# Models

> Browse INFRO's model catalog: vendor/model-name IDs, GET /v1/models, capability flags, context length, per-token pricing, and the deprecation policy.

Source: https://infro.io/docs/models

> **Note:** INFRO is in private early access. Running these examples requires an early-access account, an active trial or subscription entitlement, and your own provider connection. Self-serve purchasing is not generally open. See [Early access](https://infro.io/early-access).

INFRO routes to the text, image, video, and audio models your connected providers serve, from every major lab, behind one API. Each model has a stable ID you pass as `model` — to [chat completions](https://infro.io/docs/api/chat-completions), [images](https://infro.io/docs/modalities/images), [video](https://infro.io/docs/modalities/video), or [audio](https://infro.io/docs/modalities/audio) — and a catalog entry with its vendor's reference rate and capabilities.

See which providers you can connect at [/providers](https://infro.io/providers), and fetch the models your key can call with `GET /v1/models` — useful for model pickers, validating IDs at startup, or filtering by capability.

## Model IDs

Every model ID is `vendor/model-name`; IDs are matched case-insensitively. The vendor is the lab that trained the model, not the account that serves it — `anthropic/claude-sonnet-5` is served by whichever of your connections can serve Anthropic models (Anthropic directly, or Vertex AI, for example). A bare name without the vendor, like `claude-sonnet-5`, also resolves when exactly one of your connected vendors has a model by that name; if more than one does, the request returns `400` with code `ambiguous_model`. The name of one of your [routes](https://infro.io/docs/routes) is also a valid `model`. For providers whose ids INFRO cannot derive (LaoZhang, Together, Fireworks, Bedrock, an OpenAI-compatible endpoint and others), `<provider>/<model id>` sends the provider's own id to that provider's connections exactly as written, case included; see [Providers](https://infro.io/docs/providers). Every response names the `provider` and `connection` that served it, and `route` gives its position in the chain (`primary`, `standby_a`, …).

```text
openai/gpt-5.6-sol
anthropic/claude-sonnet-5
google/gemini-3.1-pro
deepseek/deepseek-v4-flash
qwen/qwen3-coder
```

A mistyped or unknown ID returns `404` with error type `model_not_found`. A known model that none of your connections can serve returns `503` with code `no_provider_connected`, naming the provider to connect. Don't retry either — see [error handling](https://infro.io/docs/api/errors) for which statuses are retryable.

## List models

`GET /v1/models` returns what the calling key can actually reach: a catalog model appears only when at least one enabled, healthy connection in the key's environment serves it and every allowlist that applies permits it. Your organization's active routes are listed too, with `type: "route"`. It works with any OpenAI-compatible SDK's `models.list()`.

**curl**

```bash
curl https://api.infro.io/v1/models \
  -H "Authorization: Bearer $INFRO_API_KEY"
```

**Python**

```python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.infro.io/v1",
    api_key=os.environ["INFRO_API_KEY"],
)

for model in client.models.list().data:
    print(model.id)
```

**TypeScript**

```typescript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.infro.io/v1",
  apiKey: process.env.INFRO_API_KEY,
});

const models = await client.models.list();
for (const model of models.data) {
  console.log(model.id);
}
```

```json
{
  "data": [
    {
      "id": "anthropic/claude-sonnet-5",
      "type": "model",
      "name": "Claude Sonnet 5",
      "context_length": null,
      "pricing": {
        "prompt": "0.000002",
        "completion": "0.00001",
        "source": "vendor_list"
      },
      "capabilities": [],
      "served_by": [
        { "id": "conn_8Kx2mQ4vR7tYb1Zp", "name": "Production Anthropic", "provider_kind": "anthropic" }
      ]
    },
    {
      "id": "support-agent",
      "type": "route",
      "name": "Support agent",
      "context_length": null,
      "pricing": { "source": "unpriced" },
      "capabilities": [],
      "strategy": "priority",
      "targets": [
        { "model": "anthropic/claude-sonnet-5", "connection": "conn_8Kx2mQ4vR7tYb1Zp" }
      ]
    }
  ]
}
```

- `id` (string) — Canonical `vendor/model-name` ID for a model, or the slug of a route. Pass this as `model` in requests; model IDs (not route slugs) can also go in `fallbacks` lists.
- `type` ("model" | "route") — Whether the entry is a catalog model or one of your organization's routes.
- `name` (string) — Human-readable display name, suitable for UI.
- `context_length` (integer | null) — Maximum context window in tokens — prompt and completion combined. `null` when the catalog does not record it, and always `null` for a route.
- `pricing.prompt` (string) — USD per prompt token at the vendor's published list rate — reference data for cost estimation, not a price INFRO charges. This field always shows the list rate; your organization's own rate, once entered under Prices in the console, is what cost estimates use instead. A string to avoid float precision issues; multiply by 1,000,000 for per-1M-token comparison. Absent when the model is priced per unit or not priced.
- `pricing.completion` (string) — USD per completion token at the vendor's published list rate, on the same terms.
- `pricing.unit / pricing.per` (string) — For models billed per unit (images, video, audio): the list rate in USD and the unit it applies to.
- `pricing.source` ("vendor_list" | "unpriced") — `vendor_list` when the figures are the vendor's published rate; `unpriced` when no rate is known, in which case requests to the model are recorded as unpriced, never as free.
- `capabilities` (array of strings) — Feature flags: any of `tools`, `vision`, `json`. See below.
- `served_by` (array of objects) — Models only. Your connections that would serve a request for this model, in the order they would be tried: `id`, `name` and `provider_kind`.
- `strategy / targets` (string / array of objects) — Routes only. The route's strategy and its enabled targets in order, each a `model` and a `connection` ID.

## Capabilities

The `capabilities` array records what a model supports. The catalog only lists a flag once it has been verified for that model, and many entries do not record capabilities yet, so an empty array means *not recorded*, not *unsupported*. Three flags:

- `tools` (capability) — Supports the OpenAI `tools`/`tool_choice` schema, normalized across providers. See [tool calling](https://infro.io/docs/features/tool-calling).
- `vision` (capability) — Accepts `image_url` content parts (HTTPS or base64 data URLs, 20MB max per image request). See [vision](https://infro.io/docs/features/vision).
- `json` (capability) — Supports strict `json_schema` structured outputs. Plain `{"type": "json_object"}` works on most models regardless of this flag — `json` specifically gates strict schema mode. See [structured outputs](https://infro.io/docs/features/structured-outputs).

