`thinwrap/llm`

thinwrap/llm for PHP — one typed Chat facade over 18 LLM providers (15 OpenAI-compatible + native Anthropic, Bedrock, Gemini), plus embeddings on 11. Stateless, SDK-free, BYO PSR-18 client — the in-process complement to an LLM gateway.

Packagist · thinwrap/llm@1.0.0 GitHub · thinwrap/llm-php

PHP constraints

Runtime dependencies: php-http/discovery, psr/http-client, psr/http-factory
BYO HTTP client: consumer-supplied PSR-18 client via php-http/discovery
Provenance: cosign-signed GitHub Release artifacts
Minimum runtime: PHP 8.2+

PSR-17/PSR-18 discovery is auto-detected; consumers can also pass clients explicitly

30-second install

composer require thinwrap/llm

2-minute end-to-end example

One Chat facade, every provider. Switching vendor is theLlmProviderId case, the config class, and the model — thecomplete($input) call and the ChatResult stay identical.

use Thinwrap\Llm\Chat;
use Thinwrap\Llm\DTO\Chat\ChatInput;
use Thinwrap\Llm\DTO\Chat\ChatMessage;
use Thinwrap\Llm\Enum\ChatRole;
use Thinwrap\Llm\Enum\LlmProviderId;
use Thinwrap\Llm\Exception\ConnectorError;
use Thinwrap\Llm\Providers\Shared\OpenAiCompatConfig;

$chat = new Chat(LlmProviderId::OpenAI, new OpenAiCompatConfig(apiKey: getenv('OPENAI_API_KEY')));

try {
    $res = $chat->complete(new ChatInput(
        model: 'gpt-4o-mini',
        messages: [new ChatMessage(ChatRole::User, 'Say hi in one word.')],
    ));
    echo $res->message->content;
    echo $res->usage->inputTokens . '/' . $res->usage->outputTokens;
} catch (ConnectorError $e) {
    error_log($e->providerCode->value . ': ' . ($e->providerMessage ?? ''));
}

The 15 first-class OpenAI-compatible providers all takeOpenAiCompatConfig; anthropic,bedrock, and gemini are native adapters with their own config classes. Same ->complete($input) shape throughout.

use Thinwrap\Llm\Providers\Anthropic\AnthropicConfig;

$anthropic = new Chat(LlmProviderId::Anthropic, new AnthropicConfig(apiKey: getenv('ANTHROPIC_API_KEY')));
// same ->complete($input) shape, same ChatResult

Supported providers

18 providers ship with thinwrap/llm@1.0.0.
Provider	Operations	Auth	README
`openai` OpenAI	chat, embeddings	bearer	docs
`azure-openai` Azure OpenAI	chat, embeddings	header	docs
`anthropic` Anthropic	chat	header	docs
`gemini` Google Gemini	chat	header	docs
`bedrock` AWS Bedrock	chat	aws-sig-v4	docs
`mistral` Mistral	chat, embeddings	bearer	docs
`cloudflare` Cloudflare Workers AI	chat, embeddings	bearer	docs
`together` Together AI	chat, embeddings	bearer	docs
`fireworks` Fireworks AI	chat, embeddings	bearer	docs
`deepinfra` DeepInfra	chat, embeddings	bearer	docs
`openrouter` OpenRouter	chat, embeddings	bearer	docs
`groq` Groq	chat	bearer	docs
`deepseek` DeepSeek	chat	bearer	docs
`xai` xAI (Grok)	chat	bearer	docs
`perplexity` Perplexity	chat	bearer	docs
`vllm` vLLM	chat, embeddings	bearer	docs
`ollama` Ollama	chat, embeddings	bearer	docs
`lmstudio` LM Studio	chat, embeddings	bearer	docs

Migration paths

The in-process complement to a gateway

Thinwrap LLM is a thin, in-process, SDK-free facade — it does not proxy your traffic. It normalizes the request/response shape across vendors so your code stays vendor-neutral; routing, budgets, and observability stay wherever you already run them. Provider-specific request fields ride through _passthrough; the decoded vendor body is always on the result's raw.

Embeddings

The OpenAI-float subset (11 of the 18 providers — see the table above) also exposes an Embeddings facade with the same provider-switching model.

Bring your own PSR-18 client

A PSR-18 client + PSR-17 factories are auto-discovered viaphp-http/discovery, or pass one explicitly. The wrapper holds no state — retry, timeout, and the client lifecycle stay with the consumer.

Cross-language siblings

The TypeScript (/packages/llm-ts) and Go (/packages/llm-go) variants ship the same facade shape and provider set — cross-language parity is a design goal, not a hard release gate.

Repo README