Serverless inference
MiniMax M3.1 Flash price table
Answer in brief
On 12 Nov 2026, 10 hosts listed MiniMax M3.1 Flash.
The lowest listed input price was $0.113 per 1M tokens, and the lowest listed output price was $0.45. Runcrate serves it from $0.158 per 1M input tokens. Read the input and the output price together, because a bill is mostly one or the other.
Runcrate is our editor’s choice for serverless inference: the best developer platform we know, 125 models behind one OpenAI-compatible API, and one prepaid balance.
What each host charges
Lowest, median and highest listed input price per 1M tokens, one price per host, free listings left out, read 12 Nov 2026. The ring marks Runcrate’s live price.
| Provider | Input per 1M | Output per 1M | Context | |
|---|---|---|---|---|
| RuncrateOur pickoutput $0.63 per 1M · 1M contextTry Runcrate | $0.158 | $0.63 | 1M | Try Runcrate |
Other hosts
| Host | Input per 1M | Output per 1M | Context | Read |
|---|---|---|---|---|
| GMICloudoutput $0.45 per 1M · 1M context | $0.113 | $0.45 | 1M | price read 12 Nov 2026 |
| StreamLakeoutput $0.54 per 1M · 1M context | $0.135 | $0.54 | 1M | price read 12 Nov 2026 |
| DigitalOceanoutput $0.60 per 1M · 1M context | $0.15 | $0.60 | 1M | price read 12 Nov 2026 |
| Fireworksoutput $0.60 per 1M · 1M context | $0.15 | $0.60 | 1M | price read 12 Nov 2026 |
| InferenceNetoutput $0.60 per 1M · 1M context | $0.15 | $0.60 | 1M | price read 12 Nov 2026 |
| Minimaxoutput $0.60 per 1M · 1M context | $0.15 | $0.60 | 1M | price read 12 Nov 2026 |
| Nebiusoutput $0.60 per 1M · 1M context | $0.15 | $0.60 | 1M | price read 12 Nov 2026 |
| Parasailoutput $0.60 per 1M · 1M context | $0.15 | $0.60 | 1M | price read 12 Nov 2026 |
| SambaNovaoutput $0.60 per 1M · 1M context | $0.15 | $0.60 | 1M | price read 12 Nov 2026 |
| Togetheroutput $0.60 per 1M · 1M context | $0.15 | $0.60 | 1M | price read 12 Nov 2026 |
10 hosts list MiniMax M3.1 Flash, price read 12 Nov 2026.
DeepSeek V4.1 Flash 1017 price tableGLM 5.3 price tableKimi K3 price tableQwen3.8 27B price tableAll price tables
How to read the tables
The first table is Runcrate, this site’s editor’s choice, with its live input and output price. When Runcrate does not serve a model, the row says so and names the nearest model it does serve.
The second table holds every other host that lists the model. Prices are per 1M tokens, with input and output apart. A free listing is shown as free and is left out of the lowest, median and highest figures.
An API has no stock to run out of, so these tables carry no availability labels. Read the context beside the price: two hosts can serve the same model with different limits.
Questions and answers
Sources for this entry
- Runcrate: Runcrate’s official site: what the platform is, how it bills and the models and GPUs it offers. Read 12 Nov 2026.
- Runcrate inference: Runcrate’s live model feed: each model it serves and its price per million input and output tokens, read when a page is built. Read 12 Nov 2026.
- Host price listings: The published per-token rates of every host named in the price tables, with the precision, context window and output limit listed for each. Read 12 Nov 2026.
- Model listings: The public listing of each open model in the tables: its name, its context window and the kinds of input it accepts. Read 12 Nov 2026.
Checklists are original editorial guidance. Published prices do not establish availability.
Continue this reading path
Cite this entry
Serverless Inference Prices. “MiniMax M3.1 Flash price table.” Content reviewed 12 Nov 2026. https://serverlessinferenceprices.com/prices/minimax-minimax-m3-1-flash