To filter the catalog by capability, fetch the list and check membership:

**curl**

```bash
curl -s https://api.infro.io/v1/models \
  -H "Authorization: Bearer $INFRO_API_KEY" |
  jq -r '.data[] | select(.capabilities | index("vision")) | .id'
```

**Python**

```python
import os
import requests

resp = requests.get(
    "https://api.infro.io/v1/models",
    headers={"Authorization": f"Bearer {os.environ['INFRO_API_KEY']}"},
)

vision_models = [
    m["id"] for m in resp.json()["data"]
    if "vision" in m["capabilities"]
]
print(vision_models)
```

**TypeScript**

```typescript
const resp = await fetch("https://api.infro.io/v1/models", {
  headers: { Authorization: `Bearer ${process.env.INFRO_API_KEY}` },
});
const { data } = await resp.json();

const visionModels = data
  .filter((m) => m.capabilities.includes("vision"))
  .map((m) => m.id);
console.log(visionModels);
```

## Context length and pricing

`context_length`, when recorded, is the total window: input tokens plus generated tokens must fit inside it. When a completion hits the window (or your `max_tokens`), it stops with `finish_reason: "length"` — budget accordingly for long prompts.

Catalog pricing is the **model vendor's own published rate**, and INFRO adds nothing to it — your provider invoices you directly at whatever you have negotiated with them. Each response carries `usage.cost`, an estimate of what that request will cost you, and `usage.price_source`, which says where the rate came from: `custom_provider` or `custom` when you have entered your own rate under [Prices](https://infro.io/docs/org/billing), `list` for the vendor's list rate, or `provider` when the provider reported the cost itself. When no rate is known, `usage.cost` is `null` and `price_source` is absent.

## Model reference pages

Each model in the reference catalog has its own page: the vendor's list rate, the endpoint it is called on, and a request sample. The rates are the vendor's published list rates, checked 2026-10-05. Your provider bills you at whatever you have negotiated with them, and INFRO adds nothing. A model is reachable through INFRO only when one of your own [provider connections](https://infro.io/docs/providers) serves it.

