> ## Documentation Index > Fetch the complete documentation index at: https://hyperbolic.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Inference overview > Call open-source language models through Hyperbolic's OpenAI-compatible chat completions API, billed per token from your credit balance. Hyperbolic Inference gives you API access to open-source language models without renting or managing GPUs. You send OpenAI-compatible chat completion requests, and you pay per token from your credit balance. > [card] [Quick start](https://hyperbolic.ai/docs/inference/quickstart.md) > > Create a key and make your first request. > [card] [Chat completions](https://hyperbolic.ai/docs/inference/text-apis.md) > > Parameters, streaming, and SDK examples. ## What's available | | | | - | - | | **Base URL** | `https://api.hyperbolic.ai/inference/v1` | | **Endpoints** | `POST /chat/completions`, `GET /models` | | **Request format** | OpenAI chat completions, with streaming | | **Models** | Text models. See [Available models](#available-models) | | **Authentication** | An `sk_live_` API key, sent as a Bearer token | | **Billing** | Per million tokens, deducted from your credit balance | | **Rate limit** | 300 requests per minute per API key | | **Time limit** | 600 seconds for `glm-5.3-flash` and `qwen3.8-27b`, 300 seconds for other models. See [Time limits](https://hyperbolic.ai/docs/inference/text-apis.md#time-limits) | > [!NOTE] > > Inference serves text models only. Image generation, text-to-speech, vision, and base completion models from the previous inference API aren't available. ## Who can use inference To send inference requests, you need: * **A Pro plan, or an Organization.** Personal accounts on the Free Tier can't use inference. To upgrade, make a one-time deposit of \$5 or more. There's no subscription. Click **Upgrade to Pro for \$5** under **Settings > Plan**, or upgrade from the Model Playground. API access is restored within 30 seconds of upgrading. Requests made with an Organization API key, or from the dashboard while you're working in an Organization, don't require a Pro plan. See [Plan](https://hyperbolic.ai/docs/general/account-management.md#plan). * **An `sk_live_` API key.** Create one under **Settings > API Keys**. Keys issued in the older format aren't accepted. See [API keys](https://hyperbolic.ai/docs/general/account-management.md#api-keys). * **Credits.** Your balance must be above zero. See [Billing](https://hyperbolic.ai/docs/general/account-management.md#billing). ## Available models Pass one of these IDs in the `model` field. Prices are in USD per million tokens, as of October 21, 2026. To get the list through the API, see [List models](https://hyperbolic.ai/docs/inference/text-apis.md#list-models). | Model ID | Input | Cached input | Output | | - | - | - | - | | `glm-5.3-flash` | \$0.15 | \$0.03 | \$0.50 | | `glm-5.3` | \$1.40 | \$0.26 | \$4.40 | | `kimi-k3` | \$3.00 | \$0.30 | \$15.00 | | `minimax-m3` | \$0.30 | \$0.06 | \$1.20 | | `deepseek-v4.1-flash` | \$0.30 | \$0.006 | \$1.20 | | `deepseek-v4-flash-0731` | \$0.06 | \$0.015 | \$0.18 | | `nemotron-3-ultra-550b-a55b` | \$0.50 | \$0.10 | \$2.20 | | `step-5-preview` | \$1.00 | \$0.10 | \$2.70 | | `mimo-v2.6-flash` | \$0.14 | \$0.0028 | \$0.28 | | `hy4-preview` | \$0.834 | \$0.042 | \$2.501 | | `qwen3.8-27b` | \$0.20 | \$0.02 | \$2.00 | ### Context and output limits Limits are in tokens, confirmed October 20–22, 2026. The context window covers your prompt and the generated output together. | Model ID | Context window | Max output | | - | - | - | | `glm-5.3-flash` | 1,048,576 | 131,072 | | `glm-5.3` | 1,048,576 | 943,718 | | `kimi-k3` | 1,048,576 | 943,718 | | `minimax-m3` | 524,288 | 512,000 | | `deepseek-v4.1-flash` | 1,048,576 | 943,718 | | `deepseek-v4-flash-0731` | 1,048,576 | 131,072 | | `nemotron-3-ultra-550b-a55b` | 202,800 | 182,520 | | `step-5-preview` | 1,000,000 | 64,000 | | `mimo-v2.6-flash` | 1,048,576 | 131,072 | | `hy4-preview` | 1,048,576 | 64,000 | | `qwen3.8-27b` | 196,608 | No separate limit | For `glm-5.3-flash` and `qwen3.8-27b`, a request whose prompt plus `max_tokens` doesn't fit in the context window