> ## Documentation Index > Fetch the complete documentation index at: https://docs.aireserve.com/llms.txt > Use this file to discover all available pages before exploring further. # Models > One API key unlocks every model in the catalog — chat, reasoning, vision, image generation, and video — through a single, flat ID namespace. One API key unlocks every model below through a single, flat ID namespace — the same `model` / `modelId` string works across the Converse SDKs, the OpenAI-compatible endpoints, and the Bedrock wire-format routes. The live catalog is always available programmatically: ```bash theme={"dark"} curl https://api.aireserve.com/v1/models \ -H "Authorization: Bearer $AUDACITY_API_KEY" ``` `GET /v1/models` returns the OpenAI-shaped list, so model pickers and framework integrations that enumerate models work unchanged. Treat it as the source of truth — the tables below are a human-readable snapshot. ## Chat & reasoning models **Reasoning models and small `max_tokens`.** Models that think before answering (`gemini-3-flash-preview`, `gpt-5.x`, `grok-4-1-fast-reasoning`, …) spend part of the token budget on internal reasoning. With a tight cap (e.g. `max_tokens: 50`) the budget can be consumed before any visible text is produced — the response then comes back with `finish_reason / stop_reason = max_tokens` (or `length`) and empty content. That's the model, not an error: raise `max_tokens` (a few hundred is a safe floor for reasoning models) or pick a non-reasoning model for short outputs. | Family | Model IDs | Notes | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | | OpenAI GPT | `gpt-5.5`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-4o`, `gpt-4o-mini`, `gpt-4-turbo` | Vision on 4o/5.x; automatic prompt caching | | Anthropic Claude | `claude-fable-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-sonnet-4-5`, `claude-haiku-4-5-20251001` | Vision; explicit prompt caching ([minimums](/capabilities/prompt-caching)); `-bedrock` variants available ([below](#bedrock-routed-variants-&-aws-model-ids)) | | Google Gemini | `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash` | Vision + native video input ([table](/capabilities/video-input)); implicit caching | | xAI Grok | `grok-4-3`, `grok-4-1-fast-reasoning`, `grok-4-1-fast-non-reasoning`, `grok-3`, `grok-3-mini` | Automatic caching | | DeepSeek | `deepseek-reasoner`, `deepseek-chat`, `deepseek-v4-pro`, `deepseek-v4-flash` | `deepseek-reasoner-bedrock` variant available | | Meta Llama | `llama-4-maverick`, `llama-4-scout` | `-bedrock` variants available | | Mistral | `mistral-large`, `mistral-small` | `mistral-large-bedrock` variant available | | Moonshot / Kimi | `kimi-k2.7-code`, `kimi-k2.6`, `moonshot-v1-8k`, `moonshot-v1-32k`, `moonshot-v1-128k` | `kimi-k2.7-code` is coding-tuned | | Alibaba Qwen | `qwen-3.7-max`, `qwen-3.7-plus` | | | Perplexity Sonar | `sonar-pro`, `sonar`, `sonar-reasoning-pro`, `sonar-deep-research` | Web-grounded answers with citations | | NVIDIA Nemotron | `nemotron-3-ultra`, `nemotron-3-super`, `nemotron-3-nano` | Open-weight, managed hosting | | Other open-weight | `minimax-m3`, `glm-5.2`, `gpt-oss-120b`, `gpt-oss-20b` | Managed hosting | Convenience aliases: `claude-sonnet` and `claude-opus` track our recommended current Sonnet and Opus releases, so pinned integrations can opt into upgrades by using the alias instead of a dated ID. Retired model IDs return `404 ResourceNotFoundException` — enumerate `/v1/models` rather than hardcoding lists. ## Bedrock-routed variants & AWS model IDs Eleven models are also offered *via AWS Bedrock serving* under `-bedrock` IDs — same shapes, same key, one-string A/B against the direct path. See [Bedrock-routed models](/migrate/from-bedrock#bedrock-routed-models) for the full mapping. On the Bedrock wire-format routes (`/model/{id}/converse[-stream]`) the gateway additionally accepts native AWS model IDs (`us.anthropic.…`, inference-profile ARNs) so unmodified boto3 code works without renaming models — see [AWS SDK (boto3)](/connect/aws-sdk). ## 1M-token context The extended-context models — `claude-sonnet-4-6`, `fable-5`, and `opus-4-8` — serve a full 1M-token window through the gateway. Two equivalent ways to opt in: * Append the `[1m]` suffix to the model ID (e.g. `claude-sonnet-4-6[1m]`) — the gateway accepts this form directly. * Send the `anthropic-beta: context-1m-2025-08-07` header, which the gateway relays to Anthropic. Tokens are billed at the model's normal rates. Running Claude Code? It budgets a 200K window by default behind a custom base URL — pin the `[1m]` form through `ANTHROPIC_MODEL` to get the full window; see [Why the `[1m]` suffix?](/connect/claude-code#why-the-1m-suffix) for the details. ## China-hosted models A few catalog models are served by providers operating under PRC jurisdiction — prompts sent to these models are processed on that provider's infrastructure: `deepseek-chat` and `deepseek-reasoner` (DeepSeek's own API), and the Moonshot official-API models (`kimi-k3`, `moonshot-v1-8k`, `moonshot-v1-32k`, `moonshot-v1-128k`). The distinguishing test is the serving infrastructure, not the model's origin — Chinese-origin open weights served from US infrastructure (for example `deepseek-v4-pro`, `qwen-3.7-max`, `kimi-k2.7-code`, or `deepseek-reasoner-bedrock` on AWS) are not China-hosted. Organization admins control access with a per-client opt-in: when disabled, China-hosted models are excluded everywhere — the chat picker, auto-routing, and API traffic through the gateway. See the [provider data-handling disclosures](https://aireserve.com/developers/data-handling) for what each provider receives. ## Image generation Via `POST /v1/images/generations` ([guide & pricing](/capabilities/image-generation)): `gemini-2.5-flash-image`, `gpt-image-1`. The retired `dall-e-3`, `imagen-3`, `imagen-4`, `imagen-4-fast`, and `imagen-4-ultra` IDs return errors — migrate to `gemini-2.5-flash-image` or `gpt-image-1`. ## Video generation Via the async `POST /v1/videos/generations` job API ([guide & pricing](/capabilities/video-generation)): `wan-2.6` and `seedance-2.0`. ## Capability reference | Capability | Where documented | | --------------------------- | ------------------------------------------------------------------- | | Streaming | [Streaming](/capabilities/streaming) — all chat models | | Tool use / function calling | [Tool use](/capabilities/tool-use) | | Vision (image input) | [Images](/capabilities/vision) — per-model table | | Video input | [Video input](/capabilities/video-input) — per-model table | | Prompt caching | [Prompt caching](/capabilities/prompt-caching) — per-model minimums | | Token counting | `POST /v1/messages/count_tokens` (Anthropic-shape) |