Mixlayer

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 Mixlayer

Model name

9 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:mixlayer	262k	$0.315/M	$1.26/M	$0.00945/M	N/A	N/A
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:mixlayer	262k	$0.315/M	$1.26/M	$0.00945/M	N/A	N/A
GLM 5.3 FP8 z-ai/glm-5.3:mixlayer	262k	$1.21/M	$4.09/M	$0.242/M	N/A	N/A
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:mixlayer	262k	$1.21/M	$4.09/M	$0.242/M	N/A	N/A
Qwen 3.6 35B A3B BF16 Qwen/Qwen3.6-35B-A3B:mixlayer	131k	$0.263/M	$1.36/M	Free	N/A	N/A
Qwen 3.6 35B A3B Thinking BF16 Qwen/Qwen3.6-35B-A3B:thinking:mixlayer	131k	$0.263/M	$1.36/M	Free	N/A	N/A
Qwen3.5 9B BF16 qwen/qwen3.5-9b:mixlayer	131k	$0.105/M	$0.42/M	Free	N/A	N/A
Qwen3.8 27B BF16 qwen3.8-27b:mixlayer	262k	$0.263/M	$2.05/M	$0.084/M	N/A	N/A
Qwen3.8 27B Thinking BF16 qwen3.8-27b:thinking:mixlayer	262k	$0.263/M	$2.05/M	$0.084/M	N/A	N/A

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:mixlayer

Context

262k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

$0.00945/M

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

262k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

$0.00945/M

TTFT

N/A

Throughput

N/A

GLM 5.3

FP8

z-ai/glm-5.3:mixlayer

Context

262k

Input /M

$1.21/M

Output /M

$4.09/M

Cache read /M

$0.242/M

TTFT

N/A

Throughput

N/A

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:mixlayer

Context

262k

Input /M

$1.21/M

Output /M

$4.09/M

Cache read /M

$0.242/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B

BF16

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

Context

131k

Input /M

$0.263/M

Output /M

$1.36/M

Cache read /M

Free

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B Thinking

BF16

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

Context

131k

Input /M

$0.263/M

Output /M

$1.36/M

Cache read /M

Free

TTFT

N/A

Throughput

N/A

Qwen3.5 9B

BF16

qwen/qwen3.5-9b:mixlayer

Context

131k

Input /M

$0.105/M

Output /M

$0.42/M

Cache read /M

Free

TTFT

N/A

Throughput

N/A

Qwen3.8 27B

BF16

qwen3.8-27b:mixlayer

Context

262k

Input /M

$0.263/M

Output /M

$2.05/M

Cache read /M

$0.084/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B Thinking

BF16

qwen3.8-27b:thinking:mixlayer

Context

262k

Input /M

$0.263/M

Output /M

$2.05/M

Cache read /M

$0.084/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 Mixlayer via the API

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

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