MiniMax M2.5 Lightning
MiniMax-M2.5-lightningPricing
List prices at MiniMax, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.30 | $2.40 | |
| Cached input 90% off input | $0.03 | 90% off input | |
| Cache write, 5 minutes | $0.375 |
What it costs a month
At MiniMax list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$246
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$166
- Coding agent1,000 requests a day, 40K in / 2K out, cached$277
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,296
Where to run it
1 host serve MiniMax M2.5 Lightning. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
MiniMaxLab API MiniMax-M2.5-lightning | $0.30 / $2.40 | MiniMax-M2.5-lightning |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt caching
- Open weights
- License: Apache-2.0Runtimes: SGLang, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than MiniMax.
Smaller MiniMax models
No cheaper MiniMax model keeps its key capabilities.
Other frontier labs
- 44% less
- 76% less
- 76% less
- 68% less
Open-weight picks
- 4% less
- 17% less
- 23% less
- 42% less
Model line
Newer and older versions, at each lab's own price.
- UndatedMiniMax M2.5 LightningLatest$0.30 / $2.40
- UndatedMiniMax M2.1 Lightning$0.30 / $2.40
Call it
Using MiniMax's API.
from litellm import completion
response = completion(
model="minimax/MiniMax-M2.5-lightning",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does MiniMax M2.5 Lightning cost?
On MiniMax, MiniMax M2.5 Lightning costs $0.30 per million input tokens and $2.40 per million output tokens. Cached input costs $0.03 per million tokens.
Which APIs offer MiniMax M2.5 Lightning?
MiniMax M2.5 Lightning runs on 1 API: MiniMax.
What is MiniMax M2.5 Lightning's context window?
1M tokens, with up to 8K tokens in one reply.
Is MiniMax M2.5 Lightning being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of MiniMax M2.5 Lightning?
No. MiniMax M2.5 Lightning is the newest model in its line.
What are cheaper alternatives to MiniMax M2.5 Lightning?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (44% less), Claude Haiku 5.5 on Anthropic (76% less) and DeepSeek V4 Pro on CLF AI Gateway (4% less). Savings are on a mix of 3 input tokens to 1 output token.
What is MiniMax M2.5 Lightning's API model id?
Use MiniMax-M2.5-lightning with MiniMax.
Sources
Raw catalog entry for MiniMax-M2.5-lightning on MiniMax
{
"input_cost_per_token": 3e-7,
"output_cost_per_token": 0.0000024,
"cache_read_input_token_cost": 3e-8,
"cache_creation_input_token_cost": 3.75e-7,
"litellm_provider": "minimax",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_system_messages": true,
"max_input_tokens": 1000000,
"max_output_tokens": 8192
}