Back to Models
Deep Principle
hydrogen-1.0

Hydrogen 1.0

Deep Principle's Hydrogen 1.0 - 1M-token context, text only

1,000,000 tokens
Input: $0.9749/M
Output: $2.65/M

Specifications

Modalities

Input
text
Output
text

Max Output Tokens

131,072

Data policy

Prompt retention
Unknown: we could not confirm
Training
Unknown: not declared

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "hydrogen-1.0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Hydrogen 1.0 actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

**Answer: There are 3 r's in "strawberry."** **Step-by-step reasoning:** **Step 1: Spell out the word letter by letter.** s – t – r – a – w – b – e – r – r – y **Step 2: Assign a position to each letter.** | Position | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | |----------|---|---|---|---|---|---|---|---|---|----| | Letter | s | t | **r** | a | w | b | e | **r** | **r** | y | **Step 3: Identify each occurrence of 'r'.** - Position 3 → 'r' (1st occurrence) - Position 8 → 'r' (2nd occurrence) - Position 9 → 'r' (3rd occurrence) **Step 4: Count them.** 3 r's total. **Verification using word parts:** "strawberry" = "straw" + "berry" - "straw" (s-t-r-a-w) contains **1** 'r' - "berry" (b-e…
13.1s response

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

# What the error means ``` TypeError: Cannot read properties of undefined (reading 'map') ``` This says: you tried to read the property `map` off of something that is `undefined`. In your component, the only place `.map` is called is: ```js users.map(user => ...) ``` So **`users` is `undefined` when the component renders**. (The `renderWithHooks` line in the stack just tells you it happened during the render of a function component — that's React internal machinery, not a bug in itself.) # Why it happens — the usual causes 1. **The parent never passed the prop** ```jsx <UserList /> // users is undefined ``` 2. **The data is loaded asynchronously**, and the componen…
27.4s response

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

# Code Review ## Issues found **Correctness / robustness** 1. **Bare `except:`** — catches *everything*, including `KeyboardInterrupt` and `SystemExit`. This makes the function impossible to interrupt during a hang and hides real bugs (e.g., a `KeyError` from malformed data will be silently retried as if it were a network error). 2. **`item["active"] == True`** — (a) PEP 8 violation (E712), (b) redundant, (c) fails on truthy-but-not-`bool` values, and (d) `item["active"]` raises `KeyError` if the key is missing (which the bare `except` then swallows). Use `item.get("active")`. 3. **Ambiguous failure signal** — returning `[]` both for "all retries failed" and for "the request succeeded but…
43.9s response

Compare these answers side by side with other models →

Frequently asked questions

How much does the Hydrogen 1.0 API cost?
On FastMetal, Hydrogen 1.0 is billed per token: $0.9749 per 1M input tokens and $2.65 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Hydrogen 1.0 with the OpenAI SDK?
Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "hydrogen-1.0" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Hydrogen 1.0?
1,000,000 tokens, shared between the prompt and the response.
What do I need to try Hydrogen 1.0?
Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try Hydrogen 1.0 right now

Hydrogen 1.0 is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.