Crusoe

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 Crusoe

Model name

18 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash FP8 deepseek/deepseek-v4-flash:crusoe	1.0M	$0.15/M	$0.29/M	$0.03/M	0%	0.6s	59 tps
DeepSeek V4 Flash (Thinking) FP8 deepseek/deepseek-v4-flash:thinking:crusoe	1.0M	$0.15/M	$0.29/M	$0.03/M	0%	0.6s	59 tps
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:crusoe	1.0M	$1.83/M	$3.65/M	$0.16/M	27.7%	0.7s	66 tps
DeepSeek V4 Pro (Thinking) FP8 deepseek/deepseek-v4-pro:thinking:crusoe	1.0M	$1.83/M	$3.65/M	$0.16/M	0%	0.7s	66 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:crusoe	1.0M	$0.30/M	$1.26/M	$0.0073/M	0%	0.5s	100 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:crusoe	1.0M	$0.30/M	$1.26/M	$0.0073/M	0%	0.5s	100 tps
DeepSeek V4.1 Flash 1017 FP8 deepseek/deepseek-v4.1-flash-1017:crusoe	1.0M	$0.30/M	$1.26/M	$0.0073/M	N/A	0.5s	109 tps
DeepSeek V4.1 Flash 1017 (Thinking) FP8 deepseek/deepseek-v4.1-flash-1017:thinking:crusoe	1.0M	$0.30/M	$1.26/M	$0.0073/M	N/A	0.5s	109 tps
Gemma 4 31B BF16 google/gemma-4-31b-it:crusoe	262k	$0.15/M	$0.42/M	$0.15/M	<0.1%	0.4s	41 tps
Gemma 4 31B (Thinking) BF16 google/gemma-4-31b-it:thinking:crusoe	262k	$0.15/M	$0.42/M	$0.15/M	<0.1%	0.4s	41 tps
GLM 5.3 FP4 z-ai/glm-5.3:crusoe	1.0M	$1.47/M	$4.62/M	$0.27/M	0%	0.8s	97 tps
GLM 5.3 (Thinking) FP4 z-ai/glm-5.3:thinking:crusoe	1.0M	$1.47/M	$4.62/M	$0.27/M	0%	0.8s	97 tps
GLM 5.3 Flash FP4 z-ai/glm-5.3-flash:crusoe	1.0M	$0.16/M	$0.53/M	$0.03/M	6%	0.9s	142 tps
GPT OSS 120B BF16 openai/gpt-oss-120b:crusoe	131k	$0.05/M	$0.26/M	$0.05/M	N/A	0.2s	350 tps
Kimi K2.6 BF16 moonshotai/kimi-k2.6:crusoe	262k	$0.73/M	$3.68/M	$0.37/M	N/A	0.3s	76 tps
Kimi K2.6 Thinking BF16 moonshotai/kimi-k2.6:thinking:crusoe	262k	$0.73/M	$3.68/M	$0.37/M	N/A	0.3s	76 tps
Nvidia Nemotron 3 Super 120B FP8 nvidia/nemotron-3-super-120b-a12b:crusoe	1.0M	$0.31/M	$2.52/M	$0.16/M	24.7%	0.4s	169 tps
Nvidia Nemotron 3 Super 120B Thinking FP8 nvidia/nemotron-3-super-120b-a12b:thinking:crusoe	1.0M	$0.31/M	$2.52/M	$0.16/M	24.7%	0.4s	169 tps

DeepSeek V4 Flash

FP8

deepseek/deepseek-v4-flash:crusoe

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

0.6s

Throughput

59 tps

DeepSeek V4 Flash (Thinking)

FP8

deepseek/deepseek-v4-flash:thinking:crusoe

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

0.6s

Throughput

59 tps

DeepSeek V4 Pro

FP8

deepseek/deepseek-v4-pro:crusoe

Context

1.0M

Input /M

$1.83/M

Output /M

$3.65/M

Cache read /M

$0.16/M

Cache hit

27.7%

TTFT

0.7s

Throughput

66 tps

DeepSeek V4 Pro (Thinking)

