BUILT INTO EVERY GOODSPEED APP
LLM Client (OpenAI + Anthropic, Cost-Gated)
A provider-agnostic LLM service exposes chat(), streamChat(), embed(), and transcribe() with OpenAI and Anthropic adapters; every call routes through a cost-budget RPC that can throttle, block, or alert when per-user or per-scope spend limits are exceeded.
- Tier: Common
- Status: Config-toggled
- Config: gasConfig.llm.provider
WHY IT MATTERS
Most mobile app projects spend weeks plumbing the same infrastructure before writing a single line of product code. LLM Client (OpenAI + Anthropic, Cost-Gated) is one of those cross-cutting concerns that every app eventually needs but almost none get right the first time. Permissions are handled incorrectly, tokens expire silently, or the feature breaks after an OS update nobody tested against.
Goodspeed solves this by shipping llm client (openai + anthropic, cost-gated) as a production-grade, tested implementation inside every generated app. The code follows the patterns in the GAS template - the same 246-feature catalog that powers every app we build. Controlled by `gasConfig.llm.provider` in gas.config.ts. You own the code from day one, can read every line, and can hire any React Native developer to extend it. The build pipeline verifies the feature compiles and routes resolve before the app lands in your repository, so you are not the one catching the integration error at 2 am before launch.
HOW IT IS WIRED
Real code from the GAS template
The excerpt below is lifted verbatim from gas.config.ts in the gas-template repository. This is the code your generated app gets, not pseudocode, not a description of intent.
// Enable this feature in gas.config.ts
export const gasConfig = {
features: {
// Set the relevant flag to true to enable
},
};Source: goodspeed-apps/gas-template → gas.config.ts
HONEST LIMITS
When LLM Client (OpenAI + Anthropic, Cost-Gated) is the wrong choice
Do not use this client for batch or background LLM jobs that run at high volume. The cost guardrails are designed for interactive per-user calls, and the per-call RPC overhead adds latency that is unsuitable for pipeline use.
Tier: Common · Config-toggled
Evaluate your use case
Check whether llm client (openai + anthropic, cost-gated) aligns with your target audience, platform constraints, and regulatory environment before enabling it.
Audit the config
The `gasConfig.llm.provider` flag controls this feature. Set it to false in gas.config.ts to disable the feature entirely with no residual code paths.
Seek alternatives
If the built-in implementation does not fit, the generated codebase is standard React Native + Expo code. Any library in the Expo ecosystem can replace the default.
APPS USING THIS FEATURE
Every generated Goodspeed app includes llm client (openai + anthropic, cost-gated). Browse the ideas catalog to see apps across all categories that ship with this feature wired in.
CAPABILITIES
LLM Client (OpenAI + Anthropic, Cost-Gated) capability breakdown
Concrete dimensions of what the built-in llm client (openai + anthropic, cost-gated) implementation covers. These reflect the actual template code, not a marketing summary.
| Item | Description | Strength |
|---|---|---|
| Storage backend | Data for this feature is managed by Supabase RPC (consume_cost) + provider API. | Supabase RPC (consume_cost) + provider API |
| Network mode | This feature operates in Online-only mode. | Online-only |
| Sync frequency | Data syncs On-demand. | On-demand |
| Tier | Common feature — config-toggled. | Common |
| Template status | Enabled via gasConfig.llm.provider. | Config-toggled |
GET IT BUILT INTO YOUR APP