MiniMax M3.1 Flash vs MiniMax M3 API pricing
Updated
MiniMax M3.1 Flash: USD 0.10 input, USD 0.50 output per 1M tokens (Inference.net). MiniMax M3: USD 0.23 input, USD 0.96 output per 1M tokens (CoreWeave Forge). At 3 input tokens per output token, MiniMax M3 costs 2.06× as much as MiniMax M3.1 Flash (USD 0.4125 vs USD 0.20 per 1M).
How do MiniMax M3.1 Flash and MiniMax M3 differ on price?
- Cheapest input price: MiniMax M3.1 Flash USD 0.10 against USD 0.23 per 1M tokens, so MiniMax M3 costs 2.3× as much.
- Cheapest output price: MiniMax M3.1 Flash USD 0.50 against USD 0.96 per 1M tokens, so MiniMax M3 costs 1.92× as much (92% more).
- Among the 201 indexed models, MiniMax M3.1 Flash ranks 56th cheapest and MiniMax M3 85th on the 3:1 blend.
- No input:output mix changes the answer: MiniMax M3.1 Flash is cheaper at every mix before cache discounts.
- Both list cached-input discounts: MiniMax M3.1 Flash at 10 standard prices of 10, from USD 0.005 (Inference.net, 95% below that provider's input price); MiniMax M3 at 10 standard prices of 10, from USD 0.048 (GMI Cloud, 80% below that provider's input price).
- Both state a context window of up to 1,048,576 tokens.
- Both have 10 providers with a standard price; 5 providers sell both (GMI Cloud, Fireworks AI, MiniMax, Parasail and 1 more).
- On one account, GMI Cloud charges USD 0.2625 for MiniMax M3.1 Flash (1.31× its cheapest price) and USD 0.42 for MiniMax M3 (1.02× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for MiniMax M3.1 Flash: its dearest standard price is 2.6× its cheapest, against 2.3× for MiniMax M3.
- MiniMax's own API charges USD 0.2625 for MiniMax M3.1 Flash at 3:1, 31% above the cheapest provider (Inference.net).
- MiniMax's own API charges USD 0.525 for MiniMax M3 at 3:1, 27% above the cheapest provider (CoreWeave Forge).
- For the one-developer coding agent preset, the gap is USD 1,740 a year in MiniMax M3.1 Flash's favour (MiniMax M3.1 Flash USD 79.65 a month, MiniMax M3 USD 224.64).
- Per character of input, MiniMax M3.1 Flash costs 57% less than MiniMax M3 in every measured language, because both use the MiniMax M3 tokenizer.
MiniMax M3.1 Flash and MiniMax M3 prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | MiniMax M3.1 Flash | MiniMax M3 |
|---|---|---|
| Model page | MiniMax M3.1 Flash MiniMax · 10 providers | MiniMax M3 MiniMax · 10 providers |
| Cheapest standard price, blended 3:1 | USD 0.20 lower USD 0.10 in / USD 0.50 out at Inference.net Inference.net page checked 2026-11-16 | USD 0.4125 USD 0.23 in / USD 0.96 out at CoreWeave Forge CoreWeave Forge page checked 2026-11-15 |
| Cheapest input | USD 0.10 lower Inference.net source | USD 0.23 CoreWeave Forge source |
| Cheapest cached input | USD 0.005 lower Inference.net source | USD 0.048 promo GMI Cloud source |
| Cheapest output | USD 0.50 lower Inference.net source | USD 0.96 CoreWeave Forge source |
| Maker's own API | USD 0.15 / USD 0.60 MiniMax source | USD 0.30 / USD 1.20 MiniMax source |
| Median standard price | USD 0.15 / USD 0.60 input / output, 10 prices | USD 0.30 / USD 1.20 input / output, 10 prices |
| Context window | 1,048,576 tokens, largest stated; from 1,000,000 at some providers | 1,048,576 tokens, largest stated; from 262,144 at some providers |
| Providers with a standard price | 10 | 10 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
- Promo: the provider calls the price promotional or discounted, so it is current now and can end without notice.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do MiniMax M3.1 Flash and MiniMax M3 cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | MiniMax M3.1 Flash | MiniMax M3 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 12.87 Inference.net | USD 28.26 CoreWeave Forge | USD 15.39 MiniMax M3.1 Flash lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 24.66 Inference.net | USD 56.64 CoreWeave Forge | USD 31.98 MiniMax M3.1 Flash lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 79.65 Inference.net | USD 224.64 GMI Cloud | USD 144.99 MiniMax M3.1 Flash lower |
MiniMax M3.1 Flash is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.82× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
MiniMax M3.1 Flash is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below MiniMax M3's, so the input:output ratio never changes the answer.
