> ## Documentation Index
> Fetch the complete documentation index at: https://docs.chipipay.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Models & Pricing

> 8 AI models across 3 providers. Pay per token with USDC credits.

## Available models

All prices are per 1 million tokens (USD). Cost = input tokens + output tokens at the rates below.

> [!NOTE]
>
> Pricing is always available live at [`GET /ai/models`](https://api.chipipay.com/v1/ai/models).
> If there is ever a discrepancy between this page and the API response, the API is the source of truth.

| Model ID | Provider | Display Name | Input / 1M tokens | Output / 1M tokens | Best for |
| - | - | - | - | - | - |
| `gpt-4o-mini` | OpenAI | GPT-4o Mini | \$0.21 | \$0.84 | Cheapest. Simple tasks, high volume. |
| `gemini-flash` | Google | Gemini 2.5 Flash | \$0.42 | \$3.50 | Fast, good quality, low cost. |
| `gpt-4.1-mini` | OpenAI | GPT-4.1 Mini | \$0.56 | \$2.24 | Better reasoning at low cost. |
| `haiku` | Anthropic | Claude Haiku 4.5 | \$1.40 | \$7.00 | **Default.** Best reasoning-to-cost ratio. |
| `gemini-pro` | Google | Gemini 2.5 Pro | \$1.75 | \$14.00 | Strong reasoning. **2 RPM** free-tier limit. |
| `gpt-4.1` | OpenAI | GPT-4.1 | \$2.80 | \$11.20 | High quality, fast. |
| `gpt-4o` | OpenAI | GPT-4o | \$3.50 | \$14.00 | Multimodal, proven. |
| `sonnet` | Anthropic | Claude Sonnet 4.5 | \$4.20 | \$21.00 | Premium. Best quality, highest cost. |

> [!TIP]
>
> Start with `gpt-4o-mini` for prototyping (\$0.21/1M input). Switch to `haiku` or `sonnet` for production quality.

## Typical costs per call

| Use case | Model | Tokens | Cost |
| - | - | - | - |
| Short chat reply | `gpt-4o-mini` | \~500 | \~\$0.0003 |
| DeFi portfolio decision (`/think`) | `haiku` | \~880 | \~\$0.002 (measured 2026-10-03) |
| Detailed analysis | `sonnet` | \~1,000 | \~\$0.013 |
| Swap calldata builder | `/execute` | N/A | \$0.002 flat |
| Token prices | `/prices` | N/A | **Free** |
| Market signals | `/signals` | N/A | **Free** up to 100/mo per org, then \$0.0005/call |

Paying a `/think` per call over x402 instead of credits costs \$0.015 (see [DeFi Intelligence](/services/ai-api/defi-intelligence#pay-per-call-with-x402)).

If a provider is down for Chipi, its models answer `503 MODEL_UNAVAILABLE` and show `available: false` in `GET /ai/models` until it is back (see [When a model is unavailable](/services/ai-api/overview#when-a-model-is-unavailable)).

## Rate limits

| Model | Provider RPM | Max output tokens |
| - | - | - |
| `gpt-4o-mini` | 30,000 | 16,384 |
| `gpt-4.1-mini` | 10,000 | 16,384 |
| `gpt-4.1` | 10,000 | 32,768 |
| `gpt-4o` | 10,000 | 16,384 |
| `haiku` | 4,000 | 8,192 |
| `sonnet` | 1,000 | 8,192 |
| `gemini-flash` | 15 (free tier) | 8,192 |
| `gemini-pro` | 2 (free tier) | 8,192 |

Your org's API key also has a per-key rate limit (default: 1,000 RPM). The effective limit is the lower of the two.

> [!NOTE]
>
> Google Gemini models are on the free tier (low RPM). For production use at scale, prefer OpenAI or Anthropic models. `gemini-pro` in particular is rate-limited to **2 RPM** — fine for occasional reasoning calls, not production traffic.

## Credits

Buy credit packs by sending USDC on Starknet:

| Pack | Price |
| - | - |
| \$2 | 2 USDC |
| \$5 | 5 USDC |
| \$25 | 25 USDC |
| \$50 | 50 USDC |
| \$100 | 100 USDC |

Buy at [dashboard.chipipay.com/configure/billing](https://dashboard.chipipay.com). Credits are USD-denominated and deducted per API call. Check your balance in the dashboard billing tab.

## OpenAPI spec

The full API spec is available at [`/v1/openapi.json`](https://api.chipipay.com/v1/openapi.json) — filtered to AI endpoints only.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.