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

10 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:crusoe	1.0M	$0.30/M	$1.26/M	$0.0073/M	0.6s	122 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	0.6s	122 tps
Gemma 4 31B BF16 google/gemma-4-31b-it:crusoe	262k	$0.15/M	$0.42/M	$0.15/M	0.5s	38 tps
Gemma 4 31B (Thinking) BF16 google/gemma-4-31b-it:thinking:crusoe	262k	$0.15/M	$0.42/M	$0.15/M	0.5s	38 tps
GLM 5.3 FP4 z-ai/glm-5.3:crusoe	1.0M	$1.47/M	$4.62/M	$0.27/M	1.3s	103 tps
GLM 5.3 (Thinking) FP4 z-ai/glm-5.3:thinking:crusoe	1.0M	$1.47/M	$4.62/M	$0.27/M	1.3s	103 tps
GLM 5.3 Flash FP4 z-ai/glm-5.3-flash:crusoe	1.0M	$0.16/M	$0.53/M	$0.03/M	0.9s	77 tps
GPT OSS 120B BF16 openai/gpt-oss-120b:crusoe	131k	$0.05/M	$0.26/M	$0.05/M	0.3s	166 tps
Kimi K2.6 BF16 moonshotai/kimi-k2.6:crusoe	262k	$0.73/M	$3.68/M	$0.37/M	0.8s	67.5 tps
Kimi K2.6 Thinking BF16 moonshotai/kimi-k2.6:thinking:crusoe	262k	$0.73/M	$3.68/M	$0.37/M	0.8s	67.5 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

TTFT

0.6s

Throughput

122 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

TTFT

0.6s

Throughput

122 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

TTFT

0.5s

Throughput

38 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

TTFT

0.5s

Throughput

38 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

TTFT

1.3s

Throughput

103 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

TTFT

1.3s

Throughput

103 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

TTFT

0.9s

Throughput

77 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

TTFT

0.3s

Throughput

166 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

TTFT

0.8s

Throughput

67.5 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

TTFT

0.8s

Throughput

67.5 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-v4.1-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.