| Model | Vendor | Modality | List rate |
| --- | --- | --- | --- |
| [Qwen Audio 3.0 TTS Flash](https://infro.io/models/qwen/qwen-audio-3.0-tts-flash) | Alibaba | Audio | $15 per 1M chars |
| [Qwen Audio 3.0 TTS Plus](https://infro.io/models/qwen/qwen-audio-3.0-tts-plus) | Alibaba | Audio | $20 per 1M chars |
| [Qwen3-ASR Flash](https://infro.io/models/qwen/qwen3-asr-flash) | Alibaba | Audio | $0.126 per audio hour |
| [Universal-3](https://infro.io/models/assemblyai/universal-3) | AssemblyAI | Audio | $0.27 per audio hour |
| [Universal-3.5 Pro](https://infro.io/models/assemblyai/universal-3.5-pro) | AssemblyAI | Audio | $0.45 per audio hour |
| [Seed Audio](https://infro.io/models/bytedance/seed-audio) | ByteDance | Audio | $0.0025 per second |
| [Orpheus 3B](https://infro.io/models/canopylabs/orpheus-3b) | Canopy Labs | Audio | $15 per 1M chars |
| [Orpheus Arabic (Saudi)](https://infro.io/models/canopylabs/orpheus-arabic-saudi) | Canopy Labs | Audio | $40 per 1M chars |
| [Orpheus V1 English](https://infro.io/models/canopylabs/orpheus-v1-english) | Canopy Labs | Audio | $22 per 1M chars |
| [Sonic 3](https://infro.io/models/cartesia/sonic-3) | Cartesia | Audio | $55 per 1M chars |
| [Aura-2](https://infro.io/models/deepgram/aura-2) | Deepgram | Audio | $30 per 1M chars |
| [Flux TTS](https://infro.io/models/deepgram/flux-tts) | Deepgram | Audio | $45 per 1M chars |
| [Nova-3](https://infro.io/models/deepgram/nova-3) | Deepgram | Audio | $0.258 per audio hour |
| [Nova-4](https://infro.io/models/deepgram/nova-4) | Deepgram | Audio | $0.26 per audio hour |
| [Eleven Music](https://infro.io/models/elevenlabs/music) | ElevenLabs | Audio | $0.0025 per second |
| [ElevenLabs Flash v2](https://infro.io/models/elevenlabs/eleven-flash-v2) | ElevenLabs | Audio | $40 per 1M chars |
| [ElevenLabs Flash v2.5](https://infro.io/models/elevenlabs/eleven-flash-v2.5) | ElevenLabs | Audio | $40 per 1M chars |
| [ElevenLabs Multilingual v2](https://infro.io/models/elevenlabs/eleven-multilingual-v2) | ElevenLabs | Audio | $80 per 1M chars |
| [ElevenLabs Sound Effects v2](https://infro.io/models/elevenlabs/sound-effects-v2) | ElevenLabs | Audio | $0.0020 per second |
| [ElevenLabs V3](https://infro.io/models/elevenlabs/eleven-v3) | ElevenLabs | Audio | $80 per 1M chars |
| [ElevenLabs V4](https://infro.io/models/elevenlabs/eleven-v4) | ElevenLabs | Audio | $80 per 1M chars |
| [ElevenLabs V4 Turbo](https://infro.io/models/elevenlabs/eleven-v4-turbo) | ElevenLabs | Audio | $40 per 1M chars |
| [Scribe v2](https://infro.io/models/elevenlabs/scribe-v2) | ElevenLabs | Audio | $0.22 per audio hour |
| [Scribe v2 Medical](https://infro.io/models/elevenlabs/scribe-v2-medical) | ElevenLabs | Audio | $0.22 per audio hour |
| [Fish Audio S1](https://infro.io/models/fish-audio/s1) | Fish Audio | Audio | $15 per 1M chars |
| [Fish Audio S2 Pro](https://infro.io/models/fish-audio/s2-pro) | Fish Audio | Audio | $15 per 1M chars |
| [Fish Audio S2.1 Pro](https://infro.io/models/fish-audio/s2.1-pro) | Fish Audio | Audio | $15 per 1M chars |
| [Fish Audio Transcribe 1](https://infro.io/models/fish-audio/transcribe-1) | Fish Audio | Audio | $0.36 per audio hour |
| [Fish Audio Transcribe 1 Pro](https://infro.io/models/fish-audio/transcribe-1-pro) | Fish Audio | Audio | $0.36 per audio hour |
| [Chirp 3](https://infro.io/models/google/chirp-3) | Google | Audio | $0.96 per audio hour |
| [Gemini 3.1 Flash TTS](https://infro.io/models/google/gemini-3.1-flash-tts) | Google | Audio | $16 per 1M chars |
| [Gemini 3.5 Transcribe](https://infro.io/models/google/gemini-3.5-transcribe) | Google | Audio | $0.30 per audio hour |
| [Lyria 2](https://infro.io/models/google/lyria-2) | Google | Audio | $0.0020 per second |
| [Lyria 3 Clip (Preview)](https://infro.io/models/google/lyria-3-clip) | Google | Audio | $0.04 per track |
| [Lyria 3.5](https://infro.io/models/google/lyria-3.5) | Google | Audio | $0.08 per track |
| [Kokoro 82M](https://infro.io/models/hexgrad/kokoro-82m) | Kokoro | Audio | $4.00 per 1M chars |
| [Muse Voice Transcribe 1.0](https://infro.io/models/meta/muse-voice-transcribe-1.0) | Meta | Audio | $0.18 per audio hour |
| [MAI-Transcribe 1.5](https://infro.io/models/microsoft/mai-transcribe-1.5) | Microsoft | Audio | $0.36 per audio hour |
| [MAI-Transcribe 2](https://infro.io/models/microsoft/mai-transcribe-2) | Microsoft | Audio | $0.10 per audio hour |
| [MAI-Voice 2](https://infro.io/models/microsoft/mai-voice-2) | Microsoft | Audio | $22 per 1M chars |
| [MAI-Voice 2 Flash](https://infro.io/models/microsoft/mai-voice-2-flash) | Microsoft | Audio | $15 per 1M chars |
| [MAI-Voice 2.1](https://infro.io/models/microsoft/mai-voice-2.1) | Microsoft | Audio | $22 per 1M chars |
| [MAI-Voice 2.1 Flash](https://infro.io/models/microsoft/mai-voice-2.1-flash) | Microsoft | Audio | $15 per 1M chars |
| [MiniMax ASR](https://infro.io/models/minimax/asr-1.0) | MiniMax | Audio | $0.38 per audio hour |
| [MiniMax Music 1.5](https://infro.io/models/minimax/music-1.5) | MiniMax | Audio | $0.03 per track |
| [MiniMax Music 2.5](https://infro.io/models/minimax/music-2.5) | MiniMax | Audio | $0.15 per track |
| [Speech 2.6](https://infro.io/models/minimax/speech-2.6) | MiniMax | Audio | $35 per 1M chars |
| [Speech 2.8 HD](https://infro.io/models/minimax/speech-2.8-hd) | MiniMax | Audio | $100 per 1M chars |
| [Speech 2.8 Turbo](https://infro.io/models/minimax/speech-2.8-turbo) | MiniMax | Audio | $60 per 1M chars |
| [Voxtral Mini Transcribe 2](https://infro.io/models/mistral/voxtral-mini-transcribe-2) | Mistral | Audio | $0.18 per audio hour |
| [Voxtral TTS](https://infro.io/models/mistral/voxtral-tts) | Mistral | Audio | $16 per 1M chars |
| [MMAudio v2](https://infro.io/models/mmaudio/mmaudio-v2) | MMAudio | Audio | $0.0010 per second |
| [Nemotron 3.5 ASR](https://infro.io/models/nvidia/nemotron-3.5-asr) | NVIDIA | Audio | $0.27 per audio hour |
| [Parakeet TDT 0.6B v3](https://infro.io/models/nvidia/parakeet-tdt-0.6b-v3) | NVIDIA | Audio | $0.09 per audio hour |
| [GPT-4o mini Transcribe](https://infro.io/models/openai/gpt-4o-mini-transcribe) | OpenAI | Audio | $0.18 per audio hour |
| [GPT-4o Transcribe](https://infro.io/models/openai/gpt-4o-transcribe) | OpenAI | Audio | $0.36 per audio hour |
| [GPT-Transcribe](https://infro.io/models/openai/gpt-transcribe) | OpenAI | Audio | $0.27 per audio hour |
| [TTS-1](https://infro.io/models/openai/tts-1) | OpenAI | Audio | $15 per 1M chars |
