/A	N/A
Mistral Small 3.2 24B (2506) INT4 ZDR	8k	$0.189/M	$0.399/M	$0.0945/M	N/A	N/A
Neural Daredevil 8B abliterated INT4 ZDR	8k	$0.441/M	$0.441/M	$0.221/M	N/A	N/A
Phi 4 Mini INT4 ZDR	8k	$0.161/M	$0.693/M	$0.0803/M	N/A	N/A
Qwen 2.5 32B Abliterated INT4 Not ZDR	8k	$0.714/M	$0.714/M	$0.357/M	N/A	N/A
Qwen 3.8 27B Antislop FP8 ZDR	66k	$0.0945/M	$0.578/M	$0.042/M	N/A	N/A
Qwen 3.8 27B Queen INT4 ZDR	8k	$0.242/M	$1.55/M	$0.118/M	N/A	N/A
Qwen 3.8 27B Swift INT4 ZDR	66k	$0.0945/M	$0.578/M	$0.042/M	N/A	N/A
Qwen 3.8 27B Uncensored FP8 ZDR	1.0M	$0.813/M	$2.57/M	$0.147/M	N/A	N/A
Qwen 3.8 27B Uncensored Thinking FP8 ZDR	1.0M	$0.813/M	$2.57/M	$0.147/M	N/A	N/A
The Drummer Cydonia 24B v4.3 INT4 ZDR	66k	$0.113/M	$0.142/M	$0.0567/M	N/A	N/A
Veiled Calla 12B FP8 Not ZDR	8k	$0.294/M	$0.294/M	$0.147/M	N/A	N/A

Aion-RP Llama 3.1 8B

Not ZDR

Context: 8k
Input /M: $0.819/M
Output /M: $1.66/M
Cache read /M: $0.41/M
TTFT: N/A
Throughput: N/A

Artemis 31B v1.2

INT4

ZDR

Context: 66k
Input /M: $0.105/M
Output /M: $0.472/M
Cache read /M: $0.0525/M
TTFT: N/A
Throughput: N/A

Assistant Pepe 32B

INT4

ZDR

Context: 41k
Input /M: $0.105/M
Output /M: $0.472/M
Cache read /M: $0.0525/M
TTFT: N/A
Throughput: N/A

Chimera X

INT4

ZDR

Context: 66k
Input /M: $0.105/M
Output /M: $0.367/M
Cache read /M: $0.042/M
TTFT: N/A
Throughput: N/A

Cogito v1 Preview Qwen 32B

INT4

Not ZDR

Context: 8k
Input /M: $1.87/M
Output /M: $1.87/M
Cache read /M: $0.934/M
TTFT: N/A
Throughput: N/A

DeepSeek V4 Pro 0813

ZDR

Context: 1.0M
Input /M: $1.26/M
Output /M: $3.99/M
Cache read /M: $0.0462/M
TTFT: N/A
Throughput: N/A

DeepSeek V4 Pro 0813 (Thinking)

ZDR

Context: 1.0M
Input /M: $1.26/M
Output /M: $3.99/M
Cache read /M: $0.0462/M
TTFT: N/A
Throughput: N/A

DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic

BF16

ZDR

Context: 33k
Input /M: $0.294/M
Output /M: $0.294/M
Cache read /M: $0.147/M
TTFT: N/A
Throughput: N/A

DeepSeek V4.1 Flash 1017

ZDR

Context: 1.0M
Input /M: $0.263/M
Output /M: $1.16/M
Cache read /M: $0.0063/M
TTFT: N/A
Throughput: N/A

DeepSeek V4.1 Flash 1017 (Thinking)

ZDR

Context: 1.0M
Input /M: $0.263/M
Output /M: $1.16/M
Cache read /M: $0.0063/M
TTFT: N/A
Throughput: N/A

EVA-Qwen2.5-32B-v0.2

INT4

ZDR

Context: 8k
Input /M: $0.818/M
Output /M: $0.818/M
Cache read /M: $0.409/M
TTFT: N/A
Throughput: N/A

Gemma 3 12B IT

INT4

ZDR

Context: 8k
Input /M: $0.265/M
Output /M: $0.265/M
Cache read /M: $0.132/M
TTFT: N/A
Throughput: N/A

