---
title: "Cost Models"
description: "Provider Model Input (per 1K tokens) Output (per 1K tokens) Anthropic claude 3 opus $0.015 $0.075 Anthropic claude 3 sonnet $0.003 $0.015 Anthropic claude 3 haiku $0.00025 $0.00125 OpenAI gpt 4 $0.03 $0.06 OpenAI gpt 4 t"
resource: https://www.aiagents.nexus/docs/manual/cost-control/cost-models
generated: { by: "process:nexus-agent-assets", at: 2026-09-07T09:13:03Z }
status: stable
---

# Cost Models

## Supported Models

| Provider | Model | Input (per 1K tokens) | Output (per 1K tokens) |
|----------|-------|-----------------------|------------------------|
| Anthropic | claude-3-opus | $0.015 | $0.075 |
| Anthropic | claude-3-sonnet | $0.003 | $0.015 |
| Anthropic | claude-3-haiku | $0.00025 | $0.00125 |
| OpenAI | gpt-4 | $0.03 | $0.06 |
| OpenAI | gpt-4-turbo | $0.01 | $0.03 |
| OpenAI | gpt-3.5-turbo | $0.0005 | $0.0015 |

## Custom Cost Models

```yaml
cost:
  models:
    my-local-llama:
      inputCostPer1k: 0.001
      outputCostPer1k: 0.002
```

## Cost Optimization Tips

1. Use cheaper models for simple tasks
2. Cache responses
3. Set per-agent model preferences
4. Use the broker for skill-based routing