MiniMax M2.5 API pricing
MiniMax · Budget price tier · Modified MIT · released 2026-02. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
Promotional rate. The price we quote is 10% off StreamLake's standard $0.30 per 1M input tokens and $1.20 per 1M output tokens, and a promotion can end without notice.
A support ticket workload of 100K requests a month costs $94.50 on MiniMax M2.5; the next cheaper model in the Budget price tier for this workload, Qwen3 VL 30B A3B Thinking, does it for $93.50. The price we quote for MiniMax M2.5 has changed 8 times since 2026-08-15, most recently on 2026-11-11 when the quoted host changed (-10.0%); it is now the 120th cheapest of 160 models in the Budget price tier. Buying from Venice rather than at the price we quote lowers the token price by about 11%. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.27 per 1M tokens
- Output: $1.08 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.027 per 1M tokens
- Context window: 200K tokens
- Arena ELO: 1359 as of 2026-11-08
Available on
AWS Bedrock regions: ap-northeast-1, eu-central-1, eu-west-1, us-east-1, us-east-2, us-west-2
Market position
On blended price ($0.837 per 1M tokens at 30% input, 70% output) it is cheaper than 25% of models in the Budget price tier: 120th cheapest of 160. Across every price tier it is cheaper than 61% of priced text models in the catalogue: 120th cheapest of 303. Its Arena ELO of 1359 ranks 120th of the 160 models that carry one, above 25% of them. With an Arena score of 1359, MiniMax M2.5 sits below OptimNow's lowest working quality threshold, Standard (Arena 1420+), so the quality-bar method would not shortlist it for any of the 8 use cases the table prices. 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 M2.5 is open weights, which is not the same as open source: the weights are published, but under Modified MIT, a licence that restricts some uses. Read it before self-hosting commercially. Its published size is 230B parameters. Listed capabilities: Text, Reasoning, Agents. Filling its 200K context window once costs $0.054 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 5 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: Venice at $0.27 input / $0.95 output per 1M tokens, 11% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $88.00 there against $94.50 at the price we quote, a difference of $6.50 a month. The dearest, DigitalOcean, charges 1.2x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| Venice | $0.27 | $0.95 | not declared |
| StreamLake (price we quote) | $0.27 | $1.08 | not declared |
| AtlasCloud | $0.295 | $1.20 | fp8 |
| GMICloud | $0.30 | $1.20 | fp8 |
| DigitalOcean | $0.30 | $1.20 | not declared |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. StreamLake's listing is a promotional rate: 10% off its standard rate.
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 | $73 – $95 |
| Knowledge Q&A | 2,000 / 800 | $106 – $140 |
| Meeting Summary | 10,000 / 1,200 | $375 – $400 |
| Marketing Content | 2,500 / 1,800 | $250 – $262 |
| Coding Task | 3,000 / 2,000 | $261 – $297 |
| Invoice Processing | 1,500 / 600 | $94 – $105 |
| Call Summary | 2,000 / 700 | $125 – $130 |
| Agent Workflow | 6,000 / 3,000 | $384 – $486 |
Price history
MiniMax M2.5 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.22 input / $0.90 output per 1M tokens. The price we quote has changed 8 times since then, 5 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-11, was -10.0% on the blended price (30% input, 70% output), to $0.27 input / $1.08 output (quoted host changed, not a repricing). Net of all changes, the blended price is +20.3% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-11-11 | $0.30 / $1.20 | $0.27 / $1.08 | -10.0% (quoted host changed, not a repricing) |
| 2026-11-08 | $0.27 / $0.95 | $0.30 / $1.20 | +24.7% (quoted host changed, not a repricing) |
| 2026-11-01 | $0.30 / $1.20 | $0.27 / $0.95 | -19.8% (quoted host changed, not a repricing) |
| 2026-10-24 | $0.27 / $0.95 | $0.30 / $1.20 | +24.7% (quoted host changed, not a repricing) |
| 2026-10-15 | $0.27 / $1.08 | $0.27 / $0.95 | -10.9% (quoted host changed, not a repricing) |
3 earlier changes are not listed.
Alternatives to MiniMax M2.5
4 of the 4 comparable models below cost less than MiniMax M2.5: Gemma 3 27B undercuts it by 68%, for 1 Arena point less.
- Next cheaper model in the Budget price tier: GLM 4.5 Air (Zhipu) at $0.83 blended, 1% less.
- Next more expensive: Qwen3.6 Flash (Alibaba) at $0.8438 blended, 1% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against MiniMax M2.5.
- Gemma 3 27B (Google): $0.08 in / $0.35 out per 1M, Arena ELO 1358 (68% cheaper, 1 ELO point lower)
- Qwen3 Coder 480B A35B (Alibaba): $0.30 in / $1.00 out per 1M, Arena ELO 1357 (6% cheaper, 2 ELO points lower)
- gpt-oss-120b (OpenAI): $0.15 in / $0.60 out per 1M, Arena ELO 1365 (44% cheaper, 6 ELO points higher)
- GLM 4.7 Flash (Zhipu): $0.0605 in / $0.40 out per 1M, Arena ELO 1351 (64% cheaper, 8 ELO points lower)
- Cheapest within 15 Arena points: Nemotron 3 Nano 30B A3B (Nvidia), 78% cheaper, 11 ELO points lower, out of 11 models in that band.
- Highest Arena ELO within 20% of this price: MiMo-V2.6-Pro (Xiaomi), 12% cheaper, 133 ELO points higher, out of 23 models in that price band.
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 M3: $0.30 / $1.20
All 4 MiniMax models and prices
Common questions about MiniMax M2.5 pricing
- How much does MiniMax M2.5 cost?
- MiniMax M2.5 costs $0.27 per 1M input tokens and $1.08 per 1M output tokens at StreamLake, the host whose rate we quote. Prices as listed on 2026-11-12.
- Which host is cheapest for MiniMax M2.5?
- Cheapest host: Venice at $0.27 input / $0.95 output per 1M tokens, 11% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $88.00 there against $94.50 at the price we quote, a difference of $6.50 a month. The dearest, DigitalOcean, charges 1.2x the cheapest. Host rates as listed on 2026-11-12.
- Does MiniMax M2.5 offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.027 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would MiniMax M2.5 cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $95 on MiniMax M2.5 at the list price quoted on 2026-11-12.
- Can MiniMax M2.5 be self-hosted?
- Yes, within the terms of its licence. MiniMax M2.5 is open weights, which is not the same as open source: the weights are published, but under Modified MIT, a licence that restricts some uses. Read it before self-hosting commercially.
- Has the price of MiniMax M2.5 changed?
- MiniMax M2.5 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.22 input / $0.90 output per 1M tokens. The price we quote has changed 8 times since then, 5 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-11, was -10.0% on the blended price (30% input, 70% output), to $0.27 input / $1.08 output (quoted host changed, not a repricing). Net of all changes, the blended price is +20.3% against 2026-08-15.
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