MiniMax M2.7
TL;DR
Open-sourceOpen-source end-to-end software engineering agent.
Available on
Open-source models are available on every plan, including Go ($1/mo).
Switch with
Pick MiniMax M2.7 from the selector.
Intelligence Index
MiniMax M2.7 vs the MiniMax lineup
MiniMax M3
MiniMax M2.7
MiniMax M2.5
Speed
~49
tokens / sec
Input
$0.30
per M tokens
Output
$1.20
per M tokens
MiniMax M2.7 in Command Code
MiniMax M2.7 is MiniMax's open-source model — end-to-end software engineering agent. It runs in Command Code with a 200K-token context window, switchable any time with /model.
It scores 38.1 on the Intelligence Index — #30 of the 38 scored models in the Command Code lineup.
MiniMax M2.7 specs at a glance
What MiniMax M2.7 accepts, how much it can hold in context, and what you need to run it.
| Spec | MiniMax M2.7 |
|---|---|
| Context window | 200K tokens |
| Input modalities | text |
| Reasoning | No |
| Release date | 2026-03-18 |
| Minimum plan | Go |
MiniMax M2.7 vs the Command Code lineup
MiniMax M2.7 alongside its nearest real alternatives in the lineup — every price straight from the billing tables.
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 | 59.9 | 76.5 | ~62 tok/s | $10.00 | $50.00 | $20 | 1M |
| Tencent Hy3 | 41.2 | 58.8 | ~58 tok/s | $0.00 | $0.00 | free | 262K |
| Qwen 3.7 Plus | 39 | 55.9 | ~52 tok/s | $0.40 | $1.60 | $0.70 | 1M |
| Kimi K2.5 | 38.1 | 46.8 | ~51 tok/s | $0.60 | $3.00 | $1.20 | 256K |
| MiniMax M2.7 (this page) | 38.1 | 52.6 | ~49 tok/s | $0.30 | $1.20 | $0.525 | 200K |
| Nemotron 3 Ultra | 37.8 | 49.3 | ~204 tok/s | $0.60 | $2.40 | $1.05 | 1M |
| MiMo V2.5 | 37.2 | 56.8 | ~88 tok/s | $0.14 | $0.28 | $0.175 | 1M |
What MiniMax M2.7 is best for
MiniMax M2.7 is a open-source model from MiniMax, cheaper blended than most of the lineup ($0.525 per million tokens). It trades speed for depth — better for batch and background work than rapid iteration.
The honest way to place it: run your own session with /model and compare against the lineup table above — the numbers on this page update as the registry and billing tables change.
When to switch away from MiniMax M2.7
No single model wins every task. These are MiniMax M2.7's computed nearest alternatives — one step up, one step down in cost, one for speed, one from the same family — each switchable mid-session with /model.
Switch to Qwen 3.7 Plus
Qwen 3.7 Plus scores 39 on the Intelligence Index to MiniMax M2.7's 38.1 — the nearest genuine step up — at $0.70 blended per million tokens versus $0.525. Reach for it when a task keeps hitting MiniMax M2.7's ceiling.
Switch to MiniMax M3
MiniMax M3 runs about 25% cheaper blended ($0.3938 versus $0.525 per million tokens) while scoring 44.4 on the Intelligence Index. Switch down for high-volume work where MiniMax M2.7's edge isn't earning its rate.
Switch to MiniMax M2.5
MiniMax M2.5 streams ~78 tokens/sec to MiniMax M2.7's ~49 at a comparable blended cost ($0.525 per million tokens). Use it when iteration speed matters more than squeezing out the last point of quality.
What you pay for MiniMax M2.7
MiniMax M2.7 is billed per token at the rates below — the same billing tables the Usage page charges against, so this page cannot quote a different price than you pay.
Blended cost (3:1 input:output, the shape of a typical coding session) works out to $0.525 per million tokens.
| Per 1M tokens | Input | Output | Cache read |
|---|---|---|---|
| All requests | $0.30 | $1.20 | $0.06 |
In Command Code: caching and taste-1
Open-source models are routed across multiple upstream providers for high availability. The price you see is the mean per-provider rate; the Usage page reflects what was actually charged.
