Minimax M2.1 vs MiniMax M2 API pricing
Updated
Minimax M2.1: USD 0.30 input, USD 1.20 output per 1M tokens (Amazon Bedrock and 2 others). MiniMax M2: USD 0.2775 input, USD 1.11 output per 1M tokens (Featherless). At 3 input tokens per output token, Minimax M2.1 costs 8.1% more than MiniMax M2 (USD 0.525 vs USD 0.4856 per 1M).
How do Minimax M2.1 and MiniMax M2 differ on price?
- Cheapest input price: MiniMax M2 USD 0.2775 against USD 0.30 per 1M tokens, so Minimax M2.1 costs 1.08× as much (8% more).
- Cheapest output price: MiniMax M2 USD 1.11 against USD 1.20 per 1M tokens, so Minimax M2.1 costs 1.08× as much (8% more).
- Among the 201 indexed models, Minimax M2.1 ranks 99th cheapest and MiniMax M2 97th on the 3:1 blend.
- No input:output mix changes the answer: MiniMax M2 is cheaper at every mix before cache discounts.
- Both list cached-input discounts: Minimax M2.1 at 2 standard prices of 3, from USD 0.03 (GMI Cloud, 90% below that provider's input price); MiniMax M2 at 2 standard prices of 4, from USD 0.03 (Google Vertex AI, 90% below that provider's input price).
- Both state a context window of up to 204,800 tokens.
- MiniMax M2 has 4 providers with a standard price, 1 more than Minimax M2.1; 3 providers sell both (Featherless, Amazon Bedrock and GMI Cloud).
- On one account, Featherless charges USD 0.525 for Minimax M2.1 (its cheapest price) and USD 0.4856 for MiniMax M2 (its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for MiniMax M2: its dearest standard price is 1.08× its cheapest, against 1× for Minimax M2.1.
- Per character of input, Minimax M2.1 costs 1.08× as much as MiniMax M2 in every measured language, because both use the MiniMax M3 tokenizer.
Minimax M2.1 and MiniMax M2 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 M2.1 | MiniMax M2 |
|---|---|---|
| Model page | Minimax M2.1 MiniMax · 3 providers | MiniMax M2 MiniMax · 4 providers |
| Cheapest standard price, blended 3:1 | USD 0.525 USD 0.30 in / USD 1.20 out at Amazon Bedrock and 2 others Amazon Bedrock page checked 2026-11-14 | USD 0.4856 lower USD 0.2775 in / USD 1.11 out at Featherless Featherless page checked 2026-11-15 |
| Cheapest input | USD 0.30 Amazon Bedrock source | USD 0.2775 lower Featherless source |
| Cheapest cached input | USD 0.03 tie GMI Cloud source | USD 0.03 tie Google Vertex AI source |
| Cheapest output | USD 1.20 Amazon Bedrock source | USD 1.11 lower Featherless source |
| Maker's own API | MiniMax publishes no paid standard price on its own API that we found. | MiniMax publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.30 / USD 1.20 input / output, 3 prices | USD 0.30 / USD 1.20 input / output, 4 prices |
| Context window | 204,800 tokens, largest stated; from 196,608 at some providers | 204,800 tokens, largest stated; from 196,608 at some providers |
| Providers with a standard price | 3 | 4 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do Minimax M2.1 and MiniMax M2 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 M2.1 | MiniMax M2 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 34.02 GMI Cloud | USD 32.97 Featherless | USD 1.05 MiniMax M2 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 70.56 GMI Cloud | USD 67.27 Featherless | USD 3.29 MiniMax M2 lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 234.90 GMI Cloud | USD 234.90 Google Vertex AI | same |
MiniMax M2 is cheaper on 2 workloads. The widest gap is on RAG over documents: the dearer model costs 4.9% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
MiniMax M2 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 M2.1's, so the input:output ratio never changes the answer.
