We're giving away $10 to early supporters — follow us on X & join our Telegram group. Join Telegram Models Minimax MiniMax M2.7 HighSpeed Official minimax/minimax-m2.7-highspeed
Call minimax/minimax-m2.7-highspeed through the OneHop AI Gateway. One URL connects you to every model.
205K context Reasoning Tool calling Coding Prompt cache
MiniMax M2.7 HighSpeed · MiniMax | OneHop
Input Official $0.600 / M tokens $0.060 / M tokens Save 90%
Output Official $2.40 / M tokens $0.240 / M tokens Save 90%
Cache read $0.006/M · Cache write $—/M
Protocols OpenAI Chat Completions Status: Available: Streaminghttps://api.onehop.ai/v1 OpenAI Responses Status: Available: Streaminghttps://api.onehop.ai/v1 Anthropic Messages Status: Available: Streaminghttps://api.onehop.ai/anthropic Google Vertex AI Status: Not supported— OpenAI Images Status: Not supported— OpenAI Sora Status: Not supported— Try it in the chat playground Call IDs Use either ID to call this model via the API.
OneHop name minimax/minimax-m2.7-highspeedCopy
Official ID MiniMax-M2.7-highspeedCopy
Try it Replace the ONEHOP_KEY placeholder with your API key. Create one →
OpenAI Chat Completions OpenAI Responses Anthropic Messages
OpenAI · Python OpenAI · cURL OpenAI · TypeScript Copy
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="minimax/minimax-m2.7-highspeed",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)base_url: https://api.onehop.ai/v1
Total usage 1.43M
P50 first-token latency Insufficient data (2 requests)
Avg throughput Insufficient data (2 requests)
Success rate 99.2%