MiniMax M2.7 model profile
Evidence snapshot:
MiniMax M2.7 is a MiniMax model profile with a 204,800-token context window. The dated catalog snapshot records text modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments. Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.
MiniMax M2.7 is a reference profile: MiniMax publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
MiniMax M2.7 is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.
MiniMax M2.7 accepts text and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.
The dated reference snapshot lists $0.24 input and $0.96 output per million tokens. Cached input is $0.05 per million tokens.
The 2026-09-06 snapshot includes 1 Artificial Analysis index, 8 Design Arena categories, and AutoExacto results for 11 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
MiniMax M2.7 ranked #82 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.
Profile facts
- Profile type
- Model research profile
- Provider or publisher
- MiniMax
- Context window
- 204,800 tokens
- Snapshot date
- 2026-09-06
- Knowledge cutoff
- Not disclosed
- Reference catalog ID
- minimax/minimax-m2.7
When to pick MiniMax M2.7
MiniMax M2.7 is a reference profile: MiniMax publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.
- Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
- Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
- Look elsewhere when the request is trivial and latency-sensitive. Reasoning is mandatory on this route and cannot be turned off, so short factual requests still pay reasoning tokens and reasoning latency.
Context, modalities, and identity
MiniMax M2.7 accepts text and returns text. The snapshot records prompt caching, reasoning controls, structured output, text generation, and tool calling as capabilities or interfaces.
- Provider or publisher
- MiniMax
- Context window
- 204,800 tokens
- Maximum output
- 131,072 tokens
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- Not disclosed
Model overview
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments. Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.
- Reference model ID
- minimax/minimax-m2.7
- Canonical version
- minimax/minimax-m2.7-20260318
- Hugging Face ID
- MiniMaxAI/MiniMax-M2.7
Capabilities and supported controls
Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.
- Supported parameters
- frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p
- prompt caching
- reasoning controls
- structured output
- text generation
- tool calling
Dated pricing snapshot
The dated reference snapshot lists $0.24 input and $0.96 output per million tokens. Cached input is $0.05 per million tokens.
These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.
- Price date
- 2026-09-06
- Input
- $0.24 per 1M tokens
- Cached input
- $0.05 per 1M tokens
- Output
- $0.96 per 1M tokens
Provider routes, performance, and uptime
The snapshot retains 10 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.
- Active provider endpoints
- 10
- Best p50 latency
- 0.13 s
- Best p50 throughput
- 310 tok/s
- Availability with routing
- 97.35% over the sampled window
- Availability without routing
- 90.09% over the sampled window
- Performance date
- 2026-09-06
| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
|---|---|---|---|---|---|---|---|---|
| MARA | unknown | $0.24 / 1M | $0.96 / 1M | No verified rate | 196,608 tokens | 4.71 s | 148 tok/s | 96.82% |
| DeepInfra | fp8 | $0.25 / 1M | $1 / 1M | $0.05 / 1M | 196,608 tokens | 0.66 s | 41 tok/s | 99.99% |
| NovitaAI | fp8 | $0.27 / 1M | $1.08 / 1M | $0.054 / 1M | 204,800 tokens | 2.14 s | 12 tok/s | 99.64% |
| AtlasCloud | fp8 | $0.3 / 1M | $1.2 / 1M | $0.06 / 1M | 196,608 tokens | 1.26 s | 12 tok/s | 99.56% |
| GMICloud | fp8 | $0.3 / 1M | $1.2 / 1M | $0.06 / 1M | 196,608 tokens | 3.99 s | 7 tok/s | 99.16% |