| [TTS-1 HD](https://infro.io/models/openai/tts-1-hd) | OpenAI | Audio | $30 per 1M chars |
| [Whisper](https://infro.io/models/openai/whisper-1) | OpenAI | Audio | $0.36 per audio hour |
| [Whisper Large v3](https://infro.io/models/openai/whisper-large-v3) | OpenAI | Audio | $0.09 per audio hour |
| [Whisper v3 Turbo](https://infro.io/models/openai/whisper-v3-turbo) | OpenAI | Audio | $0.04 per audio hour |
| [Qwen3-ASR 0.6B](https://infro.io/models/qwen/qwen3-asr-0.6b) | Qwen | Audio | $0.012 per audio hour |
| [Qwen3-ASR 1.7B](https://infro.io/models/qwen/qwen3-asr-1.7b) | Qwen | Audio | $0.027 per audio hour |
| [CSM 1B](https://infro.io/models/sesame/csm-1b) | Sesame | Audio | $7.00 per 1M chars |
| [Stable Audio 2.5](https://infro.io/models/stability/stable-audio-2.5) | Stability AI | Audio | $0.20 per track |
| [Suno V5.5](https://infro.io/models/suno/suno-v5.5) | Suno | Audio | $0.10 per track |
| [Grok Speech to Text](https://infro.io/models/xai/grok-stt-1.0) | xAI | Audio | $0.10 per audio hour |
| [Grok Voice TTS](https://infro.io/models/xai/grok-voice-tts-1.0) | xAI | Audio | $15 per 1M chars |
| [GLM-ASR](https://infro.io/models/zai/glm-asr-2512) | Z.ai | Audio | $0.144 per audio hour |
| [Qwen-Image 3.0](https://infro.io/models/qwen/qwen-image-3) | Alibaba | Image | $0.03 per image |
| [Qwen-Image 3.0 Pro](https://infro.io/models/qwen/qwen-image-3-pro) | Alibaba | Image | $0.04 per image |
| [Wan 2.7 Image](https://infro.io/models/alibaba/wan-2.7-image) | Alibaba | Image | $0.03 per image |
| [Wan 2.7 Image Pro](https://infro.io/models/alibaba/wan-2.7-image-pro) | Alibaba | Image | $0.075 per image |
| [FLUX.2 (dev)](https://infro.io/models/bfl/flux-2-dev) | Black Forest Labs | Image | $0.025 per image |
| [FLUX.2 (flex)](https://infro.io/models/bfl/flux-2-flex) | Black Forest Labs | Image | $0.05 per image |
| [FLUX.2 (klein) 4B](https://infro.io/models/bfl/flux-2-klein-4b) | Black Forest Labs | Image | $0.014 per image |
| [FLUX.2 (klein) 9B](https://infro.io/models/bfl/flux-2-klein-9b) | Black Forest Labs | Image | $0.015 per image |
| [FLUX.2 (max)](https://infro.io/models/bfl/flux-2-max) | Black Forest Labs | Image | $0.07 per image |
| [FLUX.2 (pro)](https://infro.io/models/bfl/flux-2-pro) | Black Forest Labs | Image | $0.03 per image |
| [Seedream 4.0](https://infro.io/models/bytedance/seedream-4) | ByteDance | Image | $0.03 per image |
| [Seedream 4.5](https://infro.io/models/bytedance/seedream-4.5) | ByteDance | Image | $0.04 per image |
| [Seedream 5.0 Flash](https://infro.io/models/bytedance/seedream-5-flash) | ByteDance | Image | $0.018 per image |
| [Seedream 5.0 Lite](https://infro.io/models/bytedance/seedream-5-lite) | ByteDance | Image | $0.035 per image |
| [Seedream 5.0 Pro](https://infro.io/models/bytedance/seedream-5-pro) | ByteDance | Image | $0.045 per image |
| [Imagen Upscaler](https://infro.io/models/google/imagen-upscaler) | Google | Image | $0.02 per image |
| [Nano Banana](https://infro.io/models/google/nano-banana) | Google | Image | $0.039 per image |
| [Nano Banana 2](https://infro.io/models/google/nano-banana-2) | Google | Image | $0.067 per image |
| [Nano Banana 2 Lite](https://infro.io/models/google/nano-banana-2-lite) | Google | Image | $0.034 per image |
| [Nano Banana Pro](https://infro.io/models/google/nano-banana-pro) | Google | Image | $0.134 per image |
| [Ideogram 3.0](https://infro.io/models/ideogram/ideogram-3) | Ideogram | Image | $0.06 per image |
| [Ideogram 4.0](https://infro.io/models/ideogram/ideogram-4) | Ideogram | Image | $0.06 per image |
| [Kling Image 3.0](https://infro.io/models/kuaishou/kling-image-3) | Kuaishou | Image | $0.028 per image |
| [Kling Image 3.0 Omni](https://infro.io/models/kuaishou/kling-image-o3) | Kuaishou | Image | $0.028 per image |
| [Uni-1.1](https://infro.io/models/luma/uni-1) | Luma | Image | $0.04 per image |
| [Uni-1.1 Max](https://infro.io/models/luma/uni-1-max) | Luma | Image | $0.10 per image |
| [Magnific Precision Upscaler v2](https://infro.io/models/magnific/precision-upscaler-v2) | Magnific | Image | $0.25 per image |
| [MiniMax Image-01](https://infro.io/models/minimax/image-01) | MiniMax | Image | $0.0035 per image |
| [GPT Image 1](https://infro.io/models/openai/gpt-image-1) | OpenAI | Image | $0.042 per image |
| [GPT Image 1 Mini](https://infro.io/models/openai/gpt-image-1-mini) | OpenAI | Image | $0.011 per image |
| [GPT Image 1.5](https://infro.io/models/openai/gpt-image-1.5) | OpenAI | Image | $0.034 per image |
| [GPT Image 2](https://infro.io/models/openai/gpt-image-2) | OpenAI | Image | $0.053 per image |
| [GPT Image 2.5 Flare](https://infro.io/models/openai/gpt-image-2.5-flare) | OpenAI | Image | $0.013 per image |
| [GPT Image 2.5 Sunburst](https://infro.io/models/openai/gpt-image-2.5-sunburst) | OpenAI | Image | $0.013 per image |
| [Real-ESRGAN](https://infro.io/models/xinntao/real-esrgan) | Real-ESRGAN | Image | $0.0020 per image |
| [Recraft Crisp Upscale](https://infro.io/models/recraft/crisp-upscale) | Recraft | Image | $0.0040 per image |
| [Recraft V3](https://infro.io/models/recraft/recraft-v3) | Recraft | Image | $0.04 per image |
| [Recraft V4](https://infro.io/models/recraft/recraft-v4) | Recraft | Image | $0.04 per image |
| [Recraft V4 Pro](https://infro.io/models/recraft/recraft-v4-pro) | Recraft | Image | $0.25 per image |
| [Recraft V4.1](https://infro.io/models/recraft/recraft-v4.1) | Recraft | Image | $0.035 per image |
| [Recraft V4.1 Flash](https://infro.io/models/recraft/recraft-v4.1-flash) | Recraft | Image | $0.0070 per image |
| [Recraft V4.1 Pro](https://infro.io/models/recraft/recraft-v4.1-pro) | Recraft | Image | $0.21 per image |
| [Runway Gen-4 Image](https://infro.io/models/runway/gen-4-image) | Runway | Image | $0.05 per image |
| [Runway Gen-4 Image Turbo](https://infro.io/models/runway/gen-4-image-turbo) | Runway | Image | $0.02 per image |
| [Topaz Image Upscale](https://infro.io/models/topaz/image-upscale) | Topaz Labs | Image | $0.08 per image |
| [Grok Imagine 2.0](https://infro.io/models/xai/grok-imagine-image-2) | xAI | Image | $0.04 per image |
| [Grok Imagine Image](https://infro.io/models/xai/grok-imagine-image) | xAI | Image | $0.02 per image |
| [Grok Imagine Image Quality](https://infro.io/models/xai/grok-imagine-image-quality) | xAI | Image | $0.05 per image |
| [CogView-4](https://infro.io/models/zai/cogview-4) | Z.ai | Image | $0.01 per image |
