
Provider pricing hub
MiniMax API pricing: M3, M3.1 Flash, M2.7 and highspeed.
MiniMax API prices on RouterPlex run from $0.15 per 1M input tokens (MiniMax M3.1 Flash) to $0.60, with 0% markup. Highspeed variants cost more than their standard twins. MiniMax M3.1 Flash, MiniMax M3 and MiniMax M3 Highspeed list 1M context. Top-ups have a $0 fee, by card from $5 or crypto; balances stop at $0 and each key has a hard USD cap.
Prices checked 17 November 2026 from the live catalog. MiniMax's pricing page last checked 10 Nov 2026: platform.minimax.io/docs/guides/pricing
5
Routes
$0.15
Cheapest input / 1M
MiniMax family
Published catalog rates.
Agent-turn cost uses 100K input and 10K output so a highspeed premium shows up per turn.
| Model route | Context | Input / 1M | Cached input / 1M | Output / 1M | Agent turn |
|---|---|---|---|---|---|
MiniMax M3.1 Flash MiniMax-M3.1-flash | 1M | $0.15 | $0.028 | $0.60 | $0.021 |
MiniMax M2.7 MiniMax-M2.7 | 196K | $0.30 | $0.025 | $1.20 | $0.042 |
MiniMax M3 MiniMax-M3 | 1M | $0.30 | $0.03 | $1.20 | $0.042 |
MiniMax M3 Highspeed MiniMax-M3-highspeed | 1M | $0.45 | $0.06 | $1.80 | $0.063 |
MiniMax M2.7 Highspeed MiniMax-M2.7-highspeed | 196K | $0.60 | $0.05 | $2.40 | $0.084 |
MiniMax pricing calculator
Same workload. Every MiniMax route.
Defaults are a 10K-in / 1K-out request, 3,000 times a month. Switch to the 100K / 10K agent turn for a coding loop, and set a cached share if your prompts repeat a long prefix.
Workload calculator
Catalog rates · USD · no markup
Share of each prompt that repeats a recent prefix (system prompt, files) and bills at the cached-input rate. Routes with no cached rate bill it as normal input.
Models in the estimate
4 selected| Route | Per request | Monthly | $100 buys |
|---|---|---|---|
| MiniMax M3.1 Flash MiniMax | $0.0021 | $6.30 | 47,619 req |
| MiniMax M2.7 MiniMax | $0.0042 | $12.60 | 23,809 req |
| MiniMax M3 MiniMax | $0.0042 | $12.60 | 23,809 req |
| MiniMax M3 Highspeed MiniMax | $0.0063 | $18.90 | 15,873 req |
Estimates apply live catalog rates, including cached input, and switch to a route's long-context rate when the prompt reaches its threshold. Actual spend follows the tokens your client sends and the model returns. Image-generation routes are omitted because they are not a chat turn.
Call it
Use MiniMax from Claude Code or the OpenAI SDK.
Claude Code and the Anthropic SDK use https://api.routerplex.com. The OpenAI SDK, Cursor and Cline use https://api.routerplex.com/v1. Same key, same catalog id, same per-key budget. Swap MiniMax-M3.1-flash for any id in the table.
export ANTHROPIC_BASE_URL=https://api.routerplex.comexport ANTHROPIC_AUTH_TOKEN="$ROUTERPLEX_API_KEY"export ANTHROPIC_MODEL=MiniMax-M3.1-flashclaude
import osfrom openai import OpenAIclient = OpenAI(base_url="https://api.routerplex.com/v1",api_key=os.environ["ROUTERPLEX_API_KEY"],)reply = client.chat.completions.create(model="MiniMax-M3.1-flash",messages=[{"role": "user", "content": "Hello!"}],)print(reply.choices[0].message.content)
How to pick
Standard or highspeed: what the premium costs.
These notes only use catalog fields: price, context, and mode. They are not quality rankings.
Cheapest per agent turn
MiniMax M3.1 Flash costs about $0.021 for a 100K-in / 10K-out turn at $0.15 / $0.60 per 1M.
Highspeed is a price premium
MiniMax M3 Highspeed is 1.5x MiniMax M3 and MiniMax M2.7 Highspeed is 2.0x MiniMax M2.7 per agent turn. MiniMax publishes no speed figure on its pricing page, so time it on your own prompts.
Context decides M3 vs M2.7
MiniMax M3 lists 1M of context. Check the context column before you pick an older id on name.
Setup notes for MiniMax M3.1 Flash, Claude Code Router and the OpenAI-compatible API. Compare the rest of the catalog on all model pricing, the cheapest-first ledger, or RouterPlex vs OpenRouter.
