The inference networkBittensor gateways
for model inference.
taoCode connects local coding tools to Bittensor gateways. Compare gateways and models to choose where your requests run.
2Gateway integrations
14Listed models
14Report TEE support
Gateways One agent, many gateways↗
Chutes SN64
OpenAI-compatible inference with a public model catalog and per-model confidential-compute metadata.
Explore gateway → Targon SN4
Confidential compute infrastructure on Bittensor, built for private AI workloads.
Explore gateway → Models across the network↗
Compare context windows, tool support, and pricing. Prices are USD per million tokens. Learn about TEE support →
14 models
Chutes / SN64TEE reported
DeepSeek-V3.2↗
tao/chutes/deepseek-ai/DeepSeek-V3.2-TEE - Context
- 128K
- Tool calling
- Supported
- Input / 1M
- $1
- Output / 1M
- $1
Text input
Chutes / SN64TEE reported
DeepSeek-V4-Flash-0731↗
tao/chutes/deepseek-ai/DeepSeek-V4-Flash-0731-TEE - Context
- 1024K
- Tool calling
- Supported
- Input / 1M
- $0.44
- Output / 1M
- $1.32
Text input
Chutes / SN64TEE reported
gemma-4-31B-turbo↗
tao/chutes/google/gemma-4-31B-turbo-TEE - Context
- 128K
- Tool calling
- Supported
- Input / 1M
- $0.12
- Output / 1M
- $0.37
Text + image input
Chutes / SN64TEE reported
Kimi-K2.6↗
tao/chutes/moonshotai/Kimi-K2.6-TEE - Context
- 256K
- Tool calling
- Supported
- Input / 1M
- $0.58
- Output / 1M
- $3.4
Text + image input
Chutes / SN64TEE reported
Kimi-K3↗
tao/chutes/moonshotai/Kimi-K3-TEE - Context
- 1024K
- Tool calling
- Supported
- Input / 1M
- $3
- Output / 1M
- $15
Text + image input
Chutes / SN64TEE reported
Nemotron-3-Nano-Omni-30B↗
tao/chutes/Nemotron-3-Nano-Omni-30B-TEE - Context
- 128K
- Tool calling
- Not reported
- Input / 1M
- $0.0245
- Output / 1M
- $0.0978
Modalities not reported
Chutes / SN64TEE reported
Qwen3-235B-A22B-Thinking-2507↗
tao/chutes/Qwen/Qwen3-235B-A22B-Thinking-2507-TEE - Context
- 256K
- Tool calling
- Supported
- Input / 1M
- $0.2989
- Output / 1M
- $1.1957
Text input
Chutes / SN64TEE reported
Qwen3-32B↗
tao/chutes/Qwen/Qwen3-32B-TEE - Context
- 40K
- Tool calling
- Supported
- Input / 1M
- $0.104
- Output / 1M
- $0.416
Text input
Chutes / SN64TEE reported
Qwen3.5-397B-A17B↗
tao/chutes/Qwen/Qwen3.5-397B-A17B-TEE - Context
- 256K
- Tool calling
- Supported
- Input / 1M
- $0.45
- Output / 1M
- $3
Text + image input
Chutes / SN64TEE reported
Qwen3.6-27B↗
tao/chutes/Qwen/Qwen3.6-27B-TEE - Context
- 256K
- Tool calling
- Supported
- Input / 1M
- $0.3
- Output / 1M
- $2
Text + image input
Chutes / SN64TEE reported
Qwen3.8-27B↗
tao/chutes/Qwen/Qwen3.8-27B-TEE - Context
- 256K
- Tool calling
- Supported
- Input / 1M
- $0.32
- Output / 1M
- $2.5
Text + image input
Chutes / SN64TEE reported
Mistral-Nemo-Instruct-2407↗
tao/chutes/unsloth/Mistral-Nemo-Instruct-2407-TEE - Context
- 128K
- Tool calling
- Not reported
- Input / 1M
- $0.0245
- Output / 1M
- $0.0978
Modalities not reported
Chutes / SN64TEE reported
GLM-5.1↗
tao/chutes/zai-org/GLM-5.1-TEE - Context
- 198K
- Tool calling
- Supported
- Input / 1M
- $0.98
- Output / 1M
- $3.08
Text input
Chutes / SN64TEE reported
GLM-5.2↗
tao/chutes/zai-org/GLM-5.2-TEE - Context
- 1024K
- Tool calling
- Supported
- Input / 1M
- $1.25
- Output / 1M
- $3.95
Text input
No matching models. Try another name or gateway.