Skip to content

> Minimax Coding

www.minimax.io

MiniMax's open platform prices large language models per token with a published input-length threshold: MiniMax-M3 is $0.30 per 1M input tokens and $1.20 per 1M output tokens for prompts up to 512K input tokens, described as a permanent 50% discount off $0.60 / $2.40, and doubles to $0.60 / $2.40 above 512K. M2.7 is $0.30 / $1.20 with prompt-cache reads at $0.06 and writes at $0.375 per 1M tokens; a Priority service tier costs 1.5x standard. The same account also bills video, speech and image work separately, for example H3 video at $0.08 per second in 768P, speech-2.8-hd TTS at $100 per 1M characters and image-01 at $0.0035 per image.

unknownbest-effort probe · checked never
Paid API API keyFreemiumMedium risk· conf 90%verified
Free credits
Not quantified
No free tier or free credit stated on official pages (checked 2026-09-16); the documented entry points are prepaid Credits (1,000 credits = $1, packages from $5) and Token Plans from $22 per month.
Cheapest input /1M
Free
USD per 1M input tokens, best tracked model
Cheapest output /1M
$0.0000
USD per 1M output tokens, best tracked model
Models tracked
5
Canonical models with normalized pricing
// source_analysisUprouter editorial analysis

// pros

  • Threshold pricing is explicit rather than blended: M3 is $0.30 / $1.20 per 1M tokens up to 512K input tokens and $0.60 / $2.40 above, with the pre-discount figures shown struck through so the discount basis is visible.
  • Prompt caching is split into read and write prices ($0.06 and $0.375 per 1M tokens on M2.7), which lets long-prefix economics be modelled directly from the page.
  • Priority admission is a same-endpoint switch (service_tier=priority) priced at exactly 1.5x standard, not a separate API surface.
  • Token Plan subscriptions are $22 (Plus), $55 (Max) and $132 (Ultra) per month with 5-hour rolling plus weekly quota windows, and purchased Credits (1,000 credits = $1) overflow after plan quota with 365-day validity.
  • Video input materials carry stated free allowances: audio input is free and the first 5 images are free on H3 (first 2 on H3-Max), with per-image overage prices published.

// cons

  • No free token tier is stated on the official pricing pages; the lowest documented entry points are a $5 credit package and the $22/month Plus Token Plan.
  • Music capabilities were withdrawn from the API: the pay-as-you-go page states paid Music and Lyrics generation closed to new users from August 20, 2026 and the free Music-3.0-free, Music-2.6-free and music-cover-free APIs were discontinued.
  • Token Plan coverage is incomplete - MiniMax H3, voice design and rapid voice cloning are not supported, and the subscription quota is shared across text, image and speech resources.
  • Cloned voices are deleted if unused for 7 days, voice design is charged on first synthesis rather than creation, and the MCP vision endpoint is billed per request ($0.01) with a price change effective July 22, 2026.

Use it where multimodal breadth under one key matters - language, video, speech and image with published per-unit prices - and start on pay-as-you-go M3 rather than a subscription. Pair it with a primary text provider and only move to a Token Plan once you can forecast consumption against the 5-hour and weekly windows.

// free_quota

Free tier present — value not quantified

This provider offers a free tier, but its terms don’t convert cleanly into a USD figure (e.g. request-count limits or capacity-dependent pools). We refuse to print a misleading zero here. See the note below and the official pricing page for the exact limits.

note: No free tier or free credit stated on official pages (checked 2026-09-16); the documented entry points are prepaid Credits (1,000 credits = $1, packages from $5) and Token Plans from $22 per month.

// pricinglast verified Sep 16, 2026
PlanTypeMonthlyInput /1MOutput /1MNote
Pay-as-you-gopayg—Free$0.0000Cheapest tracked model rate (OpenRouter-normalized).
MiniMax-M3 PAYGpayg—$0.300$1.20Includes permanent 50% discount for input ≤ 512k tokens.
Plus Subscriptionsubscription$22.00/mo——Best for personal projects and prototyping.
pricing_last_verified: Sep 16, 2026official pricing page

Pricing normalized from public sources — always verify with the provider.

// model prices

ModelInput /1MOutput /1MContext
MiniMax-M3Free$0.00001.0M
minimax-m2.7Free$0.0000205k
MiniMax M2Free$0.0000205k
MiniMax M1$0.0000$0.00001M
MiniMax-01$0.200$1.101.0M
// faq
$ Does Minimax Coding have a free tier?

Yes — Minimax Coding offers a free tier. Always confirm current limits on Minimax Coding's official pricing page — free tiers change without notice.

$ How much does Minimax Coding cost per 1M tokens?

The cheapest model we track at Minimax Coding is Free per 1M input tokens and $0.0000 per 1M output tokens. This is normalized from Minimax Coding's published pricing — verify with the provider before purchasing, since prices change frequently.

$ Is Minimax Coding safe to use?

Uprouter rates Minimax Coding as medium risk. Risk: medium. Unit prices are documented for every modality, including the 512K input threshold on M3, cache read/write rates and Priority's 1.5x multiplier, so cost modelling is possible without guessing. Two commercial risks stand out on the official pages: there is no stated free tier at all, so evaluation requires prepaid credit, and the platform has retired API capabilities before (music generation closed to new users in August 2026 and free music endpoints discontinued), which is a signal to avoid building irreplaceable dependencies on feature previews. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.

// community0 reviews

Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.

No published reviews yet — be the first.

// more_informationprice history · live status · risk & confidence · code snippets

price_history

No recorded changes yet.

live_status

current: unknown

No probes recorded yet.

Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.

risk_&_confidence

Medium risk
90%

Risk: medium. Unit prices are documented for every modality, including the 512K input threshold on M3, cache read/write rates and Priority's 1.5x multiplier, so cost modelling is possible without guessing. Two commercial risks stand out on the official pages: there is no stated free tier at all, so evaluation requires prepaid credit, and the platform has retired API capabilities before (music generation closed to new users in August 2026 and free music endpoints discontinued), which is a signal to avoid building irreplaceable dependencies on feature previews.

Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.

code_snippets

# Minimax Coding's own API — get a key from their dashboard
curl https://www.minimax.io/chat/completions \
  -H "Authorization: Bearer THEIR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.

// similar_providersscored by Paid API signals

Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.