Gemma 3 27B

INT4

Not ZDR

Context: 8k
Input /M: $0.293/M
Output /M: $0.293/M
Cache read /M: $0.147/M
TTFT: N/A
Throughput: N/A

Gemma 3 4B IT

INT4

ZDR

Context: 8k
Input /M: $0.19/M
Output /M: $0.19/M
Cache read /M: $0.0948/M
TTFT: N/A
Throughput: N/A

Gemma 4 12B Instruct

INT4

ZDR

Context: 8k
Input /M: $0.0473/M
Output /M: $0.242/M
Cache read /M: $0.0236/M
TTFT: N/A
Throughput: N/A

Gemma 4 26B A4B

INT4

Not ZDR

Context: 8k
Input /M: $0.113/M
Output /M: $0.378/M
Cache read /M: $0.0567/M
TTFT: N/A
Throughput: N/A

Gemma 4 31B

INT4

Not ZDR

Context: 8k
Input /M: $0.0945/M
Output /M: $0.452/M
Cache read /M: $0.0473/M
TTFT: N/A
Throughput: N/A

Gemma 4 31B Gembrain uncensored heretic

INT4

ZDR

Context: 66k
Input /M: $0.311/M
Output /M: $0.311/M
Cache read /M: $0.0525/M
TTFT: N/A
Throughput: N/A

Gemma 4 31B Gembrain X Core

INT4

ZDR

Context: 66k
Input /M: $0.311/M
Output /M: $0.311/M
Cache read /M: $0.0525/M
TTFT: N/A
Throughput: N/A

Gemma 4 31B MeroMero v2

INT4

ZDR

Context: 66k
Input /M: $0.0945/M
Output /M: $0.462/M
Cache read /M: $0.0473/M
TTFT: N/A
Throughput: N/A

Gemma 4 31B Split-Untied

ZDR

Context: 262k
Input /M: $0.105/M
Output /M: $0.315/M
Cache read /M: N/A
TTFT: N/A
Throughput: N/A

Gemsicle

INT4

ZDR

Context: 66k
Input /M: $0.0945/M
Output /M: $0.462/M
Cache read /M: $0.0473/M
TTFT: N/A
Throughput: N/A

GLM 5.2

ZDR

Context: 262k
Input /M: $1.47/M
Output /M: $4.62/M
Cache read /M: $0.273/M
TTFT: N/A
Throughput: N/A

GLM 5.2 (Thinking)

ZDR

Context: 262k
Input /M: $1.47/M
Output /M: $4.62/M
Cache read /M: $0.273/M
TTFT: N/A
Throughput: N/A

GLM 5.3

ZDR

Context: 1.0M
Input /M: $1.36/M
Output /M: $4.46/M
Cache read /M: $0.273/M
TTFT: N/A
Throughput: N/A

GLM 5.3 (Thinking)

ZDR

Context: 1.0M
Input /M: $1.36/M
Output /M: $4.46/M
Cache read /M: $0.273/M
TTFT: N/A
Throughput: N/A

GLM 5.3 Flash

ZDR

Context: 1.0M
Input /M: $0.157/M
Output /M: $0.525/M
Cache read /M: $0.0315/M
TTFT: N/A
Throughput: N/A

GPT OSS Safeguard 20B

MXFP4

ZDR

Context: 8k
Input /M: $0.0709/M
Output /M: $0.294/M
Cache read /M: $0.0354/M
TTFT: N/A
Throughput: N/A

Granite 4.2 8B

Not ZDR

Context: 8k
Input /M: $0.0945/M
Output /M: $0.142/M
Cache read /M: $0.0473/M
TTFT: N/A
Throughput: N/A

GrayLine Qwen3 8B

ZDR

Context: 8k
Input /M: $0.294/M
Output /M: $0.294/M
Cache read /M: $0.147/M
TTFT: N/A
Throughput: N/A

Kimi K2.6

ZDR

Context: 262k
Input /M: $0.998/M
Output /M: $4.20/M
Cache read /M: $0.168/M
TTFT: N/A
Throughput: N/A

Kimi K2.6 Thinking

ZDR

Context: 262k
Input /M: $0.998/M
Output /M: $4.20/M
Cache read /M: $0.168/M
TTFT: N/A
Throughput: N/A

