MiniMax model
minimax-m2.7
MiniMax M2.7 API
Agentic model for coding, debugging, document generation, and long-running tool workflows. Coding agents, debugging, document generation, and long-running tool workflows.
Gonka24 base price
$0.018
input / 1M tokens
$0.072
output / 1M tokens
Base public rate before account-specific pricing. Actual paid-provider cost floors can apply.
Custom context
200,000 tokens
Rounded down from the Gonka24 routing limit; this is not the vendor's headline limit.
Maximum output
16,000 tokens
Rounded down from the gateway default ceiling for this model.
Cached input
Account-specific
No fixed public cache rate; virtual cache pricing is configured per account.
Last verified
31 Aug 2026
Catalog price source updated 2026-06-29.
Capabilities
Streaming
Supported
Set stream: true for Server-Sent Events.
Tool calling
Supported
OpenAI-style tools and tool_choice; behavior can vary by selected route.
Reasoning
Route-dependent
Reasoning output is preserved when the selected upstream returns it. A stable model-specific effort mapping is not advertised.
Text output
Supported
Chat and text completions.
Image generation
Not supported
Gonka24 does not expose an image-generation endpoint for this model.
Input modalities: text. Output modality: text only. Tool and reasoning behavior can vary when traffic is routed to different compatible upstreams.
Supported request parameters
These fields are accepted by the Gonka24 OpenAI-compatible chat gateway. A selected upstream may ignore sampling controls it does not implement.
modelmessagesstreamstream_optionsmax_tokensmax_completion_tokenstemperaturetop_pstopfrequency_penaltypresence_penaltyresponse_formatseedtoolstool_choiceusercURL example
OpenAI-compatible chat completions
curl https://api.gonka24.com/v1/chat/completions \
-H "Authorization: Bearer $GONKA24_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m2.7",
"messages": [{"role": "user", "content": "Explain why the sky is blue."}],
"stream": true,
"max_tokens": 512
}'