API PRICES
MiniMax · MiniMax-M3
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 2.1 / output 8.4 CNY/million tokensMiniMax ·
- Lowest inference provider (cash)
- Input 0.315 / output 1.26 USD/million tokensOpenRouter · Aggregator · Via OpenRouter with 5% fee, original price × 1.05 ·
- Lowest relay (credit)
- 0.059063 USD credit/million total tokenswww.xpivot.top "国模二梯队" ·
Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.
All official and inference price observations
MiniMax · MiniMax-M3 official price: input 2.1, output 8.4 CNY per million tokens (MiniMax, observed 2026-11-13). Cheapest inference provider: OpenRouter, 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: www.xpivot.top, group "国模二梯队 (Not yet translated)" 0.059063 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-11-14). 110 sites have comparable prices; 465 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: Context tier: PROMPT_LE_512K · promptLength: ≤ 512k 输入 tokens · OpenRouter lists only quantized deployments of this model (fp4, fp8); they are listed separately. This is OpenRouter's single price, and it is compared.
Price ranges per million tokens
Official cash prices · Lowest 3.675 · median 3.675 · highest 3.675 · 1 quotes CNY / 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 0.15 · median 0.83475 · highest 14.7 · 44 quotes CNY / per million tokens, site credit
Relay USD credit prices · Lowest 0.059063 · median 1.0888 · highest 20 · 88 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 price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| MiniMax | Standard | 2.1 | 8.4 | 0.42 | — | CNY / 1M tokens | Context tier: PROMPT_LE_512K · promptLength: ≤ 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_512K",
"processingMode": null,
"conditionNotes": [
"promptLength: ≤ 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
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 | vs official |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator · Single price | Standard | 0.3 | 1.2 | 0.06 | — | Input 0.315 Output 1.26 Cache read 0.063 Original price × 1.05 | USD / 1M tokens | OpenRouter lists only quantized deployments of this model (fp4, fp8); they are listed separately. This is OpenRouter's single price, and it is compared.Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"input": "0.0000003",
"output": "0.0000012"
},
"conditions": [
"OpenRouter lists only quantized deployments of this model (fp4, fp8); they are listed apart from full-precision prices, so this single price is compared (R97)"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Inference providers (quantized deployments)
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 | vs official |
|---|---|---|---|---|---|---|---|---|---|---|
| CoreWeave · fp4 quantized | Standard | 0.23 | 0.96 | 0.05 | — | Input 0.2415 Output 1.008 Cache read 0.0525 Original price × 1.05 | USD / 1M tokens | Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices · quantization: fp4 · price listed by OpenRouter for this provider (endpoint coreweave/fp4)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000005",
"input": "0.00000023",
"output": "0.00000096"
},
"conditions": [
"Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"quantization: fp4",
"price listed by OpenRouter for this provider (endpoint coreweave/fp4)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| GMICloud · fp8 quantized | Standard | 0.24 | 0.96 | 0.048 | — | Input 0.252 Output 1.008 Cache read 0.0504 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 gmicloud/fp8)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.000000048",
"input": "0.00000024",
"output": "0.00000096"
},
"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
}Official source | ||
| DeepInfra · fp8 quantized | Standard | 0.28 | 1.1 | 0.056 | — | Input 0.294 Output 1.155 Cache read 0.0588 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 deepinfra/fp8)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.000000056",
"input": "0.00000028",
"output": "0.0000011"
},
"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 deepinfra/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Parasail · fp8 quantized | Standard | 0.3 | 1.2 | 0.06 | — | Input 0.315 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 parasail/fp8)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"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 parasail/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Venice · fp8 quantized | Standard | 0.3 | 1.2 | 0.06 | — | Input 0.315 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 venice/fp8)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"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 venice/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Other tariffs and prices to review
Official price
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 |
|---|---|---|---|---|---|---|---|---|---|
| MiniMax | Standard | 4.2 | 16.8 | 0.84 | — | CNY / 1M tokens | Context tier: PROMPT_GT_512K · footnote mark on the prompt-length tier; no note next to the table · promptLength: > 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"footnote mark on the prompt-length tier; no note next to the table"