| Input : output tokens | MiniMax M3.1 Flash | MiniMax M3 |
|---|---|---|
| 1 : 3 (long answers) | USD 0.40 lower Inference.net | USD 0.7775 CoreWeave Forge |
| 1 : 1 | USD 0.30 lower Inference.net | USD 0.595 CoreWeave Forge |
| 3 : 1 (the site’s blend) | USD 0.20 lower Inference.net | USD 0.4125 CoreWeave Forge |
| 10 : 1 (retrieval, long prompts) | USD 0.1364 lower Inference.net | USD 0.2964 CoreWeave Forge |
| 30 : 1 (agents, big contexts) | USD 0.1129 lower Inference.net | USD 0.2535 CoreWeave Forge |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do MiniMax M3.1 Flash and MiniMax M3 cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the MiniMax M3 tokenizer for MiniMax M3.1 Flash (the same one for both, so the gap equals the price gap):
| Content | MiniMax M3.1 Flash | MiniMax M3 |
|---|---|---|
| English | USD 0.021 lower Inference.net | USD 0.048 CoreWeave Forge |
| Arabic MSA | USD 0.031 lower Inference.net | USD 0.071 CoreWeave Forge |
| Egyptian Arabic | USD 0.033 lower Inference.net | USD 0.075 CoreWeave Forge |
| Hindi | USD 0.059 lower Inference.net | USD 0.137 CoreWeave Forge |
| Chinese | USD 0.056 lower Inference.net | USD 0.128 CoreWeave Forge |
| Spanish | USD 0.021 lower Inference.net | USD 0.049 CoreWeave Forge |
| Code | USD 0.026 lower Inference.net | USD 0.059 CoreWeave Forge |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Check it on your own traffic
- MiniMax M3.1 Flash API pricing: all 10 providers and other tiers.
- MiniMax M3 API pricing: all 10 providers and other tiers.
- Cost calculator with MiniMax M3.1 Flash and MiniMax M3 preloaded
- MiniMax token counter
- Prompt caching calculator
More comparisons: DeepSeek V4.1 Flash vs MiniMax M3.1 Flash · Qwen3.8 27B vs MiniMax M3.1 Flash · MiniMax M3 vs MiniMax M2.5 · GLM 5.3 vs MiniMax M3 · Kimi K3 vs MiniMax M3 · Qwen3.8 27B vs MiniMax M3 · DeepSeek V4.1 Flash vs MiniMax M3 · MiniMax M3 vs MiniMax M2.7 · every MiniMax M3.1 Flash comparison · every MiniMax M3 comparison · all 662 price comparisons
Questions
Is MiniMax M3.1 Flash cheaper than MiniMax M3?
Yes. On a blend of 3 input tokens to 1 output token, MiniMax M3.1 Flash costs USD 0.20 per 1M tokens and MiniMax M3 USD 0.4125, at each model's cheapest standard price. For input alone, MiniMax M3.1 Flash is cheaper (USD 0.10 against USD 0.23 per 1M); for output alone, MiniMax M3.1 Flash is (USD 0.50 against USD 0.96). This compares price only, not quality.
What do MiniMax M3.1 Flash and MiniMax M3 cost per 1M tokens?
MiniMax M3.1 Flash: from USD 0.10 input and USD 0.50 output at Inference.net; MiniMax's own API charges USD 0.15 / USD 0.60; median of 10 standard prices USD 0.15 / USD 0.60. MiniMax M3: from USD 0.23 input and USD 0.96 output at CoreWeave Forge; MiniMax's own API charges USD 0.30 / USD 1.20; median of 10 standard prices USD 0.30 / USD 1.20. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both MiniMax M3.1 Flash and MiniMax M3?
5 providers have a standard price for both: GMI Cloud (USD 0.2625 and USD 0.42 at 3:1), Fireworks AI (USD 0.2625 and USD 0.525 at 3:1), MiniMax (USD 0.2625 and USD 0.525 at 3:1), Parasail (USD 0.2625 and USD 0.525 at 3:1), Featherless (USD 0.2625 and USD 0.9625 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.20 and USD 0.4125.
Which is cheaper for a coding agent or a chatbot, MiniMax M3.1 Flash or MiniMax M3?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 79.65 a month on MiniMax M3.1 Flash (Inference.net) against USD 224.64 on MiniMax M3 (GMI Cloud), a difference of USD 144.99. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 12.87 a month on MiniMax M3.1 Flash (Inference.net) against USD 28.26 on MiniMax M3 (CoreWeave Forge), a difference of USD 15.39. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of MiniMax M3.1 Flash and MiniMax M3 change?
MiniMax M3.1 Flash is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below MiniMax M3's, so the input:output ratio never changes the answer.
Do MiniMax M3.1 Flash and MiniMax M3 have cached input pricing?
MiniMax M3.1 Flash from USD 0.005 per 1M cached input tokens (Inference.net; 10 of 10 standard prices list a discount). MiniMax M3 from USD 0.048 per 1M cached input tokens (GMI Cloud; 10 of 10 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, MiniMax M3.1 Flash or MiniMax M3?
Both go up to 1,048,576 tokens on the providers that state it.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- Inference.net: pricing (checked 2026-11-16)
- MiniMax: own API pricing (checked 2026-11-14)
- CoreWeave Forge: pricing (checked 2026-11-15)
- GMI Cloud: pricing (checked 2026-11-15)
- GMI Cloud: pricing (checked 2026-11-15)
- Fireworks AI: pricing (checked 2026-11-14)
- Fireworks AI: pricing (checked 2026-11-14)
- Parasail: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- Featherless: pricing (checked 2026-11-15)