MiniMax M2.5 - ByteSpike

Vendor: MiniMax Model ID: minimax-m2.5 Capability: 128K context · tool use · streaming · CJK-native Pricing: per-token, mid tier (live rate) MiniMax M2.5 was MiniMax’s prior production model. It earned a reputation for creative writing in Chinese — character voice consistency, dialogue, narrative flow — at a price tier where most competitors flatten tone. Still production-capable for that niche. For new general-purpose work, prefer MiniMax M2.7.

Request

curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "minimax-m2.5",
    "messages": [{"role": "user", "content": "续写这段对话，保持角色性格。"}]
  }'

Body parameters

Field	Type	Required	Default	Notes
`model`	string	yes	—	`minimax-m2.5`
`messages`	array	yes	—	CJK accepted natively.
`max_tokens`	integer	no	model max	Max: 8192.
`temperature`	number	no	1.0	Creative writing benefits from 1.0–1.3.
`tools`	array	no	—	Function calling supported.
`stream`	boolean	no	false	SSE streaming.

Response

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "minimax-m2.5",
  "choices": [{"index": 0, "message": {"role": "assistant", "content": "..."}, "finish_reason": "stop"}],
  "usage": {"prompt_tokens": 287, "completion_tokens": 612, "total_tokens": 899}
}

Code examples

curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model": "minimax-m2.5", "messages": [{"role": "user", "content": "续写对话"}]}'

Streaming + caching

"stream": true for SSE. Automatic prompt caching.

Errors

Code	Trigger	Billed?
400 / 401 / 402 / 422 / 429	Standard	No
5xx	Upstream	No (auto-retry)

When to use

Existing creative-writing pipelines validated against this version.
For new work, prefer MiniMax M2.7.
For Chinese general-purpose flagship, see Kimi K2.6 or GLM-5.1.

Limits

Limit	Value
Context window	128K tokens
Max output	8192 tokens
Supports tool use	Yes
Supports vision	No
Supports streaming	Yes
Supports prompt caching	Automatic

GLM-5.1 MiniMax M2.7

​Request

​Body parameters

​Response

​Code examples

​Streaming + caching

​Errors

​When to use

​Limits