],
"contextTier": "PROMPT_GT_512K",
"processingMode": null,
"conditionNotes": [
"promptLength: > 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| MiniMax | Other tariff | 3.15 | 12.6 | 0.63 | — | CNY / 1M tokens | Context tier: PROMPT_LE_512K · Priority processing · processingMode: priority (tab 优先) · promptLength: ≤ 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"processingMode: priority (tab 优先)"
],
"contextTier": "PROMPT_LE_512K",
"processingMode": "priority",
"conditionNotes": [
"promptLength: ≤ 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| MiniMax | Other tariff | 6.3 | 25.2 | 1.26 | — | CNY / 1M tokens | Context tier: PROMPT_GT_512K · Priority processing · processingMode: priority (tab 优先) · promptLength: > 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"processingMode: priority (tab 优先)"
],
"contextTier": "PROMPT_GT_512K",
"processingMode": "priority",
"conditionNotes": [
"promptLength: > 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Minimax | Standard | 0.3 | 1.2 | 0.06 | — | Input 0.315 Output 1.26 Cache read 0.063 Original price × 1.05 | USD / 1M tokens | Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · price listed by OpenRouter for this provider (endpoint minimax)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"input": "0.0000003",
"output": "0.0000012"
},
"conditions": [
"Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"price listed by OpenRouter for this provider (endpoint minimax)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
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 |
|---|---|---|---|---|---|---|---|---|---|
| Fireworks AI | Standard | 0.3 | 1.2 | 0.06 | — | USD / 1M tokens | Standard processing · processingMode: STANDARDFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"processingMode: STANDARD"
],
"contextTier": null,
"processingMode": "standard",
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Fireworks AI | Other tariff | 0.45 | 1.8 | 0.09 | — | USD / 1M tokens | Priority processing · processingMode: PRIORITYFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"processingMode: PRIORITY"
],
"contextTier": null,
"processingMode": "priority",
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| OpenRouter · Aggregator | Batch | 0.224 | 0.88 | 0.0448 | — | Input 0.2352 Output 0.924 Cache read 0.04704 Original price × 1.05 | USD / 1M tokens | OpenRouter batch variantFull price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000000448",
"input": "0.000000224",
"output": "0.00000088"
},
"conditions": [
"OpenRouter batch variant"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| DeepInfra | Other tariff | 0.224 | 0.88 | 0.0448 | — | Input 0.2352 Output 0.924 Cache read 0.04704 Original price × 1.05 | USD / 1M tokens | OpenRouter endpoint variant: flex · Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint deepinfra/fp8/flex)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000000448",
"input": "0.000000224",
"output": "0.00000088"
},
"conditions": [
"OpenRouter endpoint variant: flex",
"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 deepinfra/fp8/flex)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| CoreWeave | Standard | 0.23 | 0.96 | 0.05 | — | Input 0.2415 Output 1.008 Cache read 0.0525 Original price × 1.05 | USD / 1M tokens | Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices · quantization: fp4 · price listed by OpenRouter for this provider (endpoint coreweave/fp4)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000005",
"input": "0.00000023",
"output": "0.00000096"
},
"conditions": [
"Quantized deployment (fp4) served through OpenRouter; listed apart from full-precision prices"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"quantization: fp4",
"price listed by OpenRouter for this provider (endpoint coreweave/fp4)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| GMICloud | Standard | 0.24 | 0.96 | 0.048 | — | Input 0.252 Output 1.008 Cache read 0.0504 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 gmicloud/fp8)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.000000048",
"input": "0.00000024",
"output": "0.00000096"
},
"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
}Official source | |
| DeepInfra | Standard | 0.28 | 1.1 | 0.056 | — | Input 0.294 Output 1.155 Cache read 0.0588 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 deepinfra/fp8)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.000000056",
"input": "0.00000028",
"output": "0.0000011"
},
