MiniMax · MiniMax-M2.5 official price: not yet recorded. Cheapest inference provider: DigitalOcean, input 0.315, output 1.26 USD per million tokens. This is the price via OpenRouter with a 5% fee added, original price × 1.05. Original price: input 0.3, output 1.2. Cheapest relay: code-cli.cn, group "Mini-MAX" 0.18375 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-11-14). 97 sites have comparable prices; 218 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: price listed by OpenRouter for this provider (endpoint digitalocean)
Price ranges per million tokens
Inference provider cash prices · Lowest 0.55125 · median 0.55125 · highest 0.55125 · 1 quotes USD / per million tokens
Relay CNY credit prices · Lowest 0.25 · median 3.3075 · highest 21.058 · 22 quotes CNY / per million tokens, site credit
Relay USD credit prices · Lowest 0.18375 · median 1.8375 · highest 6.615 · 43 quotes USD / per million tokens, site credit
Each quote is blended into one price by this workload: ordinary input 75% · cache read 0% · output 25% · cache write 0%. Only prices in effect now are counted.
Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.
Inference providers
For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.
Provider
Tariff
Input
Output
Cache read
Cache write
Via OpenRouter with 5% fee
Unit
Observed
Conditions and source
DigitalOcean
Standard
0.3
1.2
0.06
—
Input 0.315
Output 1.26
Cache read 0.063
Original price × 1.05
USD / 1M tokens
price listed by OpenRouter for this provider (endpoint digitalocean)Full price conditions
These providers serve lower-precision builds such as fp8 and fp4. Prices are lower and output may differ from the original model.
For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.
Provider
Tariff
Input
Output
Cache read
Cache write
Via OpenRouter with 5% fee
Unit
Observed
Conditions and source
AtlasCloud · fp8 quantized
Standard
0.295
1.2
0.06
—
Input 0.30975
Output 1.26
Cache read 0.063
Original price × 1.05
USD / 1M tokens
Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint atlas-cloud/fp8)Full price conditions
{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"input": "0.000000295",
"output": "0.0000012"
},
"conditions": [
"Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"quantization: fp8",
"price listed by OpenRouter for this provider (endpoint atlas-cloud/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}
Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint gmicloud/fp8)Full price conditions
{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000003",
"input": "0.0000003",
"output": "0.0000012"
},
"conditions": [
"Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"quantization: fp8",
"price listed by OpenRouter for this provider (endpoint gmicloud/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}
Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint atlas-cloud/fp8)Full price conditions
{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"input": "0.000000295",
"output": "0.0000012"
},
"conditions": [
"Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"quantization: fp8",
"price listed by OpenRouter for this provider (endpoint atlas-cloud/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}
Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint gmicloud/fp8)Full price conditions
{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000003",
"input": "0.0000003",
"output": "0.0000012"
},
"conditions": [
"Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"quantization: fp8",
"price listed by OpenRouter for this provider (endpoint gmicloud/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}
Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.
Default channel - best value for money, most recommended, has claude series models, no gpt or gemini [machine translation]Original: 默认渠道 - 性价比最高最推荐,有claude系列模型,没有gpt和gemini
Deepseek stable channel, Chinese model, strong coding ability, very high value for money, 60% of list price, rate multiplier 0.6 [machine translation]Original: Deepseek稳定渠道,国产模型,代码能力强,性价比极高,6折,倍率0.6
All per-token prices: 128,524 prices from 1,383 sites (about 1,275 companies). 109,485 are ranked, from 1,349 sites (about 1,244 companies); 19,039 more are listed separately and not ranked. Prices collected up to 2026-11-15.
This model has 458 recorded prices; 161 can be compared directly (159 ranked, 2 listed separately). Not comparable yet: price not parsed yet 153, ratio looks unset 63, display unit not confirmed 27, billed per request or another unit 14, scope of the official doc price not confirmed 8, new price under review; showing the previous one 3. 23 more are tiered by rules and compared on the Tiered prices board
91 recent · 19 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table.
Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.
“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.
These manufacturer statements do not verify relay backends, availability, GPU ownership or cash eligibility. Aliases are never merged automatically.
MiniMax-M2.5
Manufacturer-declared status
Retired (retirement date 2026-11-18 has passed)
New-user access cutoff
2026-10-19
Model retirement date
2026-11-18
Existing pay-as-you-go users can continue until retirement; M Plan / Token Plan compatible names route to M3.1 Flash Preview from 2026-10-19. This route change is plan-specific, not a universal identity alias.
The vendor has stopped this model, or its stated retirement date has passed. This does not mean a paid test call failed.
Complete declarations and historical observations
{
"author": "MiniMax",
"availability": "EXISTING_PAYG_USERS_ONLY_PENDING_RETIREMENT",
"decision": "ADD_GROUP",
"documentedAliases": [],
"entityId": "minimax/minimax-m2.5",
"evidenceKeys": [
"minimax-models",
"minimax-sdk"
],
"newUserAccessStopsOn": "2026-10-19",
"note": "Existing pay-as-you-go users can continue until retirement; M Plan / Token Plan compatible names route to M3.1 Flash Preview from 2026-10-19. This route change is plan-specific, not a universal identity alias.",
"officialId": "MiniMax-M2.5",
"qualificationEffect": "NONE_NAME_DECLARATION_ONLY",
"retirementDate": "2026-11-18",
"sourceUrls": [
"https://platform.minimax.cn/docs/guides/models-intro",
"https://platform.minimax.cn/docs/api-reference/text-anthropic-api"
],
"verifiedOn": "2026-10-19",
"w42ObservedAt": [
"2026-10-17T04:01:32.471Z"
],
"w42OfficialPriceNames": [
"MiniMax-M2.5"
],
"w42OfficialPriceRows": 1
}