---
title: Models & pricing
description: The Clipia AI Gateway model catalog (GET /v1/models) and prices in rubles per 1M tokens — Claude, GPT, Gemini, DeepSeek, Grok.
---

Clipia AI Gateway provides access to flagship language models under one contract. `GET /v1/models` returns the catalog in an OpenAI-compatible format; the prices below are in rubles per 1M tokens, billed separately for input (prompt) and output (the model's response).

## Catalog (`GET /v1/models`)

<Method name="GET" path="/v1/models" />

<Tabs items={['Python', 'Node.js', 'cURL']}>
<Tab value="Python">

```python
models = client.models.list()
for m in models.data:
    print(m.id)
```

</Tab>
<Tab value="Node.js">

```ts
const models = await client.models.list();
for (const m of models.data) console.log(m.id);
```

</Tab>
<Tab value="cURL">

```bash
curl https://api.clipia.ai/v1/models \
  -H "Authorization: Bearer $CLIPIA_API_KEY"
```

</Tab>
</Tabs>

The response is a `data` array in OpenAI-compatible form. Each item carries an `id` (the string for the `model` field), context length, supported parameters and per-token rates:

```json
{
  "object": "list",
  "data": [
    {
      "id": "gpt-5.6-sol",
      "object": "model",
      "name": "GPT-5.6 Sol",
      "created": 1783555200,
      "owned_by": "openai",
      "context_length": 400000,
      "architecture": {
        "modality": "text+image->text",
        "input_modalities": ["text", "image"],
        "output_modalities": ["text"],
        "tokenizer": "GPT"
      },
      "pricing": { "prompt": "0.00000499875", "completion": "0.00003" },
      "supported_parameters": [
        "tools", "tool_choice", "response_format",
        "temperature", "top_p", "max_tokens", "stop", "seed"
      ]
    }
  ]
}
```

In `pricing`, values are per **single token** (prompt / response); the human-readable per-1M-token prices are in the table below. Clients use `supported_parameters` to detect which features a model supports (`tools`, `response_format`, etc.).

## Pricing

Billing is per token, separately for input and output. Charges are taken in credits from the account balance; the prices below are shown in US dollars for clarity (1M = 1,000,000 tokens).

| Model | `model` | Input, $/1M | Output, $/1M |
|-------|---------|------------:|-------------:|
| Claude Fable 5 | `claude-fable-5` | 10 | 50 |
| GPT-5.6 Sol | `gpt-5.6-sol` | 5 | 30 |
| GPT-5.6 Terra | `gpt-5.6-terra` | 2.50 | 15 |
| GPT-5.6 Luna | `gpt-5.6-luna` | 1 | 6 |
| Claude Opus 5 | `claude-opus-5` | 5 | 25 |
| Claude Sonnet 4.6 | `claude-sonnet-4-6` | 3 | 15 |
| Gemini 3.6 Flash | `gemini-3.6-flash` | 1.50 | 7.50 |
| Grok 4.5 | `grok-4.5` | 2 | 6 |
| DeepSeek V4 Pro | `deepseek-v4-pro` | 0.57 | 1.13 |
| Gemini 2.5 Flash | `gemini-2.5-flash` | 0.39 | 3.25 |
| DeepSeek V4 Flash | `deepseek-v4-flash` | 0.12 | 0.23 |
| GPT-5 nano | `gpt-5.4-nano` | 0.06 | 0.52 |
| GPT-5.5 (legacy slug) | `gpt-5.5` | 5 | 30 |
| Grok 4.3 (legacy slug) | `grok-4.3` | 1.63 | 3.25 |

<Callout type="info" title="Billed in credits">
Billing is in credits: every response carries `usage.cost` (the request cost in credits), and the exact cost of an already-completed request is returned by [`GET /v1/generation`](/en/docs/llm-gateway/account). The ruble prices are the public retail rate; top up your balance in the clipia.ai account area.
</Callout>

<Callout type="warn" title="Verify against the live catalog">
The model list and rates are updated periodically. Always take identifiers (`model`) and current prices from the live `GET /v1/models` — that is the source of truth. The values in the table are accurate as of publication.
</Callout>

## How to choose a model

- **Flagships — hard tasks.** `claude-fable-5`, `gpt-5.6-sol` and `claude-opus-5` for reasoning, code, agents and long context, where quality matters more than price.
- **Quality/price balance.** `gpt-5.6-terra`, `claude-sonnet-4-6`, `gemini-3.6-flash`, `grok-4.5` — solid all-rounders for most product scenarios.
- **Volume and low cost.** `gpt-5.6-luna`, `deepseek-v4-pro`, `gemini-2.5-flash`, `deepseek-v4-flash`, `gpt-5.4-nano` — for classification, data extraction, bulk processing and draft answers where a low per-token cost matters.

Start with a mid-tier model, measure quality on your own data, and move up to a flagship or down to a cheaper option as needed — you only change the `model` string.

## Model deep dives

Specs, limits, request examples and cost math for a specific model:

- [Claude Opus 5](/en/claude-opus-5) — 1,000,000-token context, for deep analysis, code and agent workloads.
- [Gemini 3.6 Flash](/en/gemini-3-6-flash) — 1,048,576-token context, multimodal input and a low per-request cost.