Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Announcing TEE: Trusted Execution Environments - Now Publicly Available

NEW Chutes Search - AI-Powered Search is Live! NEW fictio - Create your own experience

Pricing

Per-token rates and TEE GPU deployments, priced in the open.

No middlemen. No markup tiers. Pay for the tokens you use, or deploy your own chute on a confidential GPU and pay by the second.

See model prices Deploy your own

chutes ~ pricing live

Public inference · pay per 1M tokens

$ curl https://llm.chutes.ai/v1/chat/completions \

-H "Authorization: Bearer $CHUTES_KEY" \

-d '{"model":"google/gemma-4-31B-turbo-TEE", ...}'

↪ 12,847 tokens · $0.0023 charged · 79 live instances

Private deployment · pay per second

$ chutes deploy my_chute:chute --accept-fee

↪ GPU rates from $1.80/hr · deploy fee starts at $5.40

Model pricing

Pay per token. No subscription, no minimum, no markup. All featured models run on confidential TEE compute.

Estimate your cost

Pick a workload. Prices update below.

Pay from a Bittensor wallet in TAO

Mistral-Nemo-Instruct-2407

unsloth/Mistral-Nemo-Instruct-2407-TEE

Input

$0.0245

per 1M tokens

Output

$0.0978

per 1M tokens

Context

-

Est. cost

$0.0031

for your workload

Qwen2.5-Coder-32B-Instruct

Qwen/Qwen2.5-Coder-32B-Instruct-TEE

Input

$0.0245

per 1M tokens

Output

$0.0978

per 1M tokens

Context

-

Est. cost

$0.0031

for your workload

Qwen3-32B

Qwen/Qwen3-32B-TEE

Input

$0.08

per 1M tokens

Output

$0.24

per 1M tokens

Context

41K

Est. cost

$0.0093

for your workload

gemma-4-31B-turbo

google/gemma-4-31B-turbo-TEE

Input

$0.13

per 1M tokens

Output

$0.38

per 1M tokens

Context

131K

Est. cost

$0.015

for your workload

MiniMax M2.5

MiniMaxAI/MiniMax-M2.5-TEE

Input

$0.15

per 1M tokens

Output

$1.20

per 1M tokens

Context

197K

Est. cost

$0.0264

for your workload

DeepSeek-V3.2

deepseek-ai/DeepSeek-V3.2-TEE

Input

$0.28

per 1M tokens

Output

$0.42

per 1M tokens

Context

131K

Est. cost

$0.0274

for your workload

Kimi K2.5

moonshotai/Kimi-K2.5-TEE

Input

$0.44

per 1M tokens

Output

$2.00

per 1M tokens

Context

262K

Est. cost

$0.0592

for your workload

Qwen 3.5

Qwen/Qwen3.5-397B-A17B-TEE

Input

$0.39

per 1M tokens

Output

$2.34

per 1M tokens

Context

262K

Est. cost

$0.0593

for your workload

Qwen3.6-27B

Qwen/Qwen3.6-27B-TEE

Input

$0.50

per 1M tokens

Output

$2.00

per 1M tokens

Context

262K

Est. cost

$0.064

for your workload

Kimi K2.6

moonshotai/Kimi-K2.6-TEE

Input

$0.74

per 1M tokens

Output

$3.50

per 1M tokens

Context

262K

Est. cost

$0.1012

for your workload

GLM-5

zai-org/GLM-5-TEE

Input

$0.95

per 1M tokens

Output

$2.55

per 1M tokens

Context

203K

Est. cost

$0.1066

for your workload

GLM-5.1

zai-org/GLM-5.1-TEE

Input

$1.05

per 1M tokens

Output

$3.50

per 1M tokens

Context

203K

Est. cost

$0.126

for your workload

Looking for something else? Browse the full model catalog in the app.

Browse all models

Private Chutes

Deploy your own private chute

Run your own dedicated AI workload on verified self-serve confidential GPU capacity. Your code, your weights, your data, isolated end-to-end. Deployed in minutes from the chutes CLI. Use this when you need a private model, a custom fine-tune, or a dedicated instance for production traffic.

How it works

Build your image, define your chute

Use the CLI to build a container, declare your NodeSelector with the GPU class, VRAM, and count your workload needs, then expose your endpoints via cords.
Deploy with one command

chutes deploy registers your chute, pays the one-time fee, and brings it online as private by default.
Pay only while it runs

Billed by the second at the GPU's hourly rate. Idle instances shut down automatically, so no GPU-seconds are wasted.

terminal

# In your chute definition:
# choose the self-serve private GPU class
# tee=True, node_selector=NodeSelector(gpu_count=1, include=["pro_6000"])

chutes build my_chute:chute --wait
chutes deploy my_chute:chute --accept-fee

Pricing

Private Chutes are billed at the GPU's hourly rate for however long the instance runs, plus a one-time deployment fee equal to 3× the hourly rate at the time of deployment. No subscription required.

Self-serve TEE GPU

1 verified class available

rate

RTX Pro 6000

96 GB · Blackwell · efficient private deployments

$1.80 / hour

One-time deployment fee

$5.40 = 3× hourly rate

GPUs shown here must have live pricing and TEE measurement support. The deployment fee is paid once when you run chutes deploy; after that, you pay only the per-second hourly rate while the instance is up. Actual placement follows your NodeSelector and available capacity.

Read deploy docs Talk to sales

Optional monthly plans

Prefer a monthly bill?

Plus and Pro bundle a daily request quota with a discount on per-token rates, in one predictable monthly payment. Pick a plan if you'd rather budget a fixed amount each month than top up your balance as you go.

$10 / mo

Plus

Bundled daily quota
6% off PAYG rates beyond the quota

$20 / mo

Pro

Larger daily quota
10% off PAYG rates beyond the quota

Enterprise Volume discounts, custom rate limits, dedicated support.

Frequently Asked Questions

Have questions about our pricing? We've got answers.

Still have questions?