MiniMax M3 API Pricing
Verified standard token pricing for MiniMax M3, with official-source evidence and computed workload costs.
As of Nov 9, 2026, MiniMax M3 costs $0.30 per 1M input and $1.20 per 1M output tokens, $0.06 cached input. At standard non-cached rates, 10,000 monthly requests using 800 input and 300 output tokens each cost about $6.00, before retries, tools, storage, or provider-specific discounts.
| Model | Input $/1M | Cached input $/1M | Output $/1M | Source | Last verified How we verify |
|---|---|---|---|---|---|
| MiniMax M3 | $0.30 | $0.06 | $1.20 | Official source | Nov 9, 2026 |
Prices from official provider pages, verified on the date shown.
Interactive estimate
MiniMax M3 cost calculator
Enter your monthly requests and tokens per request to estimate MiniMax M3 API cost with the verified standard prices on this page. For several models, cached input or a full monthly budget, use the AI API Cost Calculator.
- Per request
- $0.0006
- Per month
- $6.00
- Per year
- $72.00
MiniMax M3 at standard non-cached rates: input tokens x input price + output tokens x output price, per 1M tokens. Long-context pricing applies per request: this prompt size is priced at the ≤524,288 prompt tokens rate. Retries, tools and cached input are not included.
Official source detail
Full pricing details
Standard prices are shown per 1M tokens. Provider-specific tiers, components, Batch rates, and time schedules remain separate below.
Long-context pricing tiers
| Tier | Input | Cached input | Output |
|---|---|---|---|
| Long context | $0.60 | $0.12 | $2.40 |
| Short context | $0.30 | $0.06 | $1.20 |
Published pricing components
| Mode and context | Input | Cached input | Output |
|---|---|---|---|
| Standard · Short context (≤524,288) | $0.30 | $0.06 | $1.20 |
| Standard · Long context (>524,288) | $0.60 | $0.12 | $2.40 |
| Priority · Short context (≤524,288) | $0.45 | $0.09 | $1.80 |
| Priority · Long context (>524,288) | $0.90 | $0.18 | $3.60 |
Computed examples
What it costs for real workloads
| Workload | Monthly volume | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|---|
| Side project | 1,000 requests/month | 800,000 | 300,000 | $0.60 |
| Side project | 10,000 requests/month | 8,000,000 | 3,000,000 | $6.00 |
| Side project | 100,000 requests/month | 80,000,000 | 30,000,000 | $60.00 |
| Customer support chatbot | 10,000 conversations/month | 121,650,000 | 10,800,000 | $49.46 |
| Agent task | 1,000 tasks/month | 12,000,000 | 3,200,000 | $7.44 |
Assumptions
- Side project: 800 input and 300 output tokens per request at 1,000, 10,000, and 100,000 requests per month.
- Customer support chatbot: 6 replies per conversation, 600 system tokens, 90 user-message tokens, 1,000 retrieved-context tokens, 180 output tokens per reply, and 50% history carry, for 10,000 conversations.
- Agent task: 8 model calls per task, 1,500 input and 400 output tokens per call, for 1,000 tasks.
- Standard rows use non-cached, non-batch prices. A Batch row appears only when both published Batch token prices exist.
Same-provider context
MiniMax M3 in the MiniMax lineup
- MiniMax M3 ranks 2nd of 2 current MiniMax models on this site by blended price (3 input tokens : 1 output token), from lowest to highest.
- The next lower-priced MiniMax option, MiniMax M3.1 Flash, costs 50% less for the 10,000-request side-project workload ($3.00 vs $6.00).
- Output tokens cost 4× input tokens, so long answers and generated code move the bill more than prompt length does.
- Cached input is billed at $0.06 per 1M tokens, 80% below standard input, which matters when the same system prompt or documents repeat across requests.
- The verified pricing data lists no Batch price for MiniMax M3.
| MiniMax model | Input / 1M | Output / 1M | Side project, 10k requests |
|---|---|---|---|
| MiniMax M3.1 Flash | $0.15 | $0.60 | $3.00 |
| MiniMax M3 (this page) | $0.30 | $1.20 | $6.00 |
Verified changes
Price history
On Jun 1, 2026, MiniMax added MiniMax M3 with published input $0.30 and output $1.20 per 1M tokens.
View this update in the price monitor
Availability evidence
Lifecycle
- Status
- active
- Release date
- Jun 1, 2026
- Pricing basis
- Standard list price
Nearby blended prices
Compare with
Alternatives are nearest by a 3:1 input-to-output blended token price, with same-provider coverage when available.
| Model | Input / 1M | Output / 1M | Side project, 10k requests |
|---|---|---|---|
| MiniMax M3.1 Flash | $0.15 | $0.60 | $3.00 |
| DeepSeek V4.1 Flash | $0.30 | $1.20 | $6.00 |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | $6.50 |
Next steps
Related
Common questions
Frequently asked questions
How much does MiniMax M3 cost per million tokens?
MiniMax M3 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens.
Does MiniMax M3 have cached input pricing?
Yes. The published cached-input price is $0.06 per 1M tokens.
How much does MiniMax M3 cost for 10,000 requests a month?
Using 800 input and 300 output tokens per request at standard non-cached rates, 10,000 monthly requests cost about $6.00.
Where does this MiniMax M3 price come from?
The prices come from MiniMax's official pricing source and were verified on Nov 9, 2026.
See the pricing verification methodology.