MiniMax: MiniMax M2.7
minimax/minimax-m2.7
Cheapest provider
$0.28 / 1M
Morph
Fastest provider (p95)
—
No throughput data yet — populated as traffic accumulates
Intelligence (estimated)
73.1
Family + generation + popularity + price tier
Per-provider performance
Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| Morph | undisclosed | $0.2790 | $1.2000 | — | — | 99.32% | — |
| Fireworks | undisclosed | $0.3000 | $1.2000 | — | — | 95.48% | — |
| Mara | undisclosed | $0.3000 | $1.2000 | — | — | 99.89% | — |
| Minimax | q8· fp8 | $0.3000 | $1.2000 | — | — | 94.49% | — |
| Together | q4· fp4 | $0.3000 | $1.2000 | — | — | 98.05% | — |
| Minimax | q8· fp8 | $0.6000 | $2.4000 | — | — | 90.33% | — |
| SambaNova | undisclosed | $0.6000 | $2.4000 | — | — | 99.80% | — |
“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).
Intelligence estimate
No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.
- ·minimax family base
- ·top-13 on OpenRouter +1
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas routes MiniMax: MiniMax M2.7
- Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
- Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For MiniMax: MiniMax M2.7 that’s currently Morph at $0.28/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.