| [GLM-Image](https://infro.io/models/zai/glm-image) | Z.ai | Image | $0.015 per image |
| [Qwen-VL Max](https://infro.io/models/qwen/qwen-vl-max) | Alibaba | Text | $0.80 in / $3.20 out per 1M tokens |
| [Qwen3-Coder](https://infro.io/models/qwen/qwen3-coder) | Alibaba | Text | $1.00 in / $5.00 out per 1M tokens |
| [Qwen3-Coder Flash](https://infro.io/models/qwen/qwen3-coder-flash) | Alibaba | Text | $0.30 in / $1.50 out per 1M tokens |
| [Qwen3-Coder Next](https://infro.io/models/qwen/qwen3-coder-next) | Alibaba | Text | $0.30 in / $1.50 out per 1M tokens |
| [Qwen3-VL Plus](https://infro.io/models/qwen/qwen3-vl-plus) | Alibaba | Text | $0.20 in / $1.60 out per 1M tokens |
| [Qwen3.5 9B](https://infro.io/models/qwen/qwen3.5-9b) | Alibaba | Text | $0.17 in / $0.25 out per 1M tokens |
| [Qwen3.6 Plus](https://infro.io/models/qwen/qwen3.6-plus) | Alibaba | Text | $0.50 in / $3.00 out per 1M tokens |
| [Qwen3.7 Max](https://infro.io/models/qwen/qwen3.7-max) | Alibaba | Text | $2.50 in / $7.50 out per 1M tokens |
| [Qwen3.7 Plus](https://infro.io/models/qwen/qwen3.7-plus) | Alibaba | Text | $0.40 in / $1.60 out per 1M tokens |
| [Qwen3.8 27B](https://infro.io/models/qwen/qwen3.8-27b) | Alibaba | Text | $0.50 in / $3.00 out per 1M tokens |
| [Qwen3.8 Flash](https://infro.io/models/qwen/qwen3.8-flash) | Alibaba | Text | $0.15 in / $0.47 out per 1M tokens |
| [Qwen3.8 Max](https://infro.io/models/qwen/qwen3.8-max) | Alibaba | Text | $2.00 in / $6.00 out per 1M tokens |
| [Amazon Nova 2 Lite](https://infro.io/models/amazon/nova-2-lite) | Amazon | Text | $0.30 in / $2.50 out per 1M tokens |
| [Amazon Nova Lite](https://infro.io/models/amazon/nova-lite) | Amazon | Text | $0.06 in / $0.24 out per 1M tokens |
| [Amazon Nova Micro](https://infro.io/models/amazon/nova-micro) | Amazon | Text | $0.035 in / $0.14 out per 1M tokens |
| [Amazon Nova Pro](https://infro.io/models/amazon/nova-pro) | Amazon | Text | $0.80 in / $3.20 out per 1M tokens |
| [Claude Fable 5](https://infro.io/models/anthropic/claude-fable-5) | Anthropic | Text | $10 in / $50 out per 1M tokens |
| [Claude Fable 5.1](https://infro.io/models/anthropic/claude-fable-5.1) | Anthropic | Text | $10 in / $50 out per 1M tokens |
| [Claude Haiku 4.5](https://infro.io/models/anthropic/claude-haiku-4.5) | Anthropic | Text | $1.00 in / $5.00 out per 1M tokens |
| [Claude Opus 4.5](https://infro.io/models/anthropic/claude-opus-4.5) | Anthropic | Text | $5.00 in / $25 out per 1M tokens |
| [Claude Opus 4.6](https://infro.io/models/anthropic/claude-opus-4.6) | Anthropic | Text | $5.00 in / $25 out per 1M tokens |
| [Claude Opus 4.7](https://infro.io/models/anthropic/claude-opus-4.7) | Anthropic | Text | $5.00 in / $25 out per 1M tokens |
| [Claude Opus 4.8](https://infro.io/models/anthropic/claude-opus-4.8) | Anthropic | Text | $5.00 in / $25 out per 1M tokens |
| [Claude Opus 5](https://infro.io/models/anthropic/claude-opus-5) | Anthropic | Text | $5.00 in / $25 out per 1M tokens |
| [Claude Opus 5.5](https://infro.io/models/anthropic/claude-opus-5.5) | Anthropic | Text | $4.00 in / $20 out per 1M tokens |
| [Claude Sonnet 4.6](https://infro.io/models/anthropic/claude-sonnet-4.6) | Anthropic | Text | $3.00 in / $15 out per 1M tokens |
| [Claude Sonnet 5](https://infro.io/models/anthropic/claude-sonnet-5) | Anthropic | Text | $2.00 in / $10 out per 1M tokens |
| [Claude Sonnet 5.5](https://infro.io/models/anthropic/claude-sonnet-5.5) | Anthropic | Text | $2.00 in / $10 out per 1M tokens |
| [Clef](https://infro.io/models/cloudflare/clef) | Cloudflare | Text | $0.24 in / $0.00 out per 1M tokens |
| [Clef Flash](https://infro.io/models/cloudflare/clef-flash) | Cloudflare | Text | $0.038 in / $0.00 out per 1M tokens |
| [Clef Omni](https://infro.io/models/cloudflare/clef-omni) | Cloudflare | Text | $0.15 in / $0.00 out per 1M tokens |
| [Aya Expanse 32B](https://infro.io/models/cohere/aya-expanse-32b) | Cohere | Text | $0.50 in / $1.50 out per 1M tokens |
| [Command R](https://infro.io/models/cohere/command-r) | Cohere | Text | $0.15 in / $0.60 out per 1M tokens |
| [Command R+](https://infro.io/models/cohere/command-r-plus) | Cohere | Text | $2.50 in / $10 out per 1M tokens |
| [Command R7B](https://infro.io/models/cohere/command-r7b) | Cohere | Text | $0.037 in / $0.15 out per 1M tokens |
| [DeepSeek Flash (V4.1)](https://infro.io/models/deepseek/deepseek-flash) | DeepSeek | Text | $0.30 in / $1.20 out per 1M tokens |
| [DeepSeek V4 Flash](https://infro.io/models/deepseek/deepseek-v4-flash) | DeepSeek | Text | $0.30 in / $1.20 out per 1M tokens |
| [DeepSeek V4 Pro](https://infro.io/models/deepseek/deepseek-v4-pro) | DeepSeek | Text | $1.32 in / $3.96 out per 1M tokens |
| [Ember-1](https://infro.io/models/fireworks/ember-1) | Fireworks | Text | $3.00 in / $15 out per 1M tokens |
| [Gemini 3 Flash (Preview)](https://infro.io/models/google/gemini-3-flash) | Google | Text | $0.50 in / $3.00 out per 1M tokens |
| [Gemini 3.1 Flash-Lite](https://infro.io/models/google/gemini-3.1-flash-lite) | Google | Text | $0.25 in / $1.50 out per 1M tokens |
| [Gemini 3.1 Pro](https://infro.io/models/google/gemini-3.1-pro) | Google | Text | $2.00 in / $12 out per 1M tokens |
| [Gemini 3.5 Flash](https://infro.io/models/google/gemini-3.5-flash) | Google | Text | $1.50 in / $9.00 out per 1M tokens |
| [Gemini 3.5 Flash-Lite](https://infro.io/models/google/gemini-3.5-flash-lite) | Google | Text | $0.30 in / $2.50 out per 1M tokens |
| [Gemini 3.6 Flash](https://infro.io/models/google/gemini-3.6-flash) | Google | Text | $0.75 in / $3.75 out per 1M tokens |
| [Gemini 3.7 Flash](https://infro.io/models/google/gemini-3.7-flash) | Google | Text | $0.75 in / $3.75 out per 1M tokens |
| [Gemini 3.8 Flash](https://infro.io/models/google/gemini-3.8-flash) | Google | Text | $0.75 in / $3.75 out per 1M tokens |
| [Mercury Decide](https://infro.io/models/inception/mercury-decide) | Inception | Text | $0.02 in / $0.00 out per 1M tokens |
| [d1](https://infro.io/models/liquid/d1) | Liquid AI | Text | $0.04 in / $0.00 out per 1M tokens |
| [Llama 3.3 70B](https://infro.io/models/meta/llama-3.3-70b) | Meta | Text | $1.04 in / $1.04 out per 1M tokens |
| [Muse Glimmer 30B](https://infro.io/models/meta/muse-glimmer-30b) | Meta | Text | $0.35 in / $1.50 out per 1M tokens |
| [Microsoft-Decision-1](https://infro.io/models/microsoft/microsoft-decision-1) | Microsoft | Text | $0.042 in / $0.00 out per 1M tokens |
