Chutes

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 Chutes

Model name

17 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
Gemma 4 31B TEE TEE verified TEE/gemma4-31b:chutes	131k	$0.16/M	$0.44/M	$0.08/M	N/A	N/A
Gemma 4 31B Thinking TEE TEE verified TEE/gemma4-31b:thinking:chutes	131k	$0.16/M	$0.44/M	$0.08/M	N/A	N/A
GLM 5.1 FP8 z-ai/glm-5.1:chutes	203k	$1.03/M	$3.23/M	$0.10/M	3.7s	22 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:chutes	203k	$1.03/M	$3.23/M	$0.10/M	3.7s	22 tps
GLM 5.1 TEE TEE verified TEE/glm-5.1:chutes	131k	$1.10/M	$3.68/M	$0.55/M	N/A	N/A
GLM 5.1 Thinking TEE TEE verified TEE/glm-5.1-thinking:chutes	131k	$1.10/M	$3.68/M	$0.55/M	N/A	N/A
GLM 5.2 TEE TEE verified TEE/glm-5.2:chutes	1.0M	$1.47/M	$4.62/M	$0.73/M	N/A	N/A
GLM 5.2 Thinking TEE TEE verified TEE/glm-5.2:thinking:chutes	1.0M	$1.47/M	$4.62/M	$0.73/M	N/A	N/A
Kimi K2.6 INT4 moonshotai/kimi-k2.6:chutes	262k	$0.53/M	$2.99/M	$0.05/M	2.5s	35 tps
Kimi K2.6 TEE TEE verified TEE/kimi-k2.6:chutes	262k	$1.00/M	$4.20/M	$0.50/M	N/A	N/A
Kimi K2.6 Thinking INT4 moonshotai/kimi-k2.6:thinking:chutes	262k	$0.53/M	$2.99/M	$0.05/M	2.5s	35 tps
Kimi K3 MXFP4 moonshotai/kimi-k3:chutes	1.0M	$3.15/M	$15.75/M	$0.31/M	2.9s	15 tps
Kimi K3 TEE TEE verified TEE/kimi-k3:chutes	1.0M	$3.15/M	$15.75/M	$1.57/M	N/A	N/A
Qwen 3.6 27B FP8 alibaba/qwen3.6-27b:chutes	262k	$0.31/M	$2.10/M	$0.03/M	2.6s	32 tps
Qwen 3.6 27B Thinking FP8 alibaba/qwen3.6-27b:thinking:chutes	262k	$0.31/M	$2.10/M	$0.03/M	2.6s	32 tps
Qwen3.8 27B FP8 qwen3.8-27b:chutes	262k	$0.25/M	$2.31/M	$0.03/M	1.7s	36 tps
Qwen3.8 27B Thinking FP8 qwen3.8-27b:thinking:chutes	262k	$0.25/M	$2.31/M	$0.03/M	1.7s	36 tps

Gemma 4 31B TEE

TEE verified

TEE/gemma4-31b:chutes

Context

131k

Input /M

$0.16/M

Output /M

$0.44/M

Cache read /M

$0.08/M

TTFT

N/A

Throughput

N/A

Gemma 4 31B Thinking TEE

TEE verified

TEE/gemma4-31b:thinking:chutes

Context

131k

Input /M

$0.16/M

Output /M

$0.44/M

Cache read /M

$0.08/M

TTFT

N/A

Throughput

N/A

GLM 5.1

FP8

z-ai/glm-5.1:chutes

Context

203k

Input /M

$1.03/M

Output /M

$3.23/M

Cache read /M

$0.10/M

TTFT

3.7s

Throughput

22 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:chutes

Context

203k

Input /M

$1.03/M

Output /M

$3.23/M

Cache read /M

$0.10/M

TTFT

3.7s

Throughput

22 tps

GLM 5.1 TEE

TEE verified

TEE/glm-5.1:chutes

Context

131k

Input /M

$1.10/M

Output /M

$3.68/M

Cache read /M

$0.55/M

TTFT

N/A

Throughput

N/A

GLM 5.1 Thinking TEE

TEE verified

TEE/glm-5.1-thinking:chutes

Context

131k

Input /M

$1.10/M

Output /M

$3.68/M

Cache read /M

$0.55/M

TTFT

N/A

Throughput

N/A

GLM 5.2 TEE

TEE verified

TEE/glm-5.2:chutes

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.73/M

TTFT

N/A

Throughput

N/A

GLM 5.2 Thinking TEE

TEE verified

TEE/glm-5.2:thinking:chutes

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.73/M

TTFT

N/A

Throughput

N/A

Kimi K2.6

INT4

moonshotai/kimi-k2.6:chutes

Context

262k

Input /M

$0.53/M

Output /M

$2.99/M

Cache read /M

$0.05/M

TTFT

2.5s

Throughput

35 tps

Kimi K2.6 TEE

TEE verified

TEE/kimi-k2.6:chutes

Context

262k

Input /M

$1.00/M

Output /M

$4.20/M

Cache read /M

$0.50/M

TTFT

N/A

Throughput

N/A

Kimi K2.6 Thinking

INT4

moonshotai/kimi-k2.6:thinking:chutes

Context

262k

Input /M

$0.53/M

Output /M

$2.99/M

Cache read /M

$0.05/M

TTFT

2.5s

Throughput

35 tps

Kimi K3

MXFP4

moonshotai/kimi-k3:chutes

Context

1.0M

Input /M

$3.15/M

Output /M

$15.75/M

Cache read /M

$0.31/M

TTFT

2.9s

Throughput

15 tps

Kimi K3 TEE

TEE verified

TEE/kimi-k3:chutes

Context

1.0M

Input /M

$3.15/M

Output /M

$15.75/M

Cache read /M

$1.57/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 27B

FP8

alibaba/qwen3.6-27b:chutes

Context

262k

Input /M

$0.31/M

Output /M

$2.10/M

Cache read /M

$0.03/M

TTFT

2.6s

Throughput

32 tps

Qwen 3.6 27B Thinking

FP8

alibaba/qwen3.6-27b:thinking:chutes

Context

262k

Input /M

$0.31/M

Output /M

$2.10/M

Cache read /M

$0.03/M

TTFT

2.6s

Throughput

32 tps

Qwen3.8 27B

FP8

qwen3.8-27b:chutes

Context

262k

Input /M

$0.25/M

Output /M

$2.31/M

Cache read /M

$0.03/M

TTFT

1.7s

Throughput

36 tps

Qwen3.8 27B Thinking

FP8

qwen3.8-27b:thinking:chutes

Context

262k

Input /M

$0.25/M

Output /M

$2.31/M

Cache read /M

$0.03/M

TTFT

1.7s

Throughput

36 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 Chutes via the API

Call a model served by Chutes 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": "TEE/gemma4-31b:chutes",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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