---
title: "FitaLabs Gateway — Model Configuration"
description: "Documentation: FitaLabs Gateway — Model Configuration"
type: reference
tags: [infra, gateway, modelos, deepseek, mimo, anthropic]
timestamp: 2026-07-06
---

# FitaLabs Gateway — Model Configuration

Claude model mapping to real backends (MiMo Token Plan, DeepSeek API).

## Mapping Table

| ant_alias | model_id | display_name | provider | api_base | image |
|-----------|----------|-------------|----------|----------|-------|
| `claude-haiku-4-7[1m]` | `deepseek-v4-flash` | Haiku Seek Flash | DeepSeek | `api.deepseek.com/anthropic` | ❌ |
| `claude-sonnet-4-6[1m]` | `mimo-v2.5` | Monnet v2.5 | MiMo | `token-plan-sgp.xiaomimimo.com/anthropic` | ✅ |
| `claude-opus-4-6[1m]` | `mimo-v2.5-pro` | Mopus v2.5 Pro | MiMo | `token-plan-sgp.xiaomimimo.com/anthropic` | ❌ |
| `claude-opus-4.7[1m]` | `deepseek-v4-pro` | Dopus Pro | DeepSeek | `api.deepseek.com/anthropic` | ❌ |

## Provider-Native Models (Agent SDK)

| model_id | display_name | provider |
|----------|-------------|----------|
| `deepseek-v4-flash[1m]` | DeepSeek V4 Flash 1M | DeepSeek |
| `mimo-v2.5[1m]` | MiMo v2.5 1M | MiMo |
| `mimo-v2.5-pro[1m]` | MiMo v2.5 Pro 1M | MiMo |
| `deepseek-v4-pro[1m]` | DeepSeek V4 Pro 1M | DeepSeek |

## Audio

| model_id | provider | api_base |
|----------|----------|----------|
| `tts-1` | MiMo TTS | `token-plan-sgp.xiaomimimo.com/v1` |
| `whisper-1` | MiMo ASR | `token-plan-sgp.xiaomimimo.com/v1` |

## [1m] and non-[1m] Variants

Each Claude alias has TWO entries in config:
- `claude-sonnet-4-6[1m]` — 1M context window
- `claude-sonnet-4-6` — normal context

Desktop offers a 1M context toggle. When enabled, it sends `model[1m]`.
When disabled, it sends `model` without suffix. Both must exist in `model_list`.

## Capabilities per Tier

```python
# Derived from model_id prefix
if "haiku" in model_id:
    effort_levels = {"low", "medium"}
elif "sonnet" in model_id:
    effort_levels = {"low", "medium", "high"}
else:  # opus
    effort_levels = {"low", "medium", "high", "xhigh", "max"}
```

Desktop uses the prefix (`claude-haiku-*`, `claude-sonnet-*`, `claude-opus-*`)
to determine which effort levels to show in the selector.

Other capabilities derived from `model_info`:
- `supports_vision` → `image_input`, `pdf_input`
- `supports_1m` → `compact_20260112`

## Config YAML (exemplo)

```yaml
model_list:
  - model_name: claude-sonnet-4-6[1m]
    litellm_params:
      model: xiaomi_mimo/mimo-v2.5[1m]
      api_base: https://token-plan-sgp.xiaomimimo.com/anthropic
      rpm: 30
    model_info:
      mode: chat
      supports_vision: true
      supports_function_calling: true
      supports_1m: true
```

## Anthropic Format in /v1/models

Middleware in `gateway.py` intercepts the proxy response and translates:

```json
{
  "data": [{
    "id": "claude-sonnet-4-6[1m]",
    "type": "model",
    "display_name": "Monnet v2.5",
    "created_at": "2025-01-01T00:00:00Z",
    "capabilities": {
      "thinking": {"supported": true, "types": {"adaptive": true, "enabled": true}},
      "effort": {"low": true, "medium": true, "high": true, "max": false, "xhigh": false},
      "image_input": {"supported": true},
      "context_management": {"compact_20260112": {"supported": true}}
    }
  }]
}
```

## References
- [[fitalabs-gateway-1p-jornada]] — overview
- [[litellm-proxy-migration]] — proxy migration
- [[fitalabs-gateway-modelos]] — original routing