Say gm tofrontier models.

Drop-in access to Claude, GPT, and Gemini.

Your prompts routed through a verifiable TEE.

get an API keyemail, Google, or Bittensor

sign up with email or Google — start instantly, no card required

Easy integrations

Point Cursor, Cline, Claude Code, or your AI SDK at the gm gateway. One base URL. No rewrites.

VS Code → Cline settings → OpenAI Compatible

API ProviderOpenAI CompatibleBase URLhttps://api.saygm.com/v1API Keygm_live_…Modelclaude-sonnet-4-6

Access you can build on.

See live pricing
//01

No surprise cutoffs

models stay reachable

//02

No silent price hikes

rates published, not slipped in

//03

No breaking changes

your integration keeps working

Frontier models

Your prompt reaches the provider — and no one else in between.

Externally hosted models run on hardware the provider controls, so the provider processes your prompt under its own API terms. What gm adds: the route is sealed inside a TEE, so the operators, the host, and gm never see your prompt on the way — only the provider does.

Yougm routerModel
Confidential models

Not even the maker sees your prompt.

Open models gm runs inside the TEE itself, so your prompt is decrypted only within the enclave — invisible to the maker, the host, and us. The strongest tier: nothing leaves the box in the clear.

Yougm routerModel
No subscriptionNo credit-purchase fee
Attestation

Verified by hardware, not by policy.

The gateway runs in an Intel TDX enclave. The chip itself signs a measurement of exactly what's running — so the proof comes from Intel's silicon, not from a promise on our website.

  • Sealedyour prompts are decrypted only inside the enclave — the host and gm never see them.

  • Measuredthe chip signs a hash of the exact gateway image. It matches the published measurement, or attestation fails.

  • Boundyour TLS session terminates inside the attested enclave (RA-TLS).

live attestationverified
gateway
gw-mainnet-2
platform
Intel TDX · Phala
compose
771c33dc…78819c
os image
761c05d2…056816
tcb
OutOfDate
quote
Intel-signed
Pricing

Popular models, live pricing.

The best available pricing across every provider serving each model, per million tokens in USD.

