MiniMax M3.1 Flash API pricing

10 providers serve MiniMax M3.1 Flash. MiniMax M3.1 Flash is an open-weight model (MiniMax Community) with 428B total parameters, 23B active per token (mixture-of-experts), up to 1049K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-11-22 · list prices from provider APIs
Input floor $0.050/1M at Refuseless Output floor $0.250/1M at Refuseless Find your workload winner →

About MiniMax M3.1 Flash

MiniMax M3.1 Flash was listed on the marketplace 2026-10-19. It has a 1049K-token context window.

Provider Input $/1M Output $/1M Cache read $/1M Context
Refuseless $0.050 $0.250output floor $0.0020 1049K
Empiriolabs $0.113 $0.450 $0.011 1049K
GMI Cloud $0.113 $0.450 $0.011 1049K Use
MiniMax $0.150 $0.600 $0.015 1000K Use
Together AI $0.150 $0.600 $0.015 1049K Use
Fireworks AI $0.150 $0.600 $0.015 1049K Use
Opencode Go $0.150 $0.600 $0.015 1000K
Nebius $0.150 $0.600 $0.015 1049K Use
Inferenceapis $0.200 $0.780 $0.020 1049K
Kyma $0.203 $0.810 $0.020 1049K

Price since listing

First tracked input floor: $0.150/1M on 2026-10-20. Latest: $0.050/1M on 2026-11-22 (34 days tracked).

The cheapest way to run MiniMax M3.1 Flash

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $11.00/month, at Refuseless. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. On output-token cost alone, the API floor remains below our self-hosting estimate of ~$0.631/1M. Details below. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Or run it yourself: MiniMax M3.1 Flash self-hosting economics

MiniMax M3.1 Flash is open-weight (MiniMax Community), so the API price above competes with the GPU-hour market. 428B total parameters (MoE, ~23B active per token) needs roughly 589 GB VRAM at FP8 or 295 GB at INT4, KV-cache headroom included.

No single GPU fits MiniMax M3.1 Flash at FP8 (589 GB needed), so it needs a multi-GPU node. Cheapest tracked option: 4× MI300X (192 GB each) at roughly $2.00/hr total (RunPod). Rent 4× MI300X at RunPod → INT4 quantization drops the requirement to 295 GB. Tune it in the calculator.
Breakeven estimate: a well-batched vLLM deployment on 4× MI300X ($2.00/hr) at ~1761 aggregate tok/s and 50% utilization works out to roughly $0.631 per 1M output tokens, versus $0.250 via the cheapest output-token API (Refuseless). The API is cheaper unless your utilization or throughput beats these assumptions. Planning estimate: throughput varies with hardware, quantization, batch size and context. Tune it in the calculator.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
MiniMax M3 $0.225 $0.900 17
MiniMax M2.5 $0.270 $0.950 10
MiniMax M2.7 $0.150 $0.550 10
MiniMax M2 $0.300 $1.20 6
MiniMax M2.1 $0.300 $1.20 5
MiniMax M3 (batch) $0.224 $0.880 1

FAQ

What is the cheapest API for MiniMax M3.1 Flash?

As of 2026-11-22, the lowest input price for MiniMax M3.1 Flash is Refuseless at $0.050 per 1M input tokens. The lowest output price is Refuseless at $0.250 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is Empiriolabs at $0.113, a 125% difference.

How much VRAM do you need to self-host MiniMax M3.1 Flash?

MiniMax M3.1 Flash has 428B parameters, so plan for roughly 589 GB of VRAM at FP8 or 295 GB at INT4/AWQ, KV-cache headroom included. That exceeds a single GPU. A typical node is 4× MI300X.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON