# Models

## Fugu

Fugu balances strong performance with low latency, making it the ideal default for everyday work. Fugu will route to the best model based on the task at hand. You can also opt specific agents out of its pool to meet data, privacy, and compliance constraints.

## Fugu Ultra

Fugu Ultra coordinates a deeper pool of expert agents to maximize answer quality on hard, high-stakes problems. Fugu Ultra focuses on maximizing performance, for a higher cost. It routes between one to three agents, depending on the problem.

## Benchmark comparison

Reported benchmark scores across Fugu and other frontier models.

| Benchmark | Fugu-Ultra | Fugu | Opus 4.8 | Gemini 3.1 | GPT-5.5 |
| --- | --- | --- | --- | --- | --- |
| SWE Bench Pro | **73.7** | 59.0 | 69.2 | 54.2 | 58.6 |
| Terminal Bench 2.1 | **82.1** | 80.2 | 74.6 | 70.3 | 78.2 |
| LiveCodeBench | **93.2** | 92.9 | 87.8 | 88.5 | 85.3 |
| LiveCodeBench Pro | **90.8** | 87.8 | 84.8 | 82.9 | 88.4 |
| Humanity’s Last Exam | **50.0** | 47.2 | 49.8 | 44.4 | 41.4 |
| CharXiv Reasoning | **86.6** | 85.1 | 84.2 | 83.3 | 84.1 |
| GPQA Diamond | **95.5** | **95.5** | 92.0 | 94.3 | 93.6 |
| SciCode | 58.7 | **60.1** | 53.5 | 58.9 | 56.1 |
| τ3 Banking | 20.6 | **21.7** | 20.6 | 8.4 | 20.6 |
| Long Context Reasoning | 73.3 | **74.7** | 67.7 | 72.7 | 74.3 |
| MRCRv2 | 93.6 | 86.6 | 87.9 | 84.9 | **94.8** |
| CTI-REALM | 69.4 | 67.5 | **69.6** | 56.0 | 67.3 |

## Example Usage

These examples use the OpenAI-compatible Responses API. Set your environment variables once, then copy and run the Python or cURL example you need.

### Python

```python
# pip install openai
import os
from openai import OpenAI

base_url = os.environ["FUGU_BASE_URL"].rstrip("/")
if not base_url.endswith("/v1"):
    base_url = f"{base_url}/v1"

client = OpenAI(
    api_key=os.environ["FUGU_API_KEY"],
    base_url=base_url,
)

with client.responses.stream(
    model="fugu-ultra",
    input="Explain why streaming is useful in three short bullets.",
) as stream:
    for event in stream:
        if event.type == "response.output_text.delta":
            print(event.delta, end="", flush=True)

# Full response object assembled from the stream.
    response = stream.get_final_response()

print()
print(response)
```

## Supported endpoints

Fugu currently supports the OpenAI-compatible Chat Completions, Responses, and Models APIs. For generation requests, we strongly recommend using the Responses API, for better performance.

### Responses API

Use `/v1/responses` when you want the Responses API shape, especially for tool use, multimodal input, and proper reasoning or function calls management.

### Supported request fields

| Field | Type | Description |
| --- | --- | --- |
| `model` | `string` | Required. Model ID to use, such as `fugu` or`fugu-ultra`. |
| `input` | `string | array` | Required. A string or an array of Responses-style input items. A string input is treated as a user message. |
| `instructions` | `string` | System / developer message passed to the model. |
| `metadata` | `object` | Arbitrary key-value pairs attached to the request. |
| `stream` | `boolean` | Stream the response. |
| `max_output_tokens` | `number` | Maximum number of tokens to generate. Note for fugu-ultra, this is applied only to the final model response, orchestrator model still uses maximum token limit. |
| `reasoning` | `object` | Reasoning controls with an `effort` value of`high`, `xhigh`, or `max`.`xhigh` and `max` are aliases of the same reasoning effort. Default is `xhigh` for fugu-ultra,`high` for fugu. |
| `tools` | `array` | Tool definitions the model may call. |
| `tool_choice` | `string | object` | Controls whether and which tool is called. |
| `text.format` | `object` | Structured output with `text`,`json_object`, or `json_schema`. |
| `temperature` | `number` | Accepted but ignored. |
| `parallel_tool_calls` | `boolean` | Accepted but ignored. Set to True on the server side for models that support it. |
| `previous_response_id` | `string` | Not accepted. Send the full conversation history directly in`input` instead. |

### Chat Completions

Use `/v1/chat/completions` when you want the OpenAI Chat Completions API shape.