Horizon Beta by OpenRouter — Pricing, Benchmarks & Real Outputs
Share
Loading...
Compare Horizon Beta
Alternatives to Horizon Beta
Horizon Beta's competitors have been quietly putting in work.
Horizon Beta's competitors have been quietly putting in work.
Horizon Beta's competitors have been quietly putting in work.
Revealed as GPT-5This is a cloaked model provided to the community to gather feedback. This is an improved version of Horizon Alpha. Note: It's free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"openrouter/horizon-beta" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
41 outputs from Horizon Beta
Revealed as GPT-5This is a cloaked model provided to the community to gather feedback. This is an improved version of Horizon Alpha. Note: It's free to use during this testing period, and prompts and completions are logged by the model creator for feedback and training.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"openrouter/horizon-beta" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
41 outputs from Horizon Beta