google/gemini-2.5-pro
Google's flagship long-context model. 1M-token context with strong reasoning, coding, and vision. Competitive with top-tier models on GPQA, MATH, and SWE-bench at significantly lower cost.
Fonte: gemini_x0.5 · Verificado em 2026-07-21
Leitura de cache $0.0625/M · Gravação de cache —/M
| Faixa | Entrada | Leitura de cache | Gravação de cache | Saída |
|---|---|---|---|---|
Você pode usar qualquer ID em chamadas de API.
google/gemini-2.5-proYou can use these names directly in the request model field.
Substitua o placeholder ONEHOP_KEY pela sua API key. Criar →
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="google/gemini-2.5-pro",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)| Standard ≤200K |
| $0.625 |
| $0.0625 |
| — |
| $5 |
| Standard >200K | $1.25 | $0.125 | — | $7.5 |
6.543 requisições nos últimos 30 dias