| MiniMax | fp8 | $0.3 / 1M | $1.2 / 1M | $0.06 / 1M | 204,800 tokens | 1.17 s | 42 tok/s | 99.59% |
| DeepInfra Turbo | fp8 | $0.38 / 1M | $1.7 / 1M | $0.07 / 1M | 196,608 tokens | 1.85 s | 89 tok/s | 83.03% |
| Groq | unknown | $0.6 / 1M | $1.8 / 1M | No verified rate | 196,608 tokens | 0.13 s | 310 tok/s | 99.09% |
| SambaNova | unknown | $0.6 / 1M | $2.4 / 1M | $0.06 / 1M | 196,608 tokens | 1.06 s | 48 tok/s | 96.34% |
| MiniMax Highspeed | fp8 | $0.6 / 1M | $2.4 / 1M | $0.06 / 1M | 204,800 tokens | 0.72 s | 66 tok/s | 98.75% |
Benchmark evidence and limitations
The 2026-09-06 snapshot includes 1 Artificial Analysis index, 8 Design Arena categories, and AutoExacto results for 11 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
- Coding Index
- 52.6
- AutoExacto coverage
- 11 provider observations over 32 days
| Design Arena category | Elo | Win rate | Rank |
|---|---|---|---|
| 3d | 1231 | 50.5% | #39 |
| asciiart | 1165 | 47.5% | #36 |
| codecategories | 1251 | 52% | #36 |
| dataviz | 1253 | 52.8% | #31 |
| gamedev | 1237 | 51.4% | #38 |
| svg | 1173 | 48.9% | #44 |
| uicomponent | 1233 | 49.4% | #41 |
| website | 1258 | 52.5% | #34 |
AutoExacto provider benchmarks
Rolling provider observations from the cited third-party benchmark view. The lookback is 32 days; GPQA Diamond and TAU-Bench Airline measure different abilities and should not be blended into one score.
| Provider | GPQA Diamond | TAU-Bench Airline | Runs |
|---|---|---|---|
| AtlasCloud | 84.15% | 66.39% | 4 |
| auto-routing | 82.97% | 70.73% | 4 |
| DeepInfra | 73.78% | 70.35% | 4 |
| DeepInfra Turbo | 80.85% | 66% | 3 |
| GMICloud | 83.11% | 71.46% | 4 |
| Groq | 74.76% | 72.54% | 4 |
| MARA | 78% | 69.33% | 4 |
| MiniMax | 85.19% | 70% | 4 |
| MiniMax Highspeed | 85.58% | 73.2% | 4 |
| NovitaAI | 84.44% | 70.03% | 4 |
| SambaNova | 79.11% | 66.37% | 2 |
Popularity and market context
MiniMax M2.7 ranked #82 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
- Third-party catalog rank
- #82
- Global market share
- Not inferred
- Observation date
- 2026-09-06
Frequently asked questions
When should I use MiniMax M2.7?
MiniMax M2.7 is a reference profile: MiniMax publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr. Look elsewhere when the request is trivial and latency-sensitive: Reasoning is mandatory on this route and cannot be turned off, so short factual requests still pay reasoning tokens and reasoning latency.
What is MiniMax M2.7?
MiniMax M2.7 is a MiniMax model profile with a 204,800-token context window. The dated catalog snapshot records text modalities and interfaces for prompt caching, reasoning controls, structured output, text generation, tool calling.
What context window does MiniMax M2.7 have?
The dated profile lists 204,800 tokens of context and up to 131,072 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.
What benchmark evidence is available for MiniMax M2.7?
The 2026-09-06 snapshot includes 1 Artificial Analysis index, 8 Design Arena categories, and AutoExacto results for 11 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Is MiniMax M2.7 available through Kendr?
This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.
Does the popularity rank represent MiniMax M2.7's global market share?
MiniMax M2.7 ranked #82 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. No global market-share percentage is inferred when the source does not publish one.
Sources and evidence dates
- MiniMax M2.7 third-party catalog record (catalog, checked 2026-09-06)
- Third-party model catalog methodology (methodology, checked 2026-09-06)
- MiniMax official model documentation (primary, checked 2026-09-06)
- Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
- Design Arena leaderboard and methodology (benchmark, checked 2026-09-06)
- MiniMax M2.7 third-party catalog record (benchmark, checked 2026-09-06)