Where supported by the upstream, prompt caching is on by default — cache reads are billed at $0.06 per million tokens versus $0.30 for fresh input.
taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions.
Plan availability
MiniMax M2.7 is an open-source model, available on every plan including Go.
Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits; credits roll over and never expire, and auto top-up keeps you running if you go over.
| Plan | Price/mo | LLM credits | Models |
|---|---|---|---|
| Go | $1 | $10 | Open-source only |
| Pro | $15 | $30 | Open-source + premium |
| Provider | $15 | Pay as you go | Open-source + premium |
| Max 10× | $100 | $150 | Open-source + premium |
| Max 20× | $200 | $300 | Open-source + premium |
| Teams Pro | $40 / seat | $40 / seat | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Switching models with /model
In an interactive Command Code session, run /model to open the model selector. Pick MiniMax M2.7 and it applies to this session and to future sessions until you change it again. Premium models require Pro or higher; open-source models are available on every plan, including Go.
cmd # start an interactive session
/model # open the selector and pick MiniMax M2.7All Command Code models, ranked by quality and speed
Quality is the Intelligence Index — an aggregate score across reasoning, math, coding, and knowledge evaluations. Speed is measured output tokens per second. Models without a published score are noted. This table is regenerated from the model registry, so it is always current.
| Model | Tier | Intelligence Index | Output speed |
|---|---|---|---|
| Claude Fable 5 | Premium | 59.9 | ~62 tok/s |
| GPT-5.6 Sol | Premium | 58.9 | ~77 tok/s |
| Claude Opus 4.8 | Premium | 55.7 | ~55 tok/s |
| GPT-5.6 Terra | Premium | 55 | ~155 tok/s |
| GPT-5.5 | Premium | 54.8 | ~81 tok/s |
| Grok 4.5 | Open-source | 53.8 | ~114 tok/s |
| Claude Opus 4.7 | Premium | 53.5 | ~52 tok/s |
| Claude Sonnet 5 | Premium | 53.4 | ~79 tok/s |
| GPT-5.4 | Premium | 51.4 | ~164 tok/s |
| GPT-5.6 Luna | Premium | 51.2 | ~234 tok/s |
| GLM-5.2 | Open-source | 51.1 | ~208 tok/s |
| Muse Spark 1.1 | Premium | 50.6 | ~130 tok/s |
| Gemini 3.5 Flash | Premium | 50.2 | ~236 tok/s |
| Claude Sonnet 4.6 | Premium | 47.2 | ~55 tok/s |
| Qwen 3.7 Max | Open-source | 46 | ~196 tok/s |
| MiniMax M3 | Open-source | 44.4 | ~113 tok/s |
| DeepSeek V4 Pro | Open-source | 44.3 | ~62 tok/s |
| GPT-5.3 Codex | Premium | 44.3 | ~106 tok/s |
| Kimi K2.6 | Open-source | 44.2 | ~43 tok/s |
| MiMo V2.5 Pro | Open-source | 42.2 | ~56 tok/s |
| Kimi K2.7 Code | Open-source | 41.9 | ~46 tok/s |
| Tencent Hy3 | Open-source | 41.2 | ~58 tok/s |
| DeepSeek V4 Flash | Open-source | 40.3 | ~106 tok/s |
| GLM-5.1 | Open-source | 40.2 | ~81 tok/s |
| Qwen 3.6 Max Preview | Open-source | 40 | ~46 tok/s |
| GPT-5.4 Mini | Premium | 40 | ~171 tok/s |
| Qwen 3.6 Plus | Open-source | 39.6 | ~53 tok/s |
| GLM-5 | Open-source | 39.5 | ~51 tok/s |
| Qwen 3.7 Plus | Open-source | 39 | ~52 tok/s |
| Kimi K2.5 | Open-source | 38.1 | ~51 tok/s |
| MiniMax M2.7 (this page) | Open-source | 38.1 | ~49 tok/s |
| Nemotron 3 Ultra | Open-source | 37.8 | ~204 tok/s |
| MiMo V2.5 | Open-source | 37.2 | ~88 tok/s |
| MiniMax M2.5 | Open-source | 33.7 | ~78 tok/s |
| Step 3.7 Flash | Open-source | 30.3 | ~407 tok/s |
| Step 3.5 Flash | Open-source | 26 | ~207 tok/s |
| Gemini 3.1 Flash Lite | Premium | 25 | ~300 tok/s |
| Claude Haiku 4.5 | Premium | 23.7 | ~103 tok/s |
| Kimi K3 | Open-source | Not yet scored | — |
| Kimi K2.7 Code HighSpeed | Open-source | Not yet scored | — |
| GLM-5.2 Fast | Open-source | Not yet scored | — |
| Inkling | Open-source | Not yet scored | — |
| Fugu Ultra | Premium | Not yet scored | — |
Frequently asked questions
MiniMax M2.7 or Qwen 3.7 Plus?
