OpenAI compatible API · Attested · Public status

GMI Cloud

Explore GMI Cloud models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

GMI Cloudgmi

No provider claim

All providers

Provider	GMI Cloud
Provider website	https://www.gmicloud.ai/
Models	74 public models
Prepaid routes	5
BYOK routes	74
Zero data retention	not claimed
Confidential compute	not claimed
Provider E2EE	not claimed
Policy note	GMI runs isolated/VPC GPU inference, but that is network isolation, NOT an attested TEE — so no confidential-compute, zero-retention, or E2EE claim is marked. Retention/training terms are unverified (the published policy page is JavaScript-only and would not render). Policy source

Measured performance

41 samples

Continuously sampled across GMI Cloud's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	3666 ms
Effective throughput	22 tok/s n=4
Uptime	100.00%

Model	p50 TTFT	p50 TTFB	Effective throughput	Uptime	Config excluded	Availability samples
z-ai/glm-5.2	3666 ms	3666 ms	24 tok/s n=2	100.00%	1 `unsupported_route`	10
moonshotai/kimi-k3	5428 ms	5427 ms	19 tok/s n=2	100.00%	—	10
z-ai/glm-5.1	2154 ms	2154 ms	—	100.00%	—	6
z-ai/glm-5	2421 ms	2421 ms	—	100.00%	1 `unsupported_route`	8
deepseek/deepseek-v4-pro	4823 ms	4823 ms	—	100.00%	—	7

GMI Cloud performance history · Full provider & model leaderboard.

