[MiniMax](/ai-gateway/models/labs/minimax) # MiniMax M3 MiniMax M3 is MiniMax's first model with a 1.0M tokens context window and native multimodal input. It targets software engineering, terminal-based tool use, and agentic web browsing, with a max output of 1.0M tokens per request. Your use is subject to MiniMax's [Terms](https://platform.minimax.io/protocol/terms-of-service) & [Privacy](https://platform.minimax.io/protocol/privacy-policy) Policies. Implicit CachingReasoningTool UseVision (Image)File Input [Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway) AI SDKChat CompletionsMessagesResponses ``` 1import { streamText } from 'ai' 2 3const result = streamText({ 4 model: 'minimax/minimax-m3', 5 prompt: 'Why is the sky blue?' 6}) ``` [Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk) [Overview](/ai-gateway/models/minimax-m3) [API](/ai-gateway/models/minimax-m3/api) [About](/ai-gateway/models/minimax-m3/about) [Providers](/ai-gateway/models/minimax-m3/providers) [Throughput](/ai-gateway/models/minimax-m3/throughput) [Latency](/ai-gateway/models/minimax-m3/latency) [Uptime](/ai-gateway/models/minimax-m3/uptime) [Status](/ai-gateway/models/minimax-m3/status) [Similar](/ai-gateway/models/minimax-m3/similar) [FAQ](/ai-gateway/models/minimax-m3/faq) ## [Copy link to heading](#playground)Playground Try out MiniMax M3 by MiniMax. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days. ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75)MiniMax M3 ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=96&q=75) MiniMax M3 ## [Copy link to heading](#providers)Providers Route requests across multiple providers. Copy a provider slug to set your preference. Visit the [docs](/docs/ai-gateway/provider-options) for more info. Using a provider means you agree to their terms, listed under Legal. | Provider | | --- | | Context | Max Output | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) [MiniMax](/ai-gateway/models/providers/minimax) 50% off Legal:[Terms](https://platform.minimax.io/protocol/terms-of-service)•[Privacy](https://platform.minimax.io/protocol/privacy-policy) | 1M | 1M | 1.6s | 92tps | $0.60/M$0.30/M +1 more | $2.40/M$1.20/M +1 more | Read: $0.12/M$0.06/M+1 more Write: — | — | +2 | | | 05/31/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![fireworks logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffireworks.png&w=48&q=75) [Fireworks](/ai-gateway/models/providers/fireworks) Legal:[Terms](https://fireworks.ai/terms-of-service)•[Privacy](https://fireworks.ai/privacy-policy) | 512K | 512K | 1.6s | 126tps | $0.30/M | $1.20/M | Read:$0.06/M Write:— | — | +1 | | | 05/31/2026 | | | ![nebius logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnebius.png&w=48&q=75) [Nebius](/ai-gateway/models/providers/nebius) Legal:[Terms](https://docs.nebius.com/legal/terms-of-use?_gl=1*17d22j*_gcl_au*MTAwNjQ2OTE2LjE3NjYwOTcyMzcuMTI0OTg1NTgzNi4xNzY2MDk3ODgzLjE3NjYwOTg1MzY.)•[Privacy](https://docs.nebius.com/legal/privacy?_gl=1*17d22j*_gcl_au*MTAwNjQ2OTE2LjE3NjYwOTcyMzcuMTI0OTg1NTgzNi4xNzY2MDk3ODgzLjE3NjYwOTg1MzY.) | 1M | 1M | 1.0s | 140tps | $0.30/M | $1.20/M | | — | +1 | | | 05/31/2026 | | | ![gmicloud logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fgmicloud.png%3Fv%3D1785888489595&w=48&q=75) [GMICloud](/ai-gateway/models/providers/gmicloud) 60% off Legal:[Terms](https://www.gmicloud.ai/en/terms-and-conditions)•[Privacy](https://www.gmicloud.ai/en/privacy-policy) | 1M | 1M | 2.8s | 103tps | $0.60/M$0.24/M +1 more | $2.40/M$0.96/M +1 more | Read: $0.12/M$0.05/M+1 more Write: — | — | +1 | | | 05/31/2026 | | ## [Copy link to heading](#throughput)Throughput24 hours 1W 1D P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#latency)Latency24 hours 1W 1D P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info. ## [Copy link to heading](#uptime)Uptime24 hours 1W 1D 1H Direct request success rate on AI Gateway and per-provider. Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/uptime) for more info. 1W 1D 1H ## [Copy link to heading](#more-models-by-minimax)More models by MiniMax All Text Code | Model | | --- | | Context | Latency | Throughput | Input | Output | Cache | Web Search | Capabilities | Providers | ZDR | No Training | Release Date | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) [minimax/minimax-m2.7](/ai-gateway/models/minimax-m2.7) | 205K | 1.0s | 158tps | $0.30/MFast $0.60/M | $1.20/MFast $2.40/M | Read:$0.06/M Write:$0.38/M | — | | ![fireworks logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Ffireworks.png&w=48&q=75) ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) | | | 03/18/2026 | | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) [minimax/minimax-m2.7-highspeed](/ai-gateway/models/minimax-m2.7-highspeed) | 205K | 1.2s | 51tps | $0.60/M | $2.40/M | Read:$0.06/M Write:$0.38/M | — | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) | | | 03/18/2026 | | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) [minimax/minimax-m2.5](/ai-gateway/models/minimax-m2.5) | 