FAQ
Getting started
Why should I use Siraya AI?
Siraya AI provides a unified API to access all the major LLM models on the market. It also allows users to aggregate their billing in one place and keep track of all of their usage using our analytics. Siraya AI passes through the pricing of the underlying providers, while pooling their uptime, so you get the same pricing you’d get from the provider directly, with a unified API and fallbacks so that you get much better uptime.What makes Siraya AI unique?
Siraya AI AI stands out as a unified routing layer that connects multiple AI model providers through a single, consistent API. Instead of integrating separately with different LLM or embedding services, developers can use Siraya AI to simplify model management, request routing, and version control. Siraya AI offers flexible configuration options—such as automatic provider selection, fallback routing, and performance optimization—which help ensure reliability and cost-efficiency. In short, Siraya AI AI makes it easier to build and scale AI applications by abstracting away provider complexity while maintaining full transparency and control.What's the story behind Siraya AI?
Siraya AI was created to solve a growing pain in the AI development world: managing multiple model providers efficiently. As the ecosystem of large language models and embeddings expanded, developers often found themselves juggling different APIs, authentication methods, and data formats for each provider. This added unnecessary friction and slowed down innovation. Seeing this challenge, the creators of Siraya AI envisioned a single, unified routing layer that could abstract away these complexities—allowing developers to focus on what matters most: building great products powered by AI. The idea was to give teams the flexibility to mix and match providers, experiment seamlessly, and improve reliability through smart routing and fallbacks. From that vision, Siraya AI emerged as an infrastructure solution designed to make multi‑provider AI development as simple, scalable, and transparent as possible. It reflects the broader effort to move from fragmented model integrations toward a cohesive, provider‑agnostic AI ecosystem.Why should a person choose Siraya AI over its competitors?
Siraya AI offers a flexible and developer‑friendly way to manage multiple AI model providers through one unified API. Unlike tools that tie you to a single vendor, Siraya AI AI lets you easily switch or combine models from different sources without changing your application code. Siraya AI provides built‑in routing logic, fallback mechanisms, and usage tracking so you can optimize cost, latency, and reliability automatically. In addition, its configuration‑based approach and detailed observability tools simplify scaling and debugging. In short, Siraya AI AI helps teams focus on building AI‑powered features rather than maintaining complex provider integrations.Who are the primary audience of Siraya AI?
The primary audience of Siraya AI includes developers, product teams, and organizations building applications that rely on AI models or large language models (LLMs). Siraya AI is designed for engineers who need to integrate, manage, and optimize access to multiple AI providers without maintaining separate APIs. Startups, enterprise AI teams, and platform builders can all benefit from its unified routing system—especially those seeking flexibility, scalability, and cost control in multi‑provider environments. In essence, Siraya AI AI serves anyone who wants to simplify AI infrastructure while maintaining high performance and reliability.How do I get started with Siraya AI AI?
To get started, create an account and add credits on the [Credits page](https://siraya.ai/dashboard/credits). Credits are simply deposits on Siraya AI that you use for LLM inference. When you use the API or chat interface, we deduct the request cost from your credits. Each model and provider has a different price per million tokens. Once you have credits you can create API keys and start using the API. You can read our [quickstart](quickstart) guide for code samples and more.How do I get support?
[support](../support)How do I get billed for my usage on Siraya AI?
For each model we have the pricing displayed per million tokens. There is usually a different price for prompt and completion tokens. There are also models that charge per request, for images and for reasoning tokens. All of these details will be visible on the [Logs page](https://siraya.ai/dashboard/logs). When you make a request to Siraya AI, we receive the total number of tokens processed by the provider. We then calculate the corresponding cost and deduct it from your credits. You can review your complete usage history in the [Activities page](https://siraya.ai/dashboard/activity). You can also add the `usage: {include: true}` parameter to your chat request to [get the billing information in the response](../observability/billing-transparency). We offer different discounts up to 35% based on the pricing of underlying providers.Pricing
What are the prices for using Siraya AI?
Siraya AI charges a [$0.35 + 5% fee](pricing-and-fee-structure) when you purchase credits. We pass through the pricing of the underlying model providers without any markup, so you pay the same rate as you would directly with the provider. For more details on our model price, please see our [Models page](https://siraya.ai/models). For more details about every request cost, please see our [Logs page](https://siraya.ai/dashboard/logs).How is the billing calculated when Prompt Cache is enabled?
Regardless of whether the cached result is used or a new prompt is processed, billing will follow the Prompt Cache rate as defined in our pricing documentation. This applies to every request, since Prompt Cache is always active in Siraya AI.
Models and Providers
What LLM models does Siraya AI support?
Siraya AI AI provides access to a wide variety of LLM models, including frontier models from major AI labs. For a complete list of models you can visit the [Models page](https://siraya.ai/models) or fetch the list through the [models api](../api-reference/models-api/list-all-models).How frequently are new models added?
We work on adding models as quickly as we can. We often have partnerships with the labs releasing models and can release models as soon as they are available.I am an inference provider, how can I get listed on Siraya AI?
If you would like to contact us, the best place to reach us is over email. [support](../support)How does model fallback work if a provider is unavailable?
If a provider returns an error Siraya AI AI will automatically fall back to the next provider. This happens transparently to the user and allows production apps to be much more resilient.API Technical Specifications
What authentication methods are supported?
Siraya AI AI uses three authentication methods: 1. API keys (passed as Bearer tokens) for accessing the completions API and other core endpointsWhat API endpoints are available?
Siraya AI implements the OpenAI API specification for /completions and /chat/completions endpoints, allowing you to use any model with the same request/response format.Which are the primary technologies used for building Siraya AI AI?
Siraya AI AI is typically built using modern, cloud‑native web technologies optimized for performance, scalability, and integration with AI services. At its core, Siraya AI AI relies on: 1. **TypeScript and Node.js** – for the main API logic, routing, and configuration management. These enable a robust developer experience and compatibility with diverse model providers. 2. **Cloud infrastructure (e.g., AWS, GCP, or similar)** – to support distributed routing, load balancing, and secure service deployment across regions. 3. **Database and caching systems** – often using PostgreSQL or similar for persistent data, and Redis or in‑memory stores for high‑speed routing decisions. 4. **API and network layer technologies** – including REST and WebSocket interfaces, authentication systems, and observability tooling to track provider usage and latency. 5. **Integration SDKs and AI provider APIs** – connectors built for leading LLM and AI platforms (such as OpenAI, Anthropic, Google, etc.) to enable seamless model switching. Together, these technologies provide a flexible foundation that allows Siraya AI AI to route, monitor, and optimize traffic across multiple AI services effectively.What are the supported formats?
The API supports text and images. [Images](../features/multimodal-input/images-inputs) can be passed as URLs or base64 encoded images. PDF and other file types are coming soon.How does streaming work?
Streaming uses server-sent events (SSE) for real-time token delivery. Set `stream: true` in your request to enable streaming responses.What SDK support is available?
Siraya AI AI is a drop-in replacement for OpenAI. Therefore, any SDKs that support OpenAI by default also support Siraya AI AI. Check out our [docs](../frameworks-and-integrations/overview) for more details.Can I mix different modalities in one request?
Yes! You can send text, images, PDFs, and audio in the same request. The model will process all inputs together.Does Siraya AI use Prompt Cache by default?
Yes. Prompt Cache is enabled by default in Siraya AI AI for all API calls. This means that whenever you send a request, Siraya AI AI will attempt to use the cached prompt/response if applicable.Will using Prompt Cache change my token usage or latency?
* **Token usage:** When a cached response is served, actual model inference may be skipped, which can reduce token consumption. * **Latency:** Cached responses are generally faster to return compared to generating new responses from the model. * **Billing:** The cost per request is based on the Prompt Cache price tier, regardless of cache hit or missCan I disable Prompt Cache?
At this time, Prompt Cache is permanently enabled in Siraya AI AI and cannot be turned off. The design ensures consistent performance optimization and uniform billing.Privacy and Data Logging
Please see our Terms of Service and Privacy Policy.