Before you bill production
MiniMax pricing, in questions.
01How much does the MiniMax API cost?+
As of 17 November 2026, MiniMax routes on RouterPlex cost $0.15 to $0.60 per 1M input tokens and $0.60 to $2.40 per 1M output tokens with 0% markup: MiniMax M3.1 Flash is $0.15 / $0.60, MiniMax M2.7 is $0.30 / $1.20, MiniMax M3 is $0.30 / $1.20, MiniMax M3 Highspeed is $0.45 / $1.80 and MiniMax M2.7 Highspeed is $0.60 / $2.40. Top-ups have a $0 fee and the balance stops at $0.
02What is MiniMax highspeed, and what does it cost?+
Highspeed ids are separate MiniMax routes with their own price. On this catalog MiniMax M3 Highspeed is $0.45 / $1.80 against $0.30 / $1.20 for MiniMax M3 (1.5x per agent turn) and MiniMax M2.7 Highspeed is $0.60 / $2.40 against $0.30 / $1.20 for MiniMax M2.7 (2.0x per agent turn). MiniMax's pricing page publishes no speed figure for them, so measure latency on your own prompts before paying the premium. (Source: platform.minimax.io/docs/guides/pricing, checked 2026-11-10.)
03MiniMax M3 or M2.7?+
On catalog fields: MiniMax M3 lists 1M context at $0.30 / $1.20 per 1M; MiniMax M2.7 lists 196K at $0.30 / $1.20. Same token price, so M3 buys the larger window at no extra rate. This page does not rank quality.
04Is MiniMax M3.1 Flash available?+
Yes. MiniMax M3.1 Flash is live as "MiniMax-M3.1-flash" at $0.15 / $0.60 per 1M with 1M context and $0.028 cached input.
05How do I get a MiniMax API key?+
On RouterPlex you do not need a MiniMax account: sign up, verify your email, and create a key in the dashboard (you can set a hard USD budget on it). Call https://api.routerplex.com/v1 with the OpenAI SDK, or point Claude Code at https://api.routerplex.com, with model "MiniMax-M3.1-flash". The same key reaches every other model in the catalog. A direct MiniMax account works differently: its pricing page says pay-as-you-go calls use Open Platform API keys and are deducted from a balance you recharge first. (Source: platform.minimax.io/docs/guides/pricing, checked 2026-11-10.)
06Is there a free MiniMax API tier on RouterPlex?+
No. RouterPlex has no free tier. Eligible verified accounts get $1 of test credit once, no card, and it never expires. After that you top up from $5 by card, or with crypto, with a $0 top-up fee; the balance stops at $0, so a MiniMax loop cannot run up a bill.
07Which MiniMax model id should I use?+
Send the catalog id exactly as written: "MiniMax-M3.1-flash" (MiniMax M3.1 Flash), "MiniMax-M2.7" (MiniMax M2.7), "MiniMax-M3" (MiniMax M3), "MiniMax-M3-highspeed" (MiniMax M3 Highspeed) and "MiniMax-M2.7-highspeed" (MiniMax M2.7 Highspeed). The cheapest per agent turn is "MiniMax-M3.1-flash". MiniMax ids are case-sensitive: "MiniMax-M3", not "minimax-m3". The page URL slug (for example /models/minimax-m3-1-flash) is not the API id; the id keeps its dots and case. Anything else returns model_not_found.
08How does MiniMax cache pricing work?+
Cached input is the part of a prompt the provider has already processed in a recent request with the same prefix, such as a long system prompt or a repeated file. It bills at the cached-input rate instead of the full input rate: $0.028 per 1M on MiniMax M3.1 Flash (input $0.15), $0.025 per 1M on MiniMax M2.7 (input $0.30), $0.03 per 1M on MiniMax M3 (input $0.30), $0.06 per 1M on MiniMax M3 Highspeed (input $0.45) and $0.05 per 1M on MiniMax M2.7 Highspeed (input $0.60). Set a cached share in the calculator above to see the effect.
09Do long MiniMax M3 prompts cost more?+
Not on RouterPlex. MiniMax's own price list charges a higher MiniMax-M3 rate above 512K input tokens; the RouterPlex catalog row for MiniMax M3 lists one rate ($0.30 / $1.20) at every prompt length. (Source: platform.minimax.io/docs/guides/pricing, checked 2026-11-10.)
Route MiniMax from one balance
Try MiniMax M3.1 Flash with $1, no card.
Try it with $1 of test credit, no card. Guided setup shows the exact Claude Code config for MiniMax M3.1 Flash.
Eligible verified accounts get the $1 once. It never expires.