Provider models

Models served by GMI Cloud.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Endpoints	Prompt	Completion	Routes
`anthropic/claude-haiku-4.5` Anthropic: Claude Haiku 4.5 providers pricing	IQ 98#82	200,000	1	$1.055/1M	$5.275/1M	BYOK
`anthropic/claude-opus-4.5` Anthropic: Claude Opus 4.5 providers pricing	IQ 113#42	200,000	1	$5.275/1M	$26.375/1M	BYOK
`anthropic/claude-opus-4.6` Anthropic: Claude Opus 4.6 providers pricing	IQ 125#11	1,000,000	1	$5.275/1M	$26.375/1M	BYOK
`anthropic/claude-opus-4.7` Anthropic: Claude Opus 4.7 providers pricing	IQ 128#9	1,000,000	1	$5.275/1M	$26.375/1M	BYOK
`anthropic/claude-opus-4.8` Anthropic: Claude Opus 4.8 benchmarks providers pricing	IQ 130#6	1,000,000	1	$5.275/1M	$26.375/1M	BYOK
`anthropic/claude-opus-5` Claude Opus 5 providers pricing	IQ 134#3	1,000,000	1	$5.275/1M	$26.375/1M	BYOK
`anthropic/claude-sonnet-4` Claude Sonnet 4	—	409,600	1	$3.165/1M	$15.825/1M	BYOK
`anthropic/claude-sonnet-4.6` Anthropic: Claude Sonnet 4.6 providers pricing	IQ 118#30	1,000,000	1	$3.165/1M	$15.825/1M	BYOK
`bytedance/seed-2.0-mini` ByteDance/Seed-2.0-mini providers pricing	—	256,000	1	$0.1055/1M	$0.422/1M	BYOK
`deepseek/deepseek-r1-0528` DeepSeek: R1 0528 providers pricing	—	163,840	1	$0.60135/1M	$2.41595/1M	BYOK
`deepseek/deepseek-v3-0324` DeepSeek V3 0324 providers pricing	—	163,840	1	$0.30595/1M	$1.2027/1M	BYOK
`deepseek/deepseek-v3.2` DeepSeek: DeepSeek V3.2 benchmarks providers pricing	IQ 103#64	163,840	1	$0.226403/1M	$0.335701/1M	BYOK
`deepseek/deepseek-v4-flash` DeepSeek: DeepSeek V4 Flash 0423 benchmarks providers pricing	IQ 113#41	1,048,576	1	$0.07385/1M	$0.1477/1M	BYOK
`deepseek/deepseek-v4-flash-0731` DeepSeek: DeepSeek V4 Flash 0731 providers pricing	—	1,048,576	1	$0.07385/1M	$0.1477/1M	BYOK
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro benchmarks providers pricing	IQ 117#31	1,048,576	2	$0.367139/1M	$0.734279/1M	prepaid BYOK
`google/gemini-3.1-flash-lite-preview` Google: Gemini 3.1 Flash Lite Preview providers pricing	IQ 101#72	1,048,576	1	$0.26375/1M	$1.5825/1M	BYOK
`google/gemini-3.1-pro-preview` Google: Gemini 3.1 Pro Preview benchmarks providers pricing	IQ 127#10	1,048,576	1	$2.11/1M	$12.66/1M	BYOK
`google/gemini-3.5-flash` Google: Gemini 3.5 Flash providers pricing	IQ 124#13	1,048,576	1	$1.5825/1M	$9.495/1M	BYOK
`google/gemini-3.5-flash-lite` Google: Gemini 3.5 Flash Lite providers pricing	IQ 108#52	1,048,576	1	$0.3165/1M	$2.6375/1M	BYOK
`google/gemini-3.6-flash` Google: Gemini 3.6 Flash providers pricing	IQ 123#14	1,048,576	1	$1.5825/1M	$7.9125/1M	BYOK
`google/gemini-3.7-flash` Google: Gemini 3.7 Flash providers pricing	IQ 122#17	1,048,576	1	$0.79125/1M	$3.95625/1M	BYOK
`google/gemma-4-26b-a4b-it` Google: Gemma 4 26B A4B providers pricing	IQ 96#89	262,144	1	$0.13715/1M	$0.422/1M	BYOK
`google/gemma-4-31b-it` Google: Gemma 4 31B providers pricing	IQ 101#73	262,144	1	$0.1477/1M	$0.422/1M	BYOK