LFM2.5 2.6B

ZDR

Context: 8k
Input /M: $0.0945/M
Output /M: $0.189/M
Cache read /M: $0.0473/M
TTFT: N/A
Throughput: N/A

Llama 3.1 8B

INT4

ZDR

Context: 8k
Input /M: $0.0514/M
Output /M: $0.0803/M
Cache read /M: $0.0257/M
TTFT: N/A
Throughput: N/A

Llama 3.2 3B Instruct

INT4

ZDR

Context: 8k
Input /M: $0.0289/M
Output /M: $0.0466/M
Cache read /M: $0.0145/M
TTFT: N/A
Throughput: N/A

Ministral 14B

INT4

ZDR

Context: 8k
Input /M: $0.189/M
Output /M: $0.189/M
Cache read /M: $0.0945/M
TTFT: N/A
Throughput: N/A

Ministral 3B

INT4

ZDR

Context: 8k
Input /M: $0.0945/M
Output /M: $0.0945/M
Cache read /M: $0.0473/M
TTFT: N/A
Throughput: N/A

Ministral 8B

INT4

ZDR

Context: 8k
Input /M: $0.142/M
Output /M: $0.142/M
Cache read /M: $0.0709/M
TTFT: N/A
Throughput: N/A

Mistral Nemo

INT4

ZDR

Context: 8k
Input /M: $0.0948/M
Output /M: $0.114/M
Cache read /M: $0.0474/M
TTFT: N/A
Throughput: N/A

Mistral Small 3 24B (2501)

INT4

ZDR

Context: 8k
Input /M: $0.109/M
Output /M: $0.343/M
Cache read /M: $0.0546/M
TTFT: N/A
Throughput: N/A

Mistral Small 3.2 24B (2506)

INT4

ZDR

Context: 8k
Input /M: $0.189/M
Output /M: $0.399/M
Cache read /M: $0.0945/M
TTFT: N/A
Throughput: N/A

Neural Daredevil 8B abliterated

INT4

ZDR

Context: 8k
Input /M: $0.441/M
Output /M: $0.441/M
Cache read /M: $0.221/M
TTFT: N/A
Throughput: N/A

Phi 4 Mini

INT4

ZDR

Context: 8k
Input /M: $0.161/M
Output /M: $0.693/M
Cache read /M: $0.0803/M
TTFT: N/A
Throughput: N/A

Qwen 2.5 32B Abliterated

INT4

Not ZDR

Context: 8k
Input /M: $0.714/M
Output /M: $0.714/M
Cache read /M: $0.357/M
TTFT: N/A
Throughput: N/A

Qwen 3.8 27B Antislop

FP8

ZDR

Context: 66k
Input /M: $0.0945/M
Output /M: $0.578/M
Cache read /M: $0.042/M
TTFT: N/A
Throughput: N/A

Qwen 3.8 27B Queen

INT4

ZDR

Context: 8k
Input /M: $0.242/M
Output /M: $1.55/M
Cache read /M: $0.118/M
TTFT: N/A
Throughput: N/A

Qwen 3.8 27B Swift

INT4

ZDR

Context: 66k
Input /M: $0.0945/M
Output /M: $0.578/M
Cache read /M: $0.042/M
TTFT: N/A
Throughput: N/A

Qwen 3.8 27B Uncensored

FP8

ZDR

Context: 1.0M
Input /M: $0.813/M
Output /M: $2.57/M
Cache read /M: $0.147/M
TTFT: N/A
Throughput: N/A

Qwen 3.8 27B Uncensored Thinking

FP8

ZDR

Context: 1.0M
Input /M: $0.813/M
Output /M: $2.57/M
Cache read /M: $0.147/M
TTFT: N/A
Throughput: N/A

The Drummer Cydonia 24B v4.3

INT4

ZDR

Context: 66k
Input /M: $0.113/M
Output /M: $0.142/M
Cache read /M: $0.0567/M
TTFT: N/A
Throughput: N/A

Veiled Calla 12B

FP8

Not ZDR

Context: 8k
Input /M: $0.294/M
Output /M: $0.294/M
Cache read /M: $0.147/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 Kitani via the API

Call a model served by Kitani 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": "aion-labs/aion-rp-llama-3.1-8b:kitani",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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