| Input : output tokens | Minimax M2.1 | MiniMax M2 |
|---|---|---|
| 1 : 3 (long answers) | USD 0.975 Amazon Bedrock | USD 0.9019 lower Featherless |
| 1 : 1 | USD 0.75 Amazon Bedrock | USD 0.6938 lower Featherless |
| 3 : 1 (the site’s blend) | USD 0.525 Amazon Bedrock | USD 0.4856 lower Featherless |
| 10 : 1 (retrieval, long prompts) | USD 0.3818 Amazon Bedrock | USD 0.3532 lower Featherless |
| 30 : 1 (agents, big contexts) | USD 0.329 Amazon Bedrock | USD 0.3044 lower Featherless |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Minimax M2.1 and MiniMax M2 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 M2.1 (the same one for both, so the gap equals the price gap):
| Content | Minimax M2.1 | MiniMax M2 |
|---|---|---|
| English | USD 0.063 Amazon Bedrock | USD 0.058 lower Featherless |
| Arabic MSA | USD 0.093 Amazon Bedrock | USD 0.086 lower Featherless |
| Egyptian Arabic | USD 0.098 Amazon Bedrock | USD 0.091 lower Featherless |
| Hindi | USD 0.178 Amazon Bedrock | USD 0.165 lower Featherless |
| Chinese | USD 0.167 Amazon Bedrock | USD 0.155 lower Featherless |
| Spanish | USD 0.064 Amazon Bedrock | USD 0.059 lower Featherless |
| Code | USD 0.077 Amazon Bedrock | USD 0.072 lower Featherless |
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 M2.1 API pricing: all 3 providers and other tiers.
- MiniMax M2 API pricing: all 4 providers and other tiers.
- Cost calculator with Minimax M2.1 and MiniMax M2 preloaded
- MiniMax token counter
- Prompt caching calculator
More comparisons: MiniMax M2.5 vs Minimax M2.1 · every Minimax M2.1 comparison · every MiniMax M2 comparison · all 662 price comparisons
Questions
Is Minimax M2.1 cheaper than MiniMax M2?
No. On a blend of 3 input tokens to 1 output token, MiniMax M2 costs USD 0.4856 per 1M tokens and Minimax M2.1 USD 0.525, at each model's cheapest standard price. For input alone, MiniMax M2 is cheaper (USD 0.2775 against USD 0.30 per 1M); for output alone, MiniMax M2 is (USD 1.11 against USD 1.20). This compares price only, not quality.
What do Minimax M2.1 and MiniMax M2 cost per 1M tokens?
Minimax M2.1: from USD 0.30 input and USD 1.20 output at Amazon Bedrock and 2 others; median of 3 standard prices USD 0.30 / USD 1.20. MiniMax M2: from USD 0.2775 input and USD 1.11 output at Featherless; median of 4 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 M2.1 and MiniMax M2?
3 providers have a standard price for both: Featherless (USD 0.525 and USD 0.4856 at 3:1), Amazon Bedrock (USD 0.525 and USD 0.525 at 3:1), GMI Cloud (USD 0.525 and USD 0.525 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.525 and USD 0.4856.
Which is cheaper for a coding agent or a chatbot, Minimax M2.1 or MiniMax M2?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 234.90 a month on Minimax M2.1 (GMI Cloud) against USD 234.90 on MiniMax M2 (Google Vertex AI), the same. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 34.02 a month on Minimax M2.1 (GMI Cloud) against USD 32.97 on MiniMax M2 (Featherless), a difference of USD 1.05. 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 M2.1 and MiniMax M2 change?
MiniMax M2 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 M2.1's, so the input:output ratio never changes the answer.
Do Minimax M2.1 and MiniMax M2 have cached input pricing?
Minimax M2.1 from USD 0.03 per 1M cached input tokens (GMI Cloud; 2 of 3 standard prices list a discount). MiniMax M2 from USD 0.03 per 1M cached input tokens (Google Vertex AI; 2 of 4 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 M2.1 or MiniMax M2?
Both go up to 204,800 tokens on the providers that state it.