# Cheapest MiniMax M3.1 Flash API providers, compared (prices checked Nov 7, 2026)

URL: https://ernd.ai/inference-prices/minimax-m3-1-flash

> ernd partners with [Wafer](https://ernd.ai/partners/wafer). Prices are from OpenRouter's public listings.

MiniMax M3.1 Flash is an open-weight model from MiniMax. On OpenRouter, 13 listings from 12 providers sell it, and the blended price runs from $0.131 to $0.262 per million tokens.

| Provider | Input /1M | Output /1M | Blended 3:1 | Cache read /1M | Context | Quantization | Latency | Throughput |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| MiniMax | $0.075 | $0.30 | $0.131 | $0.0075 | 1.05M | Not listed | 1.20 s | 106 tok/s |
| GMICloud | $0.113 | $0.45 | $0.197 | $0.0112 | 1.05M | FP8 | 1.94 s | 93 tok/s |
| StreamLake | $0.135 | $0.54 | $0.236 | $0.0135 | 1M | FP8 | 2.16 s | 65 tok/s |
| DigitalOcean | $0.15 | $0.60 | $0.262 | $0.015 | 1.05M | Not listed | 1.09 s | 179 tok/s |
| Fireworks | $0.15 | $0.60 | $0.262 | $0.015 | 1.05M | Not listed | 0.71 s | 122 tok/s |
| inference.net | $0.15 | $0.60 | $0.262 | $0.015 | 1M | FP4 | 0.45 s | 69 tok/s |
| inference.net (US) | $0.15 | $0.60 | $0.262 | $0.015 | 1M | FP4 | 0.54 s | 68 tok/s |
| ModelRun [by Modular] | $0.15 | $0.60 | $0.262 | $0.015 | 1.05M | FP4 | 0.68 s | 138 tok/s |
| Nebius Token Factory | $0.15 | $0.60 | $0.262 | $0.015 | 1.05M | FP4 | 0.70 s | 106 tok/s |
| NovitaAI | $0.15 | $0.60 | $0.262 | $0.015 | 1M | FP16 | 1.49 s | 86 tok/s |
| Parasail | $0.15 | $0.60 | $0.262 | $0.015 | 1.05M | FP8 | 0.72 s | 163 tok/s |
| SambaNova | $0.15 | $0.60 | $0.262 | $0.015 | 1.05M | Not listed | 1.47 s | 54 tok/s |
| Together | $0.15 | $0.60 | $0.262 | $0.015 | 1.05M | Not listed | 0.55 s | 118 tok/s |

Blended is three parts input price to one part output, per million tokens. Latency is time to first token and throughput is output tokens per second, both averaged from OpenRouter's daily figures for the last 7 days. Cheapest and fastest only count listings that were up when checked.

## Questions

### What is the cheapest MiniMax M3.1 Flash API provider?

MiniMax, at $0.131 per million tokens blended ($0.075 input, $0.30 output), in OpenRouter's listings on November 7, 2026.

### How much does MiniMax M3.1 Flash cost per million tokens?

Input runs from $0.075 to $0.15 per million tokens across 13 listings, and output from $0.30 to $0.60. The middle listing comes to $0.262 blended.

### Which MiniMax M3.1 Flash provider is fastest?

DigitalOcean had the most throughput over the last 7 days, about 179 tokens per second. inference.net was quickest to the first token at 0.45 s.

### How do I pay for MiniMax M3.1 Flash inference?

Buy OpenRouter credits and it sends each request to one of these providers, or open an account with a provider and pay it directly. The ernd card is a credit card for US companies. It earns 4% back on AI vendor spend and 1.5% back on everything else.

Source: OpenRouter public model and provider listings (https://openrouter.ai/models), checked November 7, 2026.

The ernd card is a credit card for US companies. It earns 4% back on AI vendor spend and 1.5% back on everything else. [Request the card at app.ernd.ai](https://app.ernd.ai/login?next=%2Fapp%2Fcard%2Fapply&utm_source=llms&utm_campaign=inference_prices).