LLM APIs through Squiid
Hosted large language model APIs for chat, reasoning, tool calling and structured output. Every provider here speaks an HTTP API that your app calls at request time, billed per token.
Who needs this
Any vibe-coded app that generates text, answers questions, routes tool calls or classifies user input.
Squiid lists 12 llm apis services: 3 live today, 3 next up and the rest on the roadmap. Each one is reachable at https://api.squiid.io/v1/<service-slug>/ with the header Authorization: Bearer $SQUIID_API_KEY, and official SDKs work by pointing their base URL at the gateway (gateway convention).
LLM APIs services
Anthropic
LLM APIsClaude models for long-context reasoning, coding and tool use
LiveInstant CECerebras
LLM APIsWafer-scale inference for open models at extreme token speeds
RoadmapInstant COCohere
LLM APIsEnterprise models with strong embeddings, rerank and RAG tooling
RoadmapInstant DSDeepSeek
LLM APIsLow-cost chat and reasoning models with an OpenAI-compatible API
RoadmapInstant FAFireworks AI
LLM APIsFast serving of open models with structured output and fine-tuning
RoadmapInstant
Google Gemini
LLM APIsGemini models with very long context, video and audio input
LiveInstant GRGroq
LLM APIsVery fast inference for open models on custom LPU hardware
Next upInstant
Mistral
LLM APIsEuropean open-weight and frontier models, plus OCR and embeddings
Next upInstant
OpenAI
LLM APIsGPT models, embeddings, images and realtime voice over one API
LiveInstant
Perplexity
LLM APIsSonar models that answer from live web results with citations
RoadmapInstant TATogether AI
LLM APIsHundreds of open-source models, plus fine-tuning and GPU clusters
RoadmapInstant
xAI
LLM APIsGrok models with an OpenAI-compatible API and live search
Next upInstantWhy connect them through Squiid
One key, not six
Your .env holds SQUIID_API_KEY and nothing else. Squiid holds the provider keys, so nothing sensitive reaches your repository, a preview deployment or an agent’s context window.
One bill, no markup
Usage is metered at the provider’s list price against prepaid credits, and subscriptions pass through at the provider’s price. Squiid adds no markup to provider prices. There is a free plan at $0 a month with a 15% fee when you top up credits, Solo at $19.97 a month with a top-up fee that starts at 8% and falls to 3.5% as your spend grows, Team from $29.97 a seat a month with the same ladder one point lower, and Custom with a rate of 3% or less.
Spend that stops
Every call is metered per service in one dashboard, and when credits run out the gateway stops authorizing usage instead of producing a bill you did not fund.
Questions people ask
Which llm apis services can I use through Squiid?
12 of them: Anthropic, Cerebras, Cohere, DeepSeek, Fireworks AI, Google Gemini, Groq, Mistral, OpenAI, Perplexity, Together AI, xAI. 3 are live today, 3 are next up, and the rest are on the roadmap. All of them run on the same SQUIID_API_KEY.
Does Squiid mark up llm apis pricing?
No. Provider usage is billed at the provider’s list price against your prepaid credits, and subscriptions pass through on the monthly Squiid invoice with no fee. Squiid earns from your plan and the percentage taken when you top up credits.
Can Claude Code and Cursor use these through one key?
Yes. Requests go to https://api.squiid.io/v1/<service>/ with an Authorization: Bearer $SQUIID_API_KEY header, and official SDKs work by pointing their base URL at the gateway. Every agent, from Claude Code and Cursor to Codex, Windsurf and Cline, uses the same single variable.
Connect llm apis in minutes.
One account, one API key and one invoice for every service in this category and the 100+ in the full catalog.