MiniMaxVerified Active: October 30, 2026
MiniMax M3.1 FlashAPI Pricing & Specifications
Ultra high-speed multimodal MoE model with 1M context window at rock-bottom token rates.
📊 Core Specifications & Pricing Rates
Standard Input
$0.15 / 1M tokens
Standard Output
$0.60 / 1M tokens
Cached Input
$0.0300 / 1M tokens
Cache Write
$0.19 / 1M tokens
Context Window
1M (1,000,000 tokens)
Max Output Tokens
64,000 tokens
Supported Capabilities:✓ Vision✓ Function Calling / Tools✓ JSON Mode✓ Deep Reasoning
📦 Asynchronous Batch API Supported: Official provider documentation offers a 50% discount on non-streaming 24h batch requests.
Live Workload Cost Estimator: MiniMax M3.1 Flash
Adjust token volumes to simulate your exact monthly API bill.
Estimated 60% repeated context
Estimated Total Monthly Cost
Compare All Models in Calculator→$8.93/ month
$0.00036 per API request(Saves $2.70/mo with caching)
💡 Estimated Monthly Workload Scenarios
High-Volume Data Extraction Pipeline
$84.00/mo200,000 log & text extractions (2,000 input, 200 output)
200,000 requests • 2000 in / 200 out
⚖️ Head-to-Head Competitor Comparisons
MiniMax M3.1 Flash vs. Claude Haiku 5.5
Similar sub-$1 budget tier; Haiku 5.5 is $0.10/$0.50, while MiniMax M3.1 Flash provides native open-weight parity and high concurrency limits.
Similar budget tier ($0.15/$0.60 vs $0.10/$0.50)View Claude Haiku 5.5 →
📜 Historical Price Changes & Updates
2026-10-24
MiniMax M3.1 Flash released at $0.15 input / $0.60 output per 1M tokens.
🔗 Verified Primary Sources
All pricing, token limits, and capabilities are cross-checked against official provider documentation and live API endpoints.