Last refreshed 2026-06-29. Next refresh: weekly.
Why use MiniMax M2.7 on Novita AI?
Novita AI offers MiniMax M2.7 with pay-as-you-go pricing at $0.30/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Compare MiniMax M2.7 across 4 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: minimax-m2.7minimax-m2.7Request example
Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare MiniMax M2.7 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenRouter | $0.28 | $1.20 |
| Fireworks AI | $0.30 | $1.20 |
| Vercel AI Gateway | $0.30 | $1.20 |
| Novita AI | $0.30 | $1.20 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.30 |
| Output tokens | $1.20 |
Capabilities
About MiniMax M2.7
MiniMax M2.7 is MiniMax's self-improving frontier model, released March 18, 2026. It introduces native multi-agent collaboration, complex skill orchestration, and early recursive self-improvement capabilities. The model uses 10B active parameters, supports a 204,800-token context window, and was released alongside MiniMax-M2.7-highspeed, a 66% faster latency-optimized variant. Public provider listings price standard M2.7 at $0.30 per 1M input tokens and $1.20 per 1M output tokens. MiniMax M3 supersedes it for million-token, multimodal, and computer-use workflows, while M2.7 remains the lower-cost text-only route when 200K context is enough.