`kwaipilot/kat-coder-pro-v2` KAT-Coder-Pro-V2 providers pricing	—	262,144	1	$0.3165/1M	$1.266/1M	BYOK
`minimax/minimax-m2.5` MiniMax: MiniMax M2.5 providers pricing	IQ 105#63	204,800	1	$0.3165/1M	$1.266/1M	BYOK
`minimax/minimax-m2.7` MiniMax: MiniMax M2.7 providers pricing	IQ 109#50	204,800	1	$0.2532/1M	$1.0128/1M	BYOK
`minimax/minimax-m3` MiniMax: MiniMax M3 benchmarks providers pricing	IQ 114#39	1,048,576	1	$0.2532/1M	$1.0128/1M	BYOK
`moonshotai/kimi-k2-instruct-0905` moonshotai/Kimi-K2-Instruct-0905	—	262,144	1	$0.60135/1M	$2.41595/1M	BYOK
`moonshotai/kimi-k2-thinking` MoonshotAI: Kimi K2 Thinking providers pricing	IQ 94#96	262,144	1	$0.844/1M	$1.266/1M	BYOK
`moonshotai/kimi-k2.5` MoonshotAI: Kimi K2.5 providers pricing	IQ 111#46	262,144	1	$0.633/1M	$3.165/1M	BYOK
`moonshotai/kimi-k2.6` MoonshotAI: Kimi K2.6 benchmarks providers pricing	IQ 119#23	262,144	1	$0.902025/1M	$3.798/1M	BYOK
`moonshotai/kimi-k2.7-code` MoonshotAI: Kimi K2.7 Code benchmarks providers pricing	IQ 118#28	262,144	1	$1.00225/1M	$4.22/1M	BYOK
`moonshotai/kimi-k2.7-code-highspeed` moonshotai/Kimi: K2.7-Code-Highspeed providers pricing	—	262,144	1	$2.0045/1M	$8.44/1M	BYOK
`moonshotai/kimi-k3` MoonshotAI: Kimi K3 providers pricing	IQ 123#16	1,048,576	2	$3.165/1M	$15.825/1M	prepaid BYOK
`nvidia/nemotron-3-ultra-550b-a55b` NVIDIA: Nemotron 3 Ultra providers pricing	—	512,288	1	$0.844/1M	$2.743/1M	BYOK
`openai/gpt-4o` OpenAI: GPT-4o providers pricing	IQ #	128,000	1	$2.6375/1M	$10.55/1M	BYOK
`openai/gpt-4o-mini` OpenAI: GPT-4o-mini providers pricing	—	128,000	1	$0.15825/1M	$0.633/1M	BYOK
`openai/gpt-5` OpenAI: GPT-5 providers pricing	IQ 111#44	400,000	1	$1.31875/1M	$10.55/1M	BYOK
`openai/gpt-5.1` OpenAI: GPT-5.1 providers pricing	IQ 111#45	400,000	1	$1.31875/1M	$10.55/1M	BYOK
`openai/gpt-5.1-chat` GPT-5.1-chat	IQ 111#45	409,600	1	$1.31875/1M	$10.55/1M	BYOK
`openai/gpt-5.2` OpenAI: GPT-5.2 providers pricing	IQ 119#21	400,000	1	$1.84625/1M	$14.77/1M	BYOK
`openai/gpt-5.2-chat` GPT-5.2-chat	IQ 119#21	409,600	1	$1.84625/1M	$14.77/1M	BYOK
`openai/gpt-5.2-codex` GPT-5.2-codex	—	409,600	1	$1.84625/1M	$14.77/1M	BYOK
`openai/gpt-5.3-codex` OpenAI: GPT-5.3-Codex providers pricing	IQ 119#22	400,000	1	$1.84625/1M	$14.77/1M	BYOK
`openai/gpt-5.4` OpenAI: GPT-5.4 providers pricing	IQ 128#8	1,050,000	1	$2.6375/1M	$15.825/1M	BYOK
`openai/gpt-5.4-mini` OpenAI: GPT-5.4 Mini providers pricing	IQ 112#43	400,000	1	$0.79125/1M	$4.7475/1M	BYOK
`openai/gpt-5.4-nano` OpenAI: GPT-5.4 Nano providers pricing	IQ 106#57	400,000	1	$0.211/1M	$1.31875/1M	BYOK
`openai/gpt-5.4-pro` OpenAI: GPT-5.4 Pro providers pricing	—	1,050,000	1	$31.65/1M	$189.9/1M	BYOK
`openai/gpt-5.5` OpenAI: GPT-5.5 benchmarks providers pricing	IQ 133#4	1,050,000	1	$5.275/1M	$31.65/1M	BYOK
`openai/gpt-5.6-sol` OpenAI: GPT-5.6 Sol providers pricing	IQ 136#2	1,050,000	1	$5.275/1M	$31.65/1M	BYOK
`openai/gpt-5.6-terra` OpenAI: GPT-5.6 Terra providers pricing	IQ 132#5	1,050,000	1	$2.6375/1M	$15.825/1M	BYOK