returns `400`. The prompt isn't truncated. `qwen3.8-27b` has no separate output limit, so its output can use whatever the prompt leaves of the 196,608-token window. Models and prices change over time. The [Models](https://app.hyperbolic.ai/models) page always shows the current list and prices. If you have custom pricing, the Models page shows your price. ## Models and pricing The [Models](https://app.hyperbolic.ai/models) page in the dashboard lists every model you can call. Each model's page shows: * The **model ID** to pass in the `model` field of your request. * The **price** per million tokens. * A **Model Playground** to try prompts in your browser. * An **API** panel with ready-to-copy request code. > [!NOTE] > > The Models page is rolling out gradually. If you don't see **Models** in the sidebar yet, your account doesn't have access to the page, but you can still call the API. ### How tokens are billed Prices are per million tokens and may differ for each part of a request: * **Input tokens**: the tokens in your prompt, including the system prompt and conversation history. * **Cached input tokens**: input tokens served from the model's prompt cache. These are a subset of your input tokens, not an extra charge. When a model has a cached input price, they're billed at that lower rate. Otherwise they're billed at the input rate. * **Output tokens**: the tokens the model generates. You aren't charged for requests that return an error. The rate that applies is the one in force when Hyperbolic receives your request. ### Personal and Organization billing * **Personal API keys** bill your personal balance. * **Organization API keys** bill the Organization's shared balance. When the Organization's balance runs out, requests are denied until an admin adds funds. Organizations are billed standard platform prices. See [Organizations](https://hyperbolic.ai/docs/general/organizations.md#billing). ## Model Playground Each model's page includes a playground for testing prompts before you write code. You can set a system prompt, temperature, top-p, and max tokens, and the responses stream into the chat. Playground requests use the same API and are billed the same way as API requests, to the personal account or Organization you're working in. * **Reasoning models** show their thinking in a collapsed **Thinking** section above the answer. If a model uses up **Max Tokens** on thinking before it starts its answer, the playground tells you to raise **Max Tokens**. * **Free Tier accounts** see a notice that the model needs a Pro account. When you send a message, an **Upgrade to Pro** dialog opens with a \$5 payment form. After the upgrade goes through, the playground sends your message. * **Organizations with no funds** see an **Add funds** prompt when you send a message. * **Errors** show the message from the API followed by its code, for example `(insufficient_balance)`. See [Errors](https://hyperbolic.ai/docs/inference/errors.md). ## Moving from the previous inference API If you used Hyperbolic's previous serverless inference API, update your integration: | | Previous API | Current API | | - | - | - | | Base URL | `https://api.hyperbolic.xyz/v1` | `https://api.hyperbolic.ai/inference/v1` | | API keys | Older key format | `sk_live_` keys only | | Plan | Free Tier included | Pro plan or Organization | | Models | Text, image, audio, and vision | Text models. See [Available models](#available-models) | Requests to `https://api.hyperbolic.xyz/v1` now return `404` with a message that the endpoint was decommissioned. Model IDs have also changed, so use an ID from [Available models](#available-models). > [!TIP] > > Need dedicated capacity, custom pricing, or a model that isn't listed? [Contact sales](mailto:sales@hyperbolic.ai). To serve a model yourself, rent an [on-demand GPU](https://hyperbolic.ai/docs/on-demand/overview.md). ## Next steps > [card] [Quick start](https://hyperbolic.ai/docs/inference/quickstart.md) > > Make your first request in a few minutes. > [card] [Errors](https://hyperbolic.ai/docs/inference/errors.md) > > Error codes and how to fix them. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.