# Dagon Inference models and prices

Build snapshot at price version 2026-11-02.2, as of 2026-11-02. Prices follow the providers and may have changed since; the live prices and current price version are at https://inference.dagon.so/v1/models (no key needed). Prices are USD per 1M tokens at the cheapest provider serving each model plus the 10% markup (15% in total on private zkAPI leases). A request that falls back to another provider is billed at that provider's rate plus the markup; its signed receipt names the provider. Billing is per request in whole micro-USD, rounded up once.

Live catalog: https://inference.dagon.so/v1/models · JSON: https://inference.dagon.so/models.json · OpenAPI: https://inference.dagon.so/openapi.json

| Model | Model id | Input | Cached input | Output | Context | Max output | Input types | Providers | Endpoints |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [Abliterated Large v2](https://inference.dagon.so/models/abliterated-model-large-v2) | `abliterated-model-large-v2` | $1.10 | $0.165 | $2.20 | 1,048,576 | 65,536 | text | abliteration.ai, Refuseless, Experiential Labs | /v1/chat/completions, /v1/responses, /v1/messages |
| [DeepSeek V4.1 Flash Abliterated](https://inference.dagon.so/models/deepseek-v4.1-flash-abliterated) | `deepseek-v4.1-flash-abliterated` | $0.132 | $0.0275 | $0.495 | 1,048,576 | 65,536 | text | Refuseless, Experiential Labs | /v1/chat/completions, /v1/responses |
| [GLM-5.3 Flash Abliterated](https://inference.dagon.so/models/glm-5.3-flash-abliterated) | `glm-5.3-flash-abliterated` | $0.132 | $0.044 | $0.55 | 1,048,576 | 65,536 | text | Refuseless, Experiential Labs | /v1/chat/completions, /v1/responses |
| [Abliterated Large Flash](https://inference.dagon.so/models/abliterated-model-large-flash) | `abliterated-model-large-flash` | $1.10 | $0.11 | $2.20 | 1,048,576 | 65,536 | text, image | abliteration.ai | /v1/chat/completions, /v1/responses, /v1/messages |
| [Abliterated Model](https://inference.dagon.so/models/abliterated-model) | `abliterated-model` | $1.10 | $0.11 | $3.30 | 262,144 | 65,536 | text, image | abliteration.ai | /v1/chat/completions, /v1/responses, /v1/messages |

Deprecated, still accepted: `abliterated-model-large` ($3.30 input, $5.50 output).

## Call a model

OpenAI SDKs: base URL `https://inference.dagon.so/v1`. Anthropic SDKs: base URL `https://inference.dagon.so`. Auth: `Authorization: Bearer <key>`.

```sh
curl https://inference.dagon.so/v1/chat/completions \
  -H "Authorization: Bearer $DAGON_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "abliterated-model-large-v2", "messages": [{"role": "user", "content": "Hello"}]}'
```