41%Cheaper than list, on average
LiveProvider bidding
48Models live
≤ RetailNever more than list
InOut
Claude Fable 5.1claude-fable-5-1Anthropic-8.4%$10.00$9.16$50.00$45.78
Claude Sonnet 5claude-sonnet-5Anthropic-64.0%$2.00$0.72$10.00$3.59
Claude Opus 4.8claude-opus-4-8Anthropic-64.0%$5.00$1.80$25.00$8.99
GLM-5.3-Flashglm-5.3-flashOpenZ.ai-7.3%$0.15$0.14$0.50$0.46
GLM-5.2glm-5.2OpenZ.ai-61.7%$1.40$0.54$4.40$1.68
Kimi K3kimi-k3OpenMoonshot AI-29.3%$3.00$2.12$15.00$10.61
GLM-5.3glm-5.3OpenZ.ai-18.5%$1.40$1.14$4.40$3.58
Claude Opus 5claude-opus-5Anthropic-64.0%$5.00$1.80$25.00$8.99
Qwen3.8-27Bqwen3.8-27bOpenQwen-58.9%$0.50$0.21$3.00$1.23
GPT-5.6 Lunagpt-5.6-lunaOpenAI-58.9%$0.20$0.08$1.20$0.49
GPT-5.6 Solgpt-5.6-solOpenAI-58.9%$4.00$1.64$20.00$8.22
Ornith 1.5 397Bornith-1.5-397bOpenOrnith-48.5%$1.40$0.72$4.40$2.27
GPT-5.5gpt-5.5OpenAI-58.9%$5.00$2.05$30.00$12.33
GPT-5.6 Terragpt-5.6-terraOpenAI-58.9%$2.00$0.82$12.00$4.93
GLM-5.2 (TEE)glm-5.2-teeOpenZ.ai-48.6%$1.40$0.72$4.40$2.26
Claude Fable 5claude-fable-5Anthropic-64.0%$10.00$3.59$50.00$17.97
GPT-5.4gpt-5.4OpenAI-58.9%$2.50$1.03$15.00$6.16
Claude Opus 4.7claude-opus-4-7Anthropic-64.0%$5.00$1.80$25.00$8.99
DeepSeek-V3.2 (TEE)deepseek-v3.2-teeOpenDeepSeek-49.6%$1.00$0.50$1.00$0.50
Claude Sonnet 4.6claude-sonnet-4-6Anthropic-64.0%$3.00$1.08$10.00$3.59
Kimi-K3 (TEE)kimi-k3-teeOpenMoonshot AI-9.4%$3.00$2.72$15.00$13.58
Claude Haiku 4.5claude-haiku-4-5Anthropic-64.0%$1.00$0.36$5.00$1.80
DeepSeek-V4-Flash-0731 (TEE)deepseek-v4-flash-0731-teeOpenDeepSeek-19.7%$0.17$0.14$0.35$0.28
Qwen3.6-35B-A3Bqwen3.6-35b-a3bOpenQwen-64.5%$0.248$0.088$1.485$0.527
Qwen3.5-397B-A17B (TEE)qwen3.5-397b-a17b-teeOpenQwen-49.5%$0.45$0.23$3.00$1.51
o3o3OpenAI-58.9%$2.00$0.82$8.00$3.29
Qwen3.8-27B (TEE)qwen3.8-27b-teeOpenQwen$0.44$3.30
GLM-5.1 (TEE)glm-5.1-teeOpenZ.ai-48.7%$1.40$0.72$4.40$2.26
Qwen3.8-Flash-Nextqwen3.8-flash-nextOpenQwen-7.3%$0.16$0.15$0.47$0.44
Qwen3-235B-A22B-Thinking-2507 (TEE)qwen3-235b-a22b-thinking-2507-teeOpenQwen-49.5%$0.2989$0.1509$1.1957$0.6035
o4-minio4-miniOpenAI-48.6%$1.10$0.57$4.40$2.26
Qwen3.6-27B (TEE)qwen3.6-27b-teeOpenQwen-48.8%$0.30$0.15$2.00$1.02
GPT-5.4 nanogpt-5.4-nanoOpenAI-58.9%$0.20$0.08$1.25$0.51
Kimi-K2.6 (TEE)kimi-k2.6-teeOpenMoonshot AI-49.5%$0.66$0.33$3.50$1.77
GPT-5.4 minigpt-5.4-miniOpenAI-58.9%$0.75$0.31$4.50$1.85
Gemma 4 31B turbo (TEE)gemma-4-31b-turbo-teeOpenGoogle-49.0%$0.12$0.06$0.37$0.19
DeepSeek-V4-Flash-0731deepseek-v4-flash-0731OpenDeepSeek-62.3%$0.44$0.17$1.32$0.50
Qwen3-32B (TEE)qwen3-32b-teeOpenQwen-49.0%$0.104$0.053$0.416$0.212
Nemotron 3 Nano Omni 30B (TEE)nemotron-3-nano-omni-30b-teeOpenNVIDIA-53.8%$0.0245$0.0113$0.0978$0.0452
Mistral Nemo (TEE)mistral-nemo-instruct-2407-teeOpenMistral-49.0%$0.0245$0.0125$0.0978$0.0499
Gemini 3.1 Pro Previewgemini-3.1-pro-previewGoogle-7.8%$2.00$1.84$12.00$11.06
Gemini 3.6 Flashgemini-3.6-flashGoogle-7.3%$0.75$0.70$3.75$3.48
Gemini 3.7 Flashgemini-3.7-flashGoogle-8.3%$0.75$0.69$3.75$3.44
Gemini 3.8 Flashgemini-3.8-flashGoogle-8.3%$0.75$0.69$3.75$3.44
GPT-5.5 Progpt-5.5-proOpenAI-48.6%$30.00$15.42$180.00$92.50
Gemini 3.5 Flash Litegemini-3.5-flash-liteGoogle-7.3%$0.30$0.28$2.50$2.32
Gemini 3.1 Flash Litegemini-3.1-flash-liteGoogle-7.3%$0.25$0.23$1.50$1.39
Gemini 3.5 Flashgemini-3.5-flashGoogle-7.3%$1.50$1.39$9.00$8.34

Ready to switch?

sign up with email or Google — start instantly, no card required