"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 deepinfra/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| Venice | Standard | 0.3 | 1.2 | 0.06 | — | Input 0.315 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 venice/fp8)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"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 venice/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| Parasail | Standard | 0.3 | 1.2 | 0.06 | — | Input 0.315 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 parasail/fp8)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"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 parasail/fp8)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| Parasail | Other tariff | 0.45 | 1.8 | 0.09 | — | Input 0.4725 Output 1.89 Cache read 0.0945 Original price × 1.05 | USD / 1M tokens | OpenRouter endpoint variant: fast · Quantized deployment (fp8) served through OpenRouter; listed apart from full-precision prices · quantization: fp8 · price listed by OpenRouter for this provider (endpoint parasail/fast)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000009",
"input": "0.00000045",
"output": "0.0000018"
},
"conditions": [
"OpenRouter endpoint variant: fast",
"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 parasail/fast)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Older official and inference provider prices
Earlier price observations and their original conditions
Official price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| MiniMax | Standard | 2.1 | 8.4 | 0.42 | — | CNY / 1M tokens | Context tier: PROMPT_LE_512K · Standard processing · promptLength: ≤ 512k 输入 tokens · processingMode: standardFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_512K",
"processingMode": "standard",
"conditionNotes": [
"promptLength: ≤ 512k 输入 tokens",
"processingMode: standard"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| MiniMax | Other tariff | 3.15 | 12.6 | 0.63 | — | CNY / 1M tokens | Context tier: PROMPT_LE_512K · Priority processing · processingMode: priority · service_tier=priority; page states priority admission and 1.5 times standard pricing · promptLength: ≤ 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"processingMode: priority",
"service_tier=priority; page states priority admission and 1.5 times standard pricing"
],
"contextTier": "PROMPT_LE_512K",
"processingMode": "priority",
"conditionNotes": [
"promptLength: ≤ 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| MiniMax | Standard | 4.2 | 16.8 | 0.84 | — | CNY / 1M tokens | Context tier: PROMPT_GT_512K · Standard processing · footnote marker on prompt-length tier; page footnote describes priority service · promptLength: > 512k 输入 tokens · processingMode: standardFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"footnote marker on prompt-length tier; page footnote describes priority service"
],
"contextTier": "PROMPT_GT_512K",
"processingMode": "standard",
"conditionNotes": [
"promptLength: > 512k 输入 tokens",
"processingMode: standard"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| MiniMax | Other tariff | 6.3 | 25.2 | 1.26 | — | CNY / 1M tokens | Context tier: PROMPT_GT_512K · Priority processing · processingMode: priority · service_tier=priority; page states priority admission and 1.5 times standard pricing · promptLength: > 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"processingMode: priority",
"service_tier=priority; page states priority admission and 1.5 times standard pricing"
],
"contextTier": "PROMPT_GT_512K",
"processingMode": "priority",
"conditionNotes": [
"promptLength: > 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| MiniMax | Standard | 2.1 | 8.4 | 0.42 | — | CNY / 1M tokens | Context tier: PROMPT_LE_512K · promptLength: ≤ 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_512K",
"processingMode": null,
"conditionNotes": [
"promptLength: ≤ 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| MiniMax | Other tariff | 3.15 | 12.6 | 0.63 | — | CNY / 1M tokens | Context tier: PROMPT_LE_512K · Priority processing · processingMode: priority (tab 优先) · promptLength: ≤ 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"processingMode: priority (tab 优先)"
],
"contextTier": "PROMPT_LE_512K",
"processingMode": "priority",
"conditionNotes": [
"promptLength: ≤ 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| MiniMax | Standard | 4.2 | 16.8 | 0.84 | — | CNY / 1M tokens | Context tier: PROMPT_GT_512K · footnote mark on the prompt-length tier; no note next to the table · promptLength: > 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"footnote mark on the prompt-length tier; no note next to the table"
],
"contextTier": "PROMPT_GT_512K",
"processingMode": null,
"conditionNotes": [
"promptLength: > 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| MiniMax | Other tariff | 6.3 | 25.2 | 1.26 | — | CNY / 1M tokens | Context tier: PROMPT_GT_512K · Priority processing · processingMode: priority (tab 优先) · promptLength: > 512k 输入 tokensFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"processingMode: priority (tab 优先)"
],
"contextTier": "PROMPT_GT_512K",
"processingMode": "priority",
"conditionNotes": [
"promptLength: > 512k 输入 tokens"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Inference providers
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| Together AI | Standard | 0.3 | 1.2 | 0.06 | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| OpenRouter · Aggregator | Standard | 0.3 | 1.2 | 0.06 | — | USD / 1M tokens | Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.00000006",
"input": "0.0000003",
"output": "0.0000012"
},
