MiniMax M3 API pricing
MiniMax · Budget price tier · MiniMax Community License · released 2026-06. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $105.00 on MiniMax M3; the next cheaper model in the Budget price tier for this workload, Llama 4 Maverick, does it for $102.50. MiniMax M3 has held the same list price since 2026-08-15 and is the 127th cheapest of 160 models in the Budget price tier. Buying from CoreWeave rather than at the price we quote lowers the token price by about 20%, for a quantized fp4 build. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.30 per 1M tokens
- Output: $1.20 per 1M tokens
- Batch API (in/out): $0.224 / $0.88 per 1M tokens
- Prompt-cache read: $0.06 per 1M tokens
- Context window: 1M tokens
- Arena ELO: 1428 as of 2026-11-08
Available on
Direct API, OpenRouter
Curated by hand; check with the provider before committing.
Market position
On blended price ($0.93 per 1M tokens at 30% input, 70% output) it is cheaper than 19% of models in the Budget price tier: 127th cheapest of 160, tied with 3 others. Across every price tier it is cheaper than 57% of priced text models in the catalogue: 127th cheapest of 303, tied with 3 others. Its Arena ELO of 1428 ranks 69th of the 160 models that carry one, tied with 2 others, above 56% of them. With an Arena score of 1428, MiniMax M3 clears OptimNow's Standard working quality threshold: Standard (Arena 1420+), used for meeting summary, invoice processing and call summary. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
MiniMax M3 is open weights, which is not the same as open source: the weights are published, but under MiniMax Community License, a licence that restricts some uses. Read it before self-hosting commercially. Its parameter count is not published. Listed capabilities: Text, Vision, Reasoning, Agents. Filling its 1M context window once costs $0.30 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 7 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Cheapest host: CoreWeave at $0.23 input / $0.96 output per 1M tokens, 20% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp4 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $82.50 there against $105.00 at the price we quote, a difference of $22.50 a month. The dearest, Parasail, charges 1.3x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| CoreWeave | $0.23 | $0.96 | fp4 |
| GMICloud | $0.24 | $0.96 | fp8 |
| DeepInfra | $0.28 | $1.10 | fp8 |
| Minimax (model maker, price we quote) | $0.30 | $1.20 | not declared |
| StreamLake (price we quote) | $0.30 | $1.20 | fp8 |
| Venice (price we quote) | $0.30 | $1.20 | fp8 |
| Parasail (price we quote) | $0.30 | $1.20 | fp8 |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest. These listings are promotional rates, below the host's standard rate: GMICloud's, 20% off; and StreamLake's, 50% off.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where MiniMax publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $83 – $105 |
| Knowledge Q&A | 2,000 / 800 | $122 – $156 |
| Meeting Summary | 10,000 / 1,200 | $313 – $444 |
| Marketing Content | 2,500 / 1,800 | $279 – $291 |
| Coding Task | 3,000 / 2,000 | $294 – $330 |
| Invoice Processing | 1,500 / 600 | $79 – $117 |
| Call Summary | 2,000 / 700 | $103 – $144 |
| Agent Workflow | 6,000 / 3,000 | $439 – $540 |
Price history
MiniMax M3 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.30 input / $1.20 output per 1M tokens. No list price change since tracking began on 2026-08-15. Last checked against the 2026-11-12 snapshot.
Alternatives to MiniMax M3
3 of the 4 comparable models below cost less than MiniMax M3: DeepSeek V3.2 undercuts it by 63%, for 3 Arena points less.
- Next cheaper model in the Budget price tier: GPT-5.6 Luna (OpenAI) at $0.90 blended, 3% less.
- Next more expensive: GPT-5.4 Nano (OpenAI) at $0.935 blended, 1% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against MiniMax M3.
- Mistral Large 3 2512 (Mistral): $0.50 in / $1.50 out per 1M, Arena ELO 1429 (29% more expensive, 1 ELO point higher)
- GPT-5.6 Luna (OpenAI): $0.20 in / $1.20 out per 1M, Arena ELO 1431 (3% cheaper, 3 ELO points higher)
- Beam 1.0 501B A23B (reflection): $0.30 in / $1.00 out per 1M, Arena ELO 1425 (15% cheaper, 3 ELO points lower)
- DeepSeek V3.2 (DeepSeek): $0.26 in / $0.38 out per 1M, Arena ELO 1425 (63% cheaper, 3 ELO points lower)
- Cheapest within 15 Arena points: Gemma 4 26B A4B (Google), 90% cheaper, 6 ELO points higher, out of 40 models in that band.
- Highest Arena ELO within 20% of this price: GLM 5.3 (Zhipu), 8% more expensive, 48 ELO points higher, out of 16 models in that price band.
MiniMax M3 head to head
Other models from MiniMax
MiniMax has 3 other models in the catalogue. Prices per 1M tokens, input then output.
- MiniMax M3.1 Flash: $0.15 / $0.60
- MiniMax M2.7: $0.21 / $0.84
- MiniMax M2.5: $0.27 / $1.08
All 4 MiniMax models and prices
Common questions about MiniMax M3 pricing
- How much does MiniMax M3 cost?
- MiniMax M3 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens. That is the model maker's own rate (Minimax). Prices as listed on 2026-11-12.
- Which host is cheapest for MiniMax M3?
- Cheapest host: CoreWeave at $0.23 input / $0.96 output per 1M tokens, 20% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp4 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $82.50 there against $105.00 at the price we quote, a difference of $22.50 a month. The dearest, Parasail, charges 1.3x the cheapest. Host rates as listed on 2026-11-12.
- Does MiniMax M3 offer batch or cached pricing?
- Yes, both. Batch API pricing is $0.224 per 1M input tokens and $0.88 per 1M output tokens, and prompt-cache reads cost $0.06 per 1M tokens, as listed on 2026-11-12.
- What would MiniMax M3 cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $105 on MiniMax M3 at the list price quoted on 2026-11-12.
- Can MiniMax M3 be self-hosted?
- Yes, within the terms of its licence. MiniMax M3 is open weights, which is not the same as open source: the weights are published, but under MiniMax Community License, a licence that restricts some uses. Read it before self-hosting commercially.
- Has the price of MiniMax M3 changed?
- MiniMax M3 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.30 input / $1.20 output per 1M tokens. No list price change since tracking began on 2026-08-15. Last checked against the 2026-11-12 snapshot.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server