| [MiniMax M2.5](https://infro.io/models/minimax/minimax-m2.5) | MiniMax | Text | $0.30 in / $1.20 out per 1M tokens |
| [MiniMax M2.7](https://infro.io/models/minimax/minimax-m2.7) | MiniMax | Text | $0.30 in / $1.20 out per 1M tokens |
| [MiniMax M2.7 Highspeed](https://infro.io/models/minimax/minimax-m2.7-highspeed) | MiniMax | Text | $0.60 in / $2.40 out per 1M tokens |
| [MiniMax M3](https://infro.io/models/minimax/minimax-m3) | MiniMax | Text | $0.30 in / $1.20 out per 1M tokens |
| [Codestral](https://infro.io/models/mistral/codestral) | Mistral | Text | $0.30 in / $0.90 out per 1M tokens |
| [Ministral 3 14B](https://infro.io/models/mistral/ministral-3-14b) | Mistral | Text | $0.20 in / $0.20 out per 1M tokens |
| [Ministral 3 3B](https://infro.io/models/mistral/ministral-3-3b) | Mistral | Text | $0.10 in / $0.10 out per 1M tokens |
| [Ministral 3 8B](https://infro.io/models/mistral/ministral-3-8b) | Mistral | Text | $0.15 in / $0.15 out per 1M tokens |
| [Mistral Large 3](https://infro.io/models/mistral/mistral-large-3) | Mistral | Text | $0.50 in / $1.50 out per 1M tokens |
| [Mistral Medium 3.5](https://infro.io/models/mistral/mistral-medium-3.5) | Mistral | Text | $1.50 in / $7.50 out per 1M tokens |
| [Mistral Small 4](https://infro.io/models/mistral/mistral-small-4) | Mistral | Text | $0.15 in / $0.60 out per 1M tokens |
| [Voxtral Small](https://infro.io/models/mistral/voxtral-small) | Mistral | Text | $0.10 in / $0.40 out per 1M tokens |
| [Kimi K2.6](https://infro.io/models/moonshot/kimi-k2.6) | Moonshot | Text | $0.95 in / $4.00 out per 1M tokens |
| [Kimi K2.7 Code](https://infro.io/models/moonshot/kimi-k2.7-code) | Moonshot | Text | $0.95 in / $4.00 out per 1M tokens |
| [Kimi K2.7 Code Highspeed](https://infro.io/models/moonshot/kimi-k2.7-code-highspeed) | Moonshot | Text | $1.90 in / $8.00 out per 1M tokens |
| [Kimi K3](https://infro.io/models/moonshot/kimi-k3) | Moonshot | Text | $3.00 in / $15 out per 1M tokens |
| [Nemotron 3 Ultra](https://infro.io/models/nvidia/nemotron-3-ultra) | NVIDIA | Text | $0.60 in / $2.40 out per 1M tokens |
| [Nemotron 3.5 Lightning 30B A3B](https://infro.io/models/nvidia/nemotron-3.5-lightning-30b-a3b) | NVIDIA | Text | $0.05 in / $0.20 out per 1M tokens |
| [GPT-4.1](https://infro.io/models/openai/gpt-4.1) | OpenAI | Text | $2.00 in / $8.00 out per 1M tokens |
| [GPT-4.1 mini](https://infro.io/models/openai/gpt-4.1-mini) | OpenAI | Text | $0.40 in / $1.60 out per 1M tokens |
| [GPT-4o](https://infro.io/models/openai/gpt-4o) | OpenAI | Text | $2.50 in / $10 out per 1M tokens |
| [GPT-4o mini](https://infro.io/models/openai/gpt-4o-mini) | OpenAI | Text | $0.15 in / $0.60 out per 1M tokens |
| [GPT-5.3 Codex](https://infro.io/models/openai/gpt-5.3-codex) | OpenAI | Text | $1.75 in / $14 out per 1M tokens |
| [GPT-5.4](https://infro.io/models/openai/gpt-5.4) | OpenAI | Text | $2.50 in / $15 out per 1M tokens |
| [GPT-5.4 mini](https://infro.io/models/openai/gpt-5.4-mini) | OpenAI | Text | $0.75 in / $4.50 out per 1M tokens |
| [GPT-5.4 nano](https://infro.io/models/openai/gpt-5.4-nano) | OpenAI | Text | $0.20 in / $1.25 out per 1M tokens |
| [GPT-5.4 Pro](https://infro.io/models/openai/gpt-5.4-pro) | OpenAI | Text | $30 in / $180 out per 1M tokens |
| [GPT-5.5](https://infro.io/models/openai/gpt-5.5) | OpenAI | Text | $5.00 in / $30 out per 1M tokens |
| [GPT-5.5 Pro](https://infro.io/models/openai/gpt-5.5-pro) | OpenAI | Text | $30 in / $180 out per 1M tokens |
| [GPT-5.6 Luna](https://infro.io/models/openai/gpt-5.6-luna) | OpenAI | Text | $0.20 in / $1.20 out per 1M tokens |
| [GPT-5.6 Sol](https://infro.io/models/openai/gpt-5.6-sol) | OpenAI | Text | $4.00 in / $20 out per 1M tokens |
| [GPT-5.6 Terra](https://infro.io/models/openai/gpt-5.6-terra) | OpenAI | Text | $2.00 in / $12 out per 1M tokens |
| [GPT-6 Astra](https://infro.io/models/openai/gpt-6-astra) | OpenAI | Text | $10 in / $50 out per 1M tokens |
| [GPT-6 Luna](https://infro.io/models/openai/gpt-6-luna) | OpenAI | Text | $0.10 in / $0.50 out per 1M tokens |
| [GPT-6 Luna (Decisions)](https://infro.io/models/openai/gpt-6-luna-decisions) | OpenAI | Text | $0.10 in / $0.00 out per 1M tokens |
| [GPT-6 Sol](https://infro.io/models/openai/gpt-6-sol) | OpenAI | Text | $2.00 in / $10 out per 1M tokens |
| [GPT-6.1 Sol](https://infro.io/models/openai/gpt-6.1-sol) | OpenAI | Text | $2.00 in / $10 out per 1M tokens |
| [gpt-oss-120b](https://infro.io/models/openai/gpt-oss-120b) | OpenAI | Text | $0.15 in / $0.60 out per 1M tokens |
| [gpt-oss-20b](https://infro.io/models/openai/gpt-oss-20b) | OpenAI | Text | $0.075 in / $0.30 out per 1M tokens |
| [o3](https://infro.io/models/openai/o3) | OpenAI | Text | $2.00 in / $8.00 out per 1M tokens |
| [o3-pro](https://infro.io/models/openai/o3-pro) | OpenAI | Text | $20 in / $80 out per 1M tokens |
| [pplx-decider v1.1 27B](https://infro.io/models/perplexity/pplx-decider-v1.1-27b) | Perplexity | Text | $0.02 in / $0.00 out per 1M tokens |
| [Sonar](https://infro.io/models/perplexity/sonar) | Perplexity | Text | $1.00 in / $1.00 out per 1M tokens |
| [Sonar Deep Research](https://infro.io/models/perplexity/sonar-deep-research) | Perplexity | Text | $2.00 in / $8.00 out per 1M tokens |
| [Sonar Pro](https://infro.io/models/perplexity/sonar-pro) | Perplexity | Text | $3.00 in / $15 out per 1M tokens |
| [Sonar Reasoning Pro](https://infro.io/models/perplexity/sonar-reasoning-pro) | Perplexity | Text | $2.00 in / $8.00 out per 1M tokens |
| [Inkling](https://infro.io/models/thinkingmachines/inkling) | Thinking Machines | Text | $1.00 in / $4.05 out per 1M tokens |
| [Jev 1.13](https://infro.io/models/typesafe/jev-1.13) | TypeSafe | Text | $0.042 in / $0.00 out per 1M tokens |
| [Solar Decide](https://infro.io/models/upstage/solar-decide) | Upstage | Text | $0.05 in / $0.00 out per 1M tokens |
| [Solar Decide Flash](https://infro.io/models/upstage/solar-decide-flash) | Upstage | Text | $0.05 in / $0.00 out per 1M tokens |
| [Grok 4.20 Multi-Agent (Beta)](https://infro.io/models/xai/grok-4.20-multi-agent-0309) | xAI | Text | $1.25 in / $2.50 out per 1M tokens |
| [Grok 4.20 Non-Reasoning](https://infro.io/models/xai/grok-4.20-0309-non-reasoning) | xAI | Text | $1.25 in / $2.50 out per 1M tokens |
| [Grok 4.20 Reasoning](https://infro.io/models/xai/grok-4.20-0309-reasoning) | xAI | Text | $1.25 in / $2.50 out per 1M tokens |