FP8

deepseek/deepseek-v4-pro:thinking:crusoe

Context

1.0M

Input /M

$1.83/M

Output /M

$3.65/M

Cache read /M

$0.16/M

Cache hit

0%

TTFT

0.7s

Throughput

66 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:crusoe

Context

1.0M

Input /M

$0.30/M

Output /M

$1.26/M

Cache read /M

$0.0073/M

Cache hit

0%

TTFT

0.5s

Throughput

100 tps

DeepSeek V4.1 Flash (Thinking)

FP8

deepseek/deepseek-v4.1-flash:thinking:crusoe

Context

1.0M

Input /M

$0.30/M

Output /M

$1.26/M

Cache read /M

$0.0073/M

Cache hit

0%

TTFT

0.5s

Throughput

100 tps

DeepSeek V4.1 Flash 1017

FP8

deepseek/deepseek-v4.1-flash-1017:crusoe

Context

1.0M

Input /M

$0.30/M

Output /M

$1.26/M

Cache read /M

$0.0073/M

Cache hit

N/A

TTFT

0.5s

Throughput

109 tps

DeepSeek V4.1 Flash 1017 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.30/M

Output /M

$1.26/M

Cache read /M

$0.0073/M

Cache hit

N/A

TTFT

0.5s

Throughput

109 tps

Gemma 4 31B

BF16

google/gemma-4-31b-it:crusoe

Context

262k

Input /M

$0.15/M

Output /M

$0.42/M

Cache read /M

$0.15/M

Cache hit

<0.1%

TTFT

0.4s

Throughput

41 tps

Gemma 4 31B (Thinking)

BF16

google/gemma-4-31b-it:thinking:crusoe

Context

262k

Input /M

$0.15/M

Output /M

$0.42/M

Cache read /M

$0.15/M

Cache hit

<0.1%

TTFT

0.4s

Throughput

41 tps

GLM 5.3

FP4

z-ai/glm-5.3:crusoe

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

Cache hit

0%

TTFT

0.8s

Throughput

97 tps

GLM 5.3 (Thinking)

FP4

z-ai/glm-5.3:thinking:crusoe

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.27/M

Cache hit

0%

TTFT

0.8s

Throughput

97 tps

GLM 5.3 Flash

FP4

z-ai/glm-5.3-flash:crusoe

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.03/M

Cache hit

6%

TTFT

0.9s

Throughput

142 tps

GPT OSS 120B

BF16

openai/gpt-oss-120b:crusoe

Context

131k

Input /M

$0.05/M

Output /M

$0.26/M

Cache read /M

$0.05/M

Cache hit

N/A

TTFT

0.2s

Throughput

350 tps

Kimi K2.6

BF16

moonshotai/kimi-k2.6:crusoe

Context

262k

Input /M

$0.73/M

Output /M

$3.68/M

Cache read /M

$0.37/M

Cache hit

N/A

TTFT

0.3s

Throughput

76 tps

Kimi K2.6 Thinking

BF16

moonshotai/kimi-k2.6:thinking:crusoe

Context

262k

Input /M

$0.73/M

Output /M

$3.68/M

Cache read /M

$0.37/M

Cache hit

N/A

TTFT

0.3s

Throughput

76 tps

Nvidia Nemotron 3 Super 120B

FP8

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

Context

1.0M

Input /M

$0.31/M

Output /M

$2.52/M

Cache read /M

$0.16/M

Cache hit

24.7%

TTFT

0.4s

Throughput

169 tps

Nvidia Nemotron 3 Super 120B Thinking

FP8

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

Context

1.0M

Input /M

$0.31/M

Output /M

$2.52/M

Cache read /M

$0.16/M

Cache hit

24.7%

TTFT

0.4s

Throughput

169 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 Crusoe via the API

Call a model served by Crusoe 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:crusoe",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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