MiniMax M3.1 Flash
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.
MiniMax-M3.1-FlashReleased 19 Oct 2026 (4 weeks ago)Pricing
List prices at MiniMax, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.15 | $0.60 | |
| Cached input 90% off input | $0.015 | 90% off input |
What it costs a month
At MiniMax list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$77.85
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$61.20
- Coding agent1,000 requests a day, 40K in / 2K out, cached$103
- Overnight batch20,000 requests a day, 4K in / 0.4K out$504
Where to run it
9 hosts serve MiniMax M3.1 Flash. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
MiniMaxLab API MiniMax-M3.1-Flash | $0.15 / $0.60 | MiniMax-M3.1-Flash | |
RefuselessCloud minimax-m3.1-flash | $0.05 / $0.25 −62% vs headline | minimax-m3.1-flash | |
EmpirioLabs AICloud minimax-m3-1-flash | $0.113 / $0.45 −25% vs headline | minimax-m3-1-flash | |
GMI CloudInference MiniMax-M3.1-Flash | $0.113 / $0.45 −25% vs headline | MiniMax-M3.1-Flash | |
OpenCode GoCloud minimax-m3.1-flash | $0.15 / $0.60 | minimax-m3.1-flash | |
Nebius AI StudioInference MiniMax-M3.1-Flash | $0.15 / $0.60 | MiniMax-M3.1-Flash | |
Together AIInference MiniMax-M3.1-Flash | $0.15 / $0.60 | MiniMax-M3.1-Flash | |
Fireworks AIInference minimax-m3p1-flash | $0.15 / $0.60 | minimax-m3p1-flash | |
Kyma APICloud minimax-m3.1-flash | $0.203 / $0.81 +35% vs headline | minimax-m3.1-flash |
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
- TextImages
- Produces
- Text
- Effort settings the source lists
- lowmediumhighxhighmax
- Features
- Prompt caching
- Open weights
- License: Apache-2.0Runs in about 529.2 GB of GPU memoryRuntimes: 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
- Refuseless62% lessminimax-m3.1-flash$0.05 / $0.25
- GMI Cloud25% lessMiniMax-M3.1-Flash$0.113 / $0.45
- EmpirioLabs AI25% lessminimax-m3-1-flash$0.113 / $0.45
Smaller MiniMax models
No cheaper MiniMax model keeps its key capabilities.
Other frontier labs
- 24% less
- 24% less
Open-weight picks
- 4% less
- 32% less
- 46% less
- 47% less
Call it
Using MiniMax's API.
from litellm import completion
response = completion(
model="minimax/MiniMax-M3.1-Flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does MiniMax M3.1 Flash cost?
On MiniMax, MiniMax M3.1 Flash costs $0.15 per million input tokens and $0.60 per million output tokens. Cached input costs $0.015 per million tokens. The cheapest host is Refuseless, at $0.05 per million input tokens and $0.25 per million output tokens.
Which APIs offer MiniMax M3.1 Flash?
MiniMax M3.1 Flash runs on 9 APIs: MiniMax, Refuseless, EmpirioLabs AI, GMI Cloud, OpenCode Go, Nebius AI Studio, Together AI, Fireworks AI and Kyma API.
What is MiniMax M3.1 Flash's context window?
1M tokens, with up to 1M tokens in one reply.
Is MiniMax M3.1 Flash being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to MiniMax M3.1 Flash?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (24% less), GPT-6 Luna on OpenAI (24% less) and Qwen3.8 27B on EmpirioLabs AI (4% less). MiniMax M3.1 Flash itself costs 62% less on Refuseless. Savings are on a mix of 3 input tokens to 1 output token.
When was MiniMax M3.1 Flash released?
MiniMax released it on 19 Oct 2026.
What is MiniMax M3.1 Flash's API model id?
Use MiniMax-M3.1-Flash with MiniMax. Other hosts use their own ids: minimax-m3.1-flash on Refuseless, minimax-m3-1-flash on EmpirioLabs AI, minimax-m3.1-flash on OpenCode Go, minimax-m3p1-flash on Fireworks AI.
Sources
- GMI Cloud pricing
- MiniMax pricing
- Nebius AI Studio pricing
- Together AI pricing
- EmpirioLabs AI pricing
- OpenCode Go pricing
- Refuseless pricing
- Fireworks AI pricing
- LiteLLM model map
Raw catalog entry for MiniMax-M3.1-Flash on MiniMax
{
"input_cost_per_token": 1.5e-7,
"output_cost_per_token": 6e-7,
"cache_read_input_token_cost": 1.5e-8,
"litellm_provider": "minimax",
"mode": "chat",
"source": "https://platform.minimax.io/docs/guides/pricing-paygo",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"reasoning_effort_levels": [
"low",
"medium",
"high",
"xhigh",
"max"
],
"supports_vision": true,
"max_input_tokens": 1000000
}