Fugu Ultra V2.0
fugu-ultra-v2-0Pricing
List prices at EmpirioLabs AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $5.00 | $30.00 | |
| Cached input 90% off input | $0.50 | 90% off input | |
| Prompts over 272K tokens | $10.00 | $45.00 |
What it costs a month
At EmpirioLabs AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$3,345
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$2,400
- Coding agent1,000 requests a day, 40K in / 2K out, cached$4,020
- Overnight batch20,000 requests a day, 4K in / 0.4K out$19,200
Where to run it
1 host serve Fugu Ultra V2.0. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
EmpirioLabs AICloud fugu-ultra-v2-0 | $5.00 / $30.00 | fugu-ultra-v2-0 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Features
- Prompt cachingBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than EmpirioLabs AI.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 29% less
- 57% less
- 64% less
- 73% less
Open-weight picks
- 64% less
- 80% less
- 85% less
- 95% less
Model line
Newer and older versions, at each lab's own price.
- UndatedFugu Ultra V2.0Latest$5.00 / $30.00
- UndatedFugu Ultra V1.1$5.00 / $30.00
- UndatedFugu Ultra V1.0$7.50 / $45.00
Call it
Using EmpirioLabs AI's API.
from litellm import completion
response = completion(
model="empiriolabs/fugu-ultra-v2-0",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Fugu Ultra V2.0 cost?
On EmpirioLabs AI, Fugu Ultra V2.0 costs $5.00 per million input tokens and $30.00 per million output tokens. Cached input costs $0.50 per million tokens.
Which APIs offer Fugu Ultra V2.0?
Fugu Ultra V2.0 runs on 1 API: EmpirioLabs AI.
What is Fugu Ultra V2.0's context window?
1M tokens, with up to 131K tokens in one reply.
Is Fugu Ultra V2.0 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Fugu Ultra V2.0?
No. Fugu Ultra V2.0 is the newest model in its line.
What are cheaper alternatives to Fugu Ultra V2.0?
Models that cost less and keep most of what it can do: Claude Opus 5.5 on Anthropic (29% less), GPT-5.3 Codex on OpenAI (57% less) and Kimi K3.1 Pro on Databricks (64% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Fugu Ultra V2.0's API model id?
Use fugu-ultra-v2-0 with EmpirioLabs AI.
Sources
Raw catalog entry for fugu-ultra-v2-0 on EmpirioLabs AI
{
"litellm_provider": "empiriolabs",
"mode": "chat",
"max_input_tokens": 1000000,
"max_output_tokens": 131072,
"input_cost_per_token": 0.000005,
"output_cost_per_token": 0.00003,
"input_cost_per_token_above_272k_tokens": 0.00001,
"output_cost_per_token_above_272k_tokens": 0.000045,
"cache_read_input_token_cost_above_272k_tokens": 0.000001,
"cache_read_input_token_cost": 5e-7,
"supports_system_messages": true,
"supports_vision": true,
"supports_reasoning": true,
"supports_web_search": true,
"supports_prompt_caching": true,
"supports_function_calling": true,
"supports_response_schema": true,
"source": "https://empiriolabs.ai/models/fugu-ultra-v2-0"
}