Qwen 3.7 Plus scores higher on the Intelligence Index (39 vs 38.1) at $0.70 blended per million tokens against MiniMax M2.7's $0.525. Default to MiniMax M2.7 and switch up when a task keeps stalling.
MiniMax M2.7 or MiniMax M3?
MiniMax M3 is about 25% cheaper blended ($0.3938 vs $0.525 per million tokens), scoring 44.4 on the Intelligence Index. Use MiniMax M3 for volume work and MiniMax M2.7 where its edge earns the difference.
How much does MiniMax M2.7 cost in Command Code?
$0.30 per million input tokens and $1.20 per million output tokens, with cache reads at $0.06. In an agent loop, cached context brings effective input to roughly $0.132 per million tokens.
What plan do I need for MiniMax M2.7?
MiniMax M2.7 is available on every plan, including Go at $1/mo.
How good is MiniMax M2.7 at coding?
MiniMax M2.7 scores 52.6 on the Coding Index — the Artificial Analysis sub-score most predictive of coding-agent performance — alongside 38.1 overall.
Does MiniMax M2.7 support image input and reasoning?
MiniMax M2.7 is text-only; paste code and logs rather than screenshots. It does not expose a reasoning mode.
Which Command Code model should I use?
Claude Fable 5 currently leads the lineup on the Intelligence Index (59.9). Grok 4.5 (53.8) leads the open-weights tier, available on every plan. For fast lookups, Step 3.7 Flash streams ~407 tok/s. There is no single right answer — switch per session with /model and let the task pick the model.
Can I mix MiniMax M2.7 with other models in a workflow?
Yes. Switch per session using /model. Common pattern: keep a default model and switch up for hard problems or down for quick lookups as the task calls for it.
Are open-source model prices fixed?
Open-source models are routed across multiple upstream providers for high availability. The price listed for each is the mean per-provider rate. Actual cost on a given request may vary slightly. The Usage page reflects the price charged.
MiniMax M2.7 or M3?
M3 is the frontier model with native multimodality and a 1M context. M2.7 is tuned specifically as an end-to-end software-engineering agent. Same token price; switch with /model.
Why no Intelligence Index for M2.7?
Public aggregate benchmarks have not yet been published for M2.7 in the current Intelligence Index format. The model is available and routed normally.
Is Command Code free to try?
The Go plan starts at $1/mo with $10 in LLM credits. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits.
Does Command Code train on my code?
No. Command Code does not train on your code or store your code snippets. taste-1 data is stored locally in your project directory.
Where can I track my usage?
The Usage page in Studio shows per-request cost, token counts, and which model ran. Settings > Billing lets you change plans, buy credits, or enable auto top-up.
Does Command Code replace my editor?
No. Command Code is editor-agnostic — it runs as a CLI and works alongside any editor (Cursor, VS Code, Zed, JetBrains, Neovim, etc.).
Related reading
- MiniMax M2.5 in Command Codecross-platform full-stack agentic dev
- MiniMax M3 in Command Codefrontier coding, agents & native multimodality
- Kimi K2.5 in Command Codemultimodal frontend coding
- Nemotron 3 Ultra in Command Codeopen reasoning model for long-horizon autonomous agents
- Every model, one referenceThe docs list of all Command Code models with ids and context windows.
- Pricing, limits, and dealsThe canonical price table, running deals, and usage estimates.
Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.