| [Grok 4.3](https://infro.io/models/xai/grok-4.3) | xAI | Text | $1.25 in / $2.50 out per 1M tokens |
| [Grok 4.5](https://infro.io/models/xai/grok-4.5) | xAI | Text | $2.00 in / $6.00 out per 1M tokens |
| [Grok 4.6](https://infro.io/models/xai/grok-4.6) | xAI | Text | $2.00 in / $6.00 out per 1M tokens |
| [Grok 4.7](https://infro.io/models/xai/grok-4.7) | xAI | Text | $2.00 in / $6.00 out per 1M tokens |
| [Grok Build 0.1](https://infro.io/models/xai/grok-build-0.1) | xAI | Text | $1.00 in / $2.00 out per 1M tokens |
| [GLM-4.5 Air](https://infro.io/models/zai/glm-4.5-air) | Z.ai | Text | $0.20 in / $1.10 out per 1M tokens |
| [GLM-4.6](https://infro.io/models/zai/glm-4.6) | Z.ai | Text | $0.60 in / $2.20 out per 1M tokens |
| [GLM-4.6V](https://infro.io/models/zai/glm-4.6v) | Z.ai | Text | $0.30 in / $0.90 out per 1M tokens |
| [GLM-4.6V FlashX](https://infro.io/models/zai/glm-4.6v-flashx) | Z.ai | Text | $0.04 in / $0.40 out per 1M tokens |
| [GLM-4.7](https://infro.io/models/zai/glm-4.7) | Z.ai | Text | $0.60 in / $2.20 out per 1M tokens |
| [GLM-4.7 FlashX](https://infro.io/models/zai/glm-4.7-flashx) | Z.ai | Text | $0.07 in / $0.40 out per 1M tokens |
| [GLM-5](https://infro.io/models/zai/glm-5) | Z.ai | Text | $1.00 in / $3.20 out per 1M tokens |
| [GLM-5.1](https://infro.io/models/zai/glm-5.1) | Z.ai | Text | $1.40 in / $4.40 out per 1M tokens |
| [GLM-5.2](https://infro.io/models/zai/glm-5.2) | Z.ai | Text | $1.40 in / $4.40 out per 1M tokens |
| [GLM-5.3](https://infro.io/models/zai/glm-5.3) | Z.ai | Text | $1.40 in / $4.40 out per 1M tokens |
| [GLM-5.3 Flash](https://infro.io/models/zai/glm-5.3-flash) | Z.ai | Text | $0.15 in / $0.50 out per 1M tokens |
| [GLM-5.3 FlashX](https://infro.io/models/zai/glm-5.3-flashx) | Z.ai | Text | $0.37 in / $1.25 out per 1M tokens |
| [HappyHorse 1.0](https://infro.io/models/alibaba/happyhorse-1.0) | Alibaba | Video | $0.099 per second |
| [HappyHorse 1.1](https://infro.io/models/alibaba/happyhorse-1.1) | Alibaba | Video | $0.14 per second |
| [Wan 2.6](https://infro.io/models/alibaba/wan-2.6) | Alibaba | Video | $0.08 per second |
| [Wan 2.7](https://infro.io/models/alibaba/wan-2.7) | Alibaba | Video | $0.10 per second |
| [Wan 3.0](https://infro.io/models/alibaba/wan-3.0) | Alibaba | Video | $0.10 per second |
| [Wan 3.0 Prime](https://infro.io/models/alibaba/wan-3.0-prime) | Alibaba | Video | $0.14 per second |
| [FLUX 3](https://infro.io/models/bfl/flux-3) | Black Forest Labs | Video | $0.17 per second |
| [OmniHuman](https://infro.io/models/bytedance/omnihuman) | ByteDance | Video | $0.14 per second |
| [OmniHuman 1.5](https://infro.io/models/bytedance/omnihuman-1.5) | ByteDance | Video | $0.12 per second |
| [Seedance 1.0 Pro](https://infro.io/models/bytedance/seedance-1.0-pro) | ByteDance | Video | $0.052 per second |
| [Seedance 1.0 Pro Fast](https://infro.io/models/bytedance/seedance-1.0-pro-fast) | ByteDance | Video | $0.02 per second |
| [Seedance 1.5 Pro](https://infro.io/models/bytedance/seedance-1.5-pro) | ByteDance | Video | $0.052 per second |
| [Seedance 2.0](https://infro.io/models/bytedance/seedance-2.0) | ByteDance | Video | $0.15 per second |
| [Seedance 2.0 Fast](https://infro.io/models/bytedance/seedance-2.0-fast) | ByteDance | Video | $0.12 per second |
| [Seedance 2.0 Mini](https://infro.io/models/bytedance/seedance-2.0-mini) | ByteDance | Video | $0.08 per second |
| [Seedance 2.5](https://infro.io/models/bytedance/seedance-2.5) | ByteDance | Video | $0.231 per second |
| [Gemini Omni Flash](https://infro.io/models/google/gemini-omni-flash) | Google | Video | $0.101 per second |
| [Veo 3.1](https://infro.io/models/google/veo-3.1) | Google | Video | $0.40 per second |
| [Veo 3.1 Fast](https://infro.io/models/google/veo-3.1-fast) | Google | Video | $0.10 per second |
| [Veo 3.1 Lite](https://infro.io/models/google/veo-3.1-lite) | Google | Video | $0.05 per second |
| [HeyGen Video 1](https://infro.io/models/heygen/heygen-video-1) | HeyGen | Video | $0.02 per second |
| [Kling 3.0](https://infro.io/models/kuaishou/kling-v3) | Kuaishou | Video | $0.084 per second |
| [Kling 3.0 Turbo](https://infro.io/models/kuaishou/kling-v3-turbo) | Kuaishou | Video | $0.112 per second |
| [Kling AI Avatar v2 Pro](https://infro.io/models/kuaishou/kling-avatar-v2-pro) | Kuaishou | Video | $0.115 per second |
| [Kling Lip-Sync](https://infro.io/models/kuaishou/kling-lipsync) | Kuaishou | Video | $0.014 per second |
| [Kling O1](https://infro.io/models/kuaishou/kling-o1) | Kuaishou | Video | $0.112 per second |
| [Kling O3](https://infro.io/models/kuaishou/kling-o3) | Kuaishou | Video | $0.084 per second |
| [Ray 3.2](https://infro.io/models/luma/ray-3.2) | Luma | Video | $0.06 per second |
| [Magnific Creative Video Upscaler](https://infro.io/models/magnific/video-upscaler-creative) | Magnific | Video | $0.168 per second |
| [Hailuo 2.3](https://infro.io/models/minimax/hailuo-2.3) | MiniMax | Video | $0.082 per second |
| [MiniMax H3](https://infro.io/models/minimax/hailuo-03) | MiniMax | Video | $0.08 per second |
| [MiniMax H3 Max](https://infro.io/models/minimax/h3-max) | MiniMax | Video | $0.08 per second |
| [MiniMax H3 Max Turbo](https://infro.io/models/minimax/h3-max-turbo) | MiniMax | Video | $0.04 per second |
| [PixVerse C1](https://infro.io/models/pixverse/pixverse-c1) | PixVerse | Video | $0.05 per second |
| [PixVerse V6](https://infro.io/models/pixverse/pixverse-v6) | PixVerse | Video | $0.045 per second |
| [Runway Gen-4 Turbo](https://infro.io/models/runway/gen-4-turbo) | Runway | Video | $0.05 per second |
| [Runway Gen-4.5](https://infro.io/models/runway/gen-4.5) | Runway | Video | $0.12 per second |
| [Lipsync 2](https://infro.io/models/sync/lipsync-2) | Sync | Video | $0.05 per second |
| [Lipsync 2 Pro](https://infro.io/models/sync/lipsync-2-pro) | Sync | Video | $0.083 per second |
| [React 1](https://infro.io/models/sync/react-1) | Sync | Video | $0.167 per second |
| [Sync 3](https://infro.io/models/sync/sync-3) | Sync | Video | $0.134 per second |
| [Topaz Video Upscale](https://infro.io/models/topaz/video-upscale) | Topaz Labs | Video | $0.01 per second |
| [Grok Imagine 1.5](https://infro.io/models/xai/grok-imagine-video-1.5) | xAI | Video | $0.08 per second |
| [Grok Imagine Video](https://infro.io/models/xai/grok-imagine-video) | xAI | Video | $0.05 per second |
| [Grok Imagine Video 1.5 Lite](https://infro.io/models/xai/grok-imagine-video-1.5-lite) | xAI | Video | $0.02 per second |