`openai/gpt-oss-120b` OpenAI: gpt-oss-120b providers pricing	IQ 105#61	131,072	1	$0.05275/1M	$0.26375/1M	BYOK
`qwen/qwen3-235b-a22b-instruct-2507-fp8` Qwen/Qwen3-235B-A22B-Instruct-2507-FP8	—	262,144	1	$0.36925/1M	$1.477/1M	BYOK
`qwen/qwen3-235b-a22b-thinking-2507-fp8` Qwen/Qwen3-235B-A22B-Thinking-2507-FP8	—	262,141	1	$0.36925/1M	$4.431/1M	BYOK
`qwen/qwen3-coder-480b-a35b-instruct-fp8` Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8	—	262,128	1	$0.9495/1M	$4.7475/1M	BYOK
`qwen/qwen3-next-80b-a3b-instruct` Qwen: Qwen3 Next 80B A3B Instruct providers pricing	—	262,144	1	$0.15825/1M	$1.5825/1M	BYOK
`qwen/qwen3-next-80b-a3b-thinking` Qwen: Qwen3 Next 80B A3B Thinking providers pricing	—	262,144	1	$0.15825/1M	$1.5825/1M	BYOK
`qwen/qwen3.5-122b-a10b` Qwen: Qwen3.5-122B-A10B providers pricing	—	262,144	1	$0.422/1M	$3.376/1M	BYOK
`qwen/qwen3.5-35b-a3b` Qwen: Qwen3.5-35B-A3B providers pricing	—	262,144	1	$0.26375/1M	$2.11/1M	BYOK
`qwen/qwen3.5-397b-a17b` Qwen: Qwen3.5 397B A17B providers pricing	—	262,144	1	$0.633/1M	$3.798/1M	BYOK
`qwen/qwen3.6-35b-a3b` Qwen: Qwen3.6 35B A3B providers pricing	IQ 100#78	262,144	1	$0.26164/1M	$1.566675/1M	BYOK
`qwen/qwen3.6-max-preview` Qwen3.6 Max Preview	IQ 114#40	262,144	1	$1.3715/1M	$8.229/1M	BYOK
`qwen/qwen3.6-plus` Qwen3.6 Plus providers pricing	IQ 110#48	262,144	1	$0.5275/1M	$3.165/1M	BYOK
`qwen/qwen3.6-plus-2026-04-02` Qwen3.6 Plus 2026-04-02 providers pricing	—	262,144	1	$0.5275/1M	$3.165/1M	BYOK
`qwen/qwen3.7-max` Qwen3.7-Max providers pricing	IQ 118#29	1,000,000	1	$2.6375/1M	$7.9125/1M	BYOK
`qwen/qwen3.8-max` Qwen3.8 Max providers pricing	IQ 119#26	1,000,000	1	$2.11/1M	$6.33/1M	BYOK
`tencent/hy3` Tencent: Hy3 providers pricing	IQ 103#67	262,144	1	$0.13293/1M	$0.55071/1M	BYOK
`tencent/hy3-preview` Tencent: Hy3 preview benchmarks	IQ 103#67	262,144	1	$0.1899/1M	$0.633/1M	BYOK
`xiaomimimo/mimo-v2.5` XiaomiMiMo/MiMo-V2.5 providers pricing	IQ 109#49	262,144	1	$0.125545/1M	$0.25109/1M	BYOK
`xiaomimimo/mimo-v2.5-pro` XiaomiMiMo/MiMo-V2.5-Pro providers pricing	IQ 115#36	1,048,576	1	$0.321248/1M	$0.642495/1M	BYOK
`z-ai/glm-4.7-fp8` Proxy: zai-org/GLM-4.7	—	202,752	1	$0.633/1M	$2.321/1M	BYOK
`z-ai/glm-5` Z.ai: GLM 5 benchmarks providers pricing	IQ 105#60	204,800	2	$0.633/1M	$2.0256/1M	prepaid BYOK
`z-ai/glm-5.1` Z.ai: GLM 5.1 benchmarks providers pricing	IQ 114#38	204,800	2	$0.96005/1M	$3.0173/1M	prepaid BYOK
`z-ai/glm-5.2` Z.ai: GLM 5.2 benchmarks providers pricing	IQ 120#19	1,048,576	2	$0.78281/1M	$2.46026/1M	prepaid BYOK

Questions

Does GMI Cloud have zero data retention?

TrustedRouter does not currently mark GMI Cloud as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.

Is GMI Cloud end-to-end encrypted?

TrustedRouter does not currently mark GMI Cloud as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.

Which GMI Cloud models are available through TrustedRouter?

This page currently lists 74 public GMI Cloud models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.