1M | 0.5s | 81tps | $0.27/MFast $0.60/M | $0.95/MFast $2.40/M | Read:$0.03/M Write:$0.38/M | — | | ![bedrock logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Famazon%2520bedrock.png&w=48&q=75) ![deepinfra logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fdeepinfra.png&w=48&q=75) ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) +2 | | | 02/12/2026 | | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) [minimax/minimax-m2.5-highspeed](/ai-gateway/models/minimax-m2.5-highspeed) | 205K | 1.2s | 66tps | $0.60/M | $2.40/M | Read:$0.03/M Write:$0.38/M | — | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) | | | 02/12/2026 | | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) [minimax/minimax-m2.1](/ai-gateway/models/minimax-m2.1) | 205K | 0.5s | 140tps | $0.30/M | $1.20/M | Read:$0.03/M Write:$0.38/M | — | | ![bedrock logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Famazon%2520bedrock.png&w=48&q=75) ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) | | | 12/23/2025 | | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) [minimax/minimax-m2](/ai-gateway/models/minimax-m2) | 205K | 0.8s | 73tps | $0.30/M | $1.20/M | Read:$0.03/M Write:$0.38/M | — | | ![minimax logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fminimax.png&w=48&q=75) ![novita logo](/vc-ap-vercel-marketing/_next/image?url=https%3A%2F%2F7nyt0uhk7sse4zvn.public.blob.vercel-storage.com%2Fdocs-assets%2Fstatic%2Fdocs%2Fai-gateway%2Flogos%2Fnovita.png&w=48&q=75) | | | 10/27/2025 | | ## [Copy link to heading](#about-minimax-m3)About MiniMax M3 MiniMax M3 is built around MiniMax Sparse Attention (MSA), an attention variant that splits the key-value cache into blocks and pre-filters which blocks contribute to each query. That design supports the 1.0M tokens context window without the quadratic compute scaling of full attention, and it lets MiniMax M3 keep prefill and decode efficient on long inputs. Native multimodality is wired in from the start of training rather than bolted on later. MiniMax M3 accepts text, image, and video input and produces text output. The pretraining pipeline aligns visual and textual semantics directly, which carries over to multimodal coding tasks like analyzing a screenshot of a failing test and writing a patch, or reproducing a bug from a GitHub issue thread. MiniMax M3 is positioned for software engineering, terminal-based tool use, and agentic web browsing. It scores 59.0% on SWE-Bench Pro and 70.06% on OSWorld-Verified for computer use. Automatic prompt caching is enabled by default, which reduces effective cost on repeated context patterns common in agent loops. ## [Copy link to heading](#what-to-consider-when-choosing-a-provider)What To Consider When Choosing a Provider - Configuration: MiniMax M3 pairs the 1.0M tokens context window with native image and video input, which makes it a fit for workflows that reason over screenshots, design references, or long video transcripts alongside code. Route through AI Gateway via the AI SDK plus Chat Completions / Responses / Messages APIs to get provider failover, observability, and unified pricing across the providers serving MiniMax M3. - Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the [documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) for details. - Authentication: AI Gateway authenticates requests using an [API key](https://vercel.com/docs/ai-gateway/authentication-and-byok#api-key-authentication) or [OIDC token](https://vercel.com/docs/ai-gateway/authentication-and-byok#oidc-token-authentication). You do not need to manage provider credentials directly. ## [Copy link to heading](#when-to-use-minimax-m3)When to Use MiniMax M3 ### Best for - Long-horizon coding agents: Sessions that span an entire repository without fragmenting context across requests - Multimodal engineering: Workflows that reason over screenshots, diagrams, or video alongside code - Computer-use agents: Browser and desktop automation that benefits from strong OSWorld performance - Terminal-driven tool chains: Agents that read command output and iterate across many steps - Long-video and long-document understanding: Tasks that require sustained attention over hours of input ### Consider alternatives when - Raw inference speed: Latency matters more than capability breadth, so consider M3-highspeed - Short single-turn text tasks: A smaller model is cheaper when the workload is single-turn and text-only - Text-only reasoning: Standard M2.7 covers the use case at lower cost when multimodal input is not needed ## [Copy link to heading](#conclusion)Conclusion MiniMax M3 brings a 1.0M tokens context window, native multimodal input, and agentic coding capability into one model. For teams running long-horizon agents over full repositories, browser sessions, or video input, MiniMax M3 reduces the need to split work across multiple specialized models. Route it through AI Gateway via the AI SDK plus Chat Completions / Responses / Messages APIs for failover and unified observability.