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 0.059063 · median 1.0888 · highest 20 (88 quotes, USD credits per million total tokens)
Relays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑USD credits / 1M | Output USD credits / 1M | Cache readUSD credits / 1M | BlendedUSD credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 76 | zen-ai.topAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 2 plans | deepseek Name on site: minimax-m3 deepseek group, official 6-zhe (60% of original price) [machine translation]Original: deepseek分组, 官方6折 Operator pending verification | 2.52 | 10.08 | — | 4.414.1× the median price | Details |
| 77 | fanapi.cbbmax.comAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 5 plans | 国模合集-自部署-特价 (Not yet translated) Name on site: minimax-m3 国模合集-自部署-特价 (Not yet translated) Operator pending verification | 3.045 | 12.18 | 0.609 | 5.32884.9× the median price | Details |
| 78 | gpt-agent.ccAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 4 plans 1 more site of the same companyBasis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | codex codex group [machine translation]Original: codex 分组 Operator pending verification | 4 | 20 | 0.4 | 87.3× the median price | Details |
| 78 | api.llm-token.cnAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 4 plans 1 more site of the same company
Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | codex codex group [machine translation]Original: codex 分组 Operator pending verification | 4 | 20 | 0.4 | 87.3× the median price | Details |
| 80 | xiaoma.bestAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 2 plans | default 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 Operator pending verification | 4.2 | 16.8 | 0.84 | 7.356.8× the median price | Details |
| 80 | xiaoma.bestAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 2 plans | Chinese models [machine translation]Group on site: 国产模型 Operator pending verification | 4.2 | 16.8 | 0.84 | 7.356.8× the median price | Details |
| 82 | fanapi.cbbmax.comAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 5 plans | 国模合集-自部署 (Not yet translated) 国模合集-自部署 (Not yet translated) Operator pending verification | 4.305 | 17.22 | 0.861 | 7.53386.9× the median price | Details |
| 82 | fanapi.cbbmax.comAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 5 plans | 国模合集-自部署-三方-特价 (Not yet translated) Name on site: minimax-m3 自部署国模三方接入特价的总合集分组 (Not yet translated) Operator pending verification | 4.305 | 17.22 | 0.861 | 7.53386.9× the median price | Details |
| 84 | fanapi.cbbmax.comAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 5 plans | 国模合集-自部署-三方 (Not yet translated) Name on site: minimax-m3 自部署国模三方接入的总合集分组 (Not yet translated) Operator pending verification | 5.67 | 22.68 | 1.134 | 9.92259.1× the median price | Details |
| 85 | gpt-agent.ccAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 4 plans 1 more site of the same companyBasis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | agent agent Operator pending verification | 6 | 30 | 0.6 | 1211× the median price | Details |
| 85 | api.llm-token.cnAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 4 plans 1 more site of the same company
Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | agent agent Operator pending verification | 6 | 30 | 0.6 | 1211× the median price | Details |
| 87 | gpt-agent.ccAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 4 plans 1 more site of the same companyBasis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | Chinese models [machine translation]Group on site: 国产模型 Chinese models [machine translation]Original: 国产模型 Operator pending verification | 10 | 50 | 1 | 2018× the median price | Details |
| 87 | api.llm-token.cnAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 4 plans 1 more site of the same company
Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | Chinese models [machine translation]Group on site: 国产模型 Chinese models [machine translation]Original: 国产模型 Operator pending verification | 10 | 50 | 1 | 2018× the median price | Details |
| Older price | |||||||
| 01 | ai.baicloud.orgAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 2 plans | Chinese models [machine translation]Group on site: 国产模型 Name on site: minimax-m3 High-fidelity [upstream integration] [machine translation]Original: 保真【对接】 Operator pending verification | 0.0675 | 0.27 | 0.0135 | 0.11813The median price is 9.2× this price | Details |
| 02 | ai.baicloud.orgAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 2 plans | all Name on site: minimax-m3 All-rounder [self-operated] [machine translation]Original: 全能王【自营】 Operator pending verification | 0.225 | 0.9 | 0.045 | 0.39375The median price is 2.8× this price | Details |
| 03 | airouter.cloudAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 1 plans | default Default group [machine translation]Original: 默认分组 Operator pending verification | 0.6 | 2.4 | 0.12 | 1.05About the median price | Details |