## Choosing a model

There is no single best model — pick by workload, and let the gateway handle the rest. A rough map:

| Tier | Try first | Good for |
| --- | --- | --- |
| Flagship | `openai/gpt-5.6-sol`, `anthropic/claude-opus-5`, `google/gemini-3.1-pro` | Hard reasoning, complex agents, high-stakes generation where quality dominates cost |
| Fast | `openai/gpt-5.6-luna`, `anthropic/claude-haiku-4.5`, `google/gemini-3.7-flash` | Classification, extraction, summarization, latency-sensitive and high-volume paths |
| Open-weight | `deepseek/deepseek-v4-flash`, `qwen/qwen3-coder`, `moonshot/kimi-k2.6` | Workloads where you want a choice of hosts, or to run the model yourself; evaluate quality on your own tasks before moving traffic |

You don't have to commit to one. A [route](https://infro.io/docs/routes) can spread a model across the provider accounts you connect, and [fallbacks](https://infro.io/docs/features/fallbacks) let you chain models — a common pattern is a flagship primary with an open-weight fallback, so an outage degrades quality instead of availability. Per-request `fallbacks` apply when `model` is a model ID; when `model` names a route, the route's own targets decide failover and `fallbacks` is ignored.

## Deprecation policy

Catalog models are deprecated with at least 30 days notice, announced by email and in the console. During the notice window the model serves normally. Whether a model stays available at all is ultimately up to the provider whose account you connect.

After retirement, the old ID becomes an alias for its designated successor — existing code keeps working with no `404`. Retired IDs drop out of `GET /v1/models`, but aliases keep resolving indefinitely.

> **Note:** Aliased requests are served and estimated as the successor model, and the response `model` field always reports the model that actually served. Log it if you need to detect when an alias kicks in.