One allowlist · Every Tempr product

Bring a key from any of these.

One server-enforced allowlist of model providers, and 3M+ models between them — first-party APIs, inference hosts, clouds, and aggregators. The list is shared by Chat, the CLI, and the Gateway, with one exception: aggregator keys like OpenRouter work in Chat and the CLI, not the Gateway. Add your own API key for any of them and Tempr talks to that provider directly on your key.

33model providers on one allowlist
3M+models across all of them, combined

Browse all models See pricing How key storage works

First-party — the model creator's own API · Inference — hosts other companies' open-weight models on its own infrastructure · Cloud — a cloud platform hosting first-party models under its own managed service · Aggregators — one key, routed to many providers through a single API. Available in Chat and the CLI only, not the Gateway.

OpenAIOpenAIFirst-party
AnthropicAnthropicFirst-party
Google GeminiGoogle GeminiFirst-party
DeepSeekDeepSeekFirst-party
xAIxAIFirst-party
MistralMistralFirst-party
Meta AIMeta AIFirst-party
CohereCohereFirst-party
OpenRouterOpenRouterAggregatorChat & CLI
Together AITogether AIInference
Fireworks AIFireworks AIInference
Hugging FaceHugging FaceInference
DeepInfraDeepInfraInference
NscaleNscaleInference
GroqGroqInference
Novita AINovita AIInference
CerebrasCerebrasInference
AI21 LabsAI21 LabsFirst-party
Aleph AlphaAleph AlphaFirst-party
Alibaba CloudAlibaba CloudFirst-party
CodestralCodestralFirst-party
Inception LabsInception LabsFirst-party
MiniMaxMiniMaxFirst-party
Moonshot AIMoonshot AIFirst-party
MorphMorphFirst-party
PerplexityPerplexityFirst-party
Public AIPublic AIFirst-party
Sarvam AISarvam AIFirst-party
Xiaomi MiMoXiaomi MiMoFirst-party
Z.aiZ.aiFirst-party
AWS BedrockAWS BedrockCloud
Azure OpenAIAzure OpenAICloud
Azure AI FoundryAzure AI FoundryCloud

More providers are added to the allowlist regularly. Yours isn’t listed yet? Request a provider.

Don’t see your host? Bring your own OpenAI-compatible endpoint as a custom model — included with Chat Pro and Teams and on every Gateway plan. Read the custom models guide.

One key, three ways to use it

Whatever you bring, it works everywhere — chat in your IDE, the same agent in your terminal, and an OpenAI-compatible API for your own apps.

Explore Chat Explore CLI Explore Gateway