| 04 | newapi.prorisehub.comAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 3 plans | Overseas Chinese coding models [machine translation]Group on site: 海外国产编程模 Name on site: minimax-m3 [Stability ⭐⭐⭐⭐⭐] Overseas open-source model channel, full-strength relay, full-strength coding models [machine translation]Original: 【稳定性⭐⭐⭐⭐⭐】海外开源模型渠道满血中转,满血版本编程模型 Operator pending verification | 1.09 | 4.36 | 0.218 | 1.90751.8× the median price | Details |
| 05 | api.wanapis.comAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 1 plans | default Name on site: minimax-m3 默认 · 全部模型可用 (Not yet translated) Operator pending verification | 2.1 | 8.4 | — | 3.6753.4× the median price | Details |
| 06 | newapi.prorisehub.comAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 3 plans | default Name on site: minimax-m3 ⚠️ Default general group: can call every model on the site, don't use it if you don't understand!!! Billing is very expensive!!! [machine translation]Original: ⚠️ 默认通用分组:可调用全站所有模型,不懂别用!!!计费很贵!!! Operator pending verification | 2.18 | 8.72 | 0.436 | 3.8153.5× the median price | Details |
| 07 | newapi.prorisehub.comAsk or discussCollected: Carried previous price Not updated this time; showing the previous price View 3 plans | OpenRouter-official relay [machine translation]Group on site: OpenRouter-官转 Name on site: minimax-m3 [Stability ⭐⭐⭐⭐⭐] openrouter official relay group, official not-dumbed-down full-strength experience [machine translation]Original: 【稳定性⭐⭐⭐⭐⭐】openrouter官方中转分组,官方不降智满血级体验 Operator pending verification | 2.616 | 10.464 | 0.5232 | 4.5784.2× the median price | Details |
| Flagged · not ranked · Recent price | |||||||
| — | www.xpivot.topAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 4 plans | 其他国模 (Not yet translated) Name on site: minimax-m3 Note: far from other providers’ prices. This price is not ranked or counted. Operator pending verification | 0.018 | 0.072 | 0.0036 | 0.0315The median price is 35× this price | Details |
| — | aimgen.techAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 1 plans | MiniMax分组(非视频) (Not yet translated) Note: far from other providers’ prices. This price is not ranked or counted. Operator pending verification | 0.024 | 0.096 | 0.0048 | 0.042The median price is 26× this price | Details |
| — | ai.gpt666claude.topAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 1 plans | 限时优惠gm (Not yet translated) Name on site: minimax-m3 站点写明为限时价格 Note: far from other providers’ prices. This price is not ranked or counted. Operator pending verification | 0.03 | 0.12 | 0.006 | 0.0525The median price is 21× this price | Details |
| — | zeekai-cn.ccAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 1 plans 1 more site of the same companyBasis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | cn_models Chinese models aggregated, usage-based [machine translation]Group on site: cn_models 国模聚合按量 Chinese multimodal models aggregated group, usage-based [machine translation]Original: 国产多模态模型聚合分组按量计费 Note: far from other providers’ prices. This price is not ranked or counted. Operator pending verification | 0.03 | 0.12 | 0.006 | 0.0525The median price is 21× this price | Details |
| — | api.zeekai-cn.ccAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 1 plans 1 more site of the same company
Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | cn_models Chinese models aggregated, usage-based [machine translation]Group on site: cn_models 国模聚合按量 Chinese multimodal models aggregated group, usage-based [machine translation]Original: 国产多模态模型聚合分组按量计费 Note: far from other providers’ prices. This price is not ranked or counted. Operator pending verification | 0.03 | 0.12 | 0.006 | 0.0525The median price is 21× this price | Details |
Special groups · 2 rows · not ranked
These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.
- Free declaration, listed separately: 1 rows
- near-zero-ratio group: 1 rows
- zero-ratio group: 1 rows
- ai.gpt666claude.top · Free group [machine translation]Group on site: 免费分组 · minimax-m3 · Input 0 / Output 0 USD credits / 1M
- api.cofinapi.top · 免费模型(不保证能用) (Not yet translated) · minimax-m3 · Input 0.021 / Output 0.084 USD credits / 1M
How this ranking works
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 875 recorded prices; 180 can be compared directly (177 ranked, 3 listed separately). Not comparable yet: price not parsed yet 280, ratio looks unset 77, new price under review; showing the previous one 29, billed per request or another unit 28, display unit not confirmed 27. 246 more are tiered by rules and compared on the Tiered prices board
122 recent · 7 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.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for MiniMax · MiniMax-M3?
www.xpivot.top, group "国模二梯队", 0.059063 USD credit per million total tokens, observed 2026-11-14. 110 sites have comparable prices.
What is the official price for MiniMax · MiniMax-M3?
Input 2.1, output 8.4 CNY per million tokens, checked 2026-11-13. Lowest inference provider: OpenRouter, 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.
How do I use MiniMax · MiniMax-M3 in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest MiniMax · MiniMax-M3 API to Claude Code for me". Install Skill →