Model comparison

Kimi K2.6 vs MiniMax M2.5

Moonshot AI against MiniMax, compared on context, price, and verified benchmark results.

Catalog record checked September 26, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

Moonshot AI

Kimi K2.6

Balanced · Open weights

MiniMax

MiniMax M2.5

Balanced · Open weights

AI model capability comparison
Specification	Kimi K2.6	MiniMax M2.5
Provider
Provider	Moonshot AI	MiniMax
Tier
Tier	Balanced	Balanced
Context window
Context window	Winner: 262K	205K
Max output
Max output	Not verifiedUnverified	Not verifiedUnverified
Input / 1M tokens
Input / 1M tokens	$0.95	Winner: $0.30
Output / 1M tokens
Output / 1M tokens	$4	Winner: $1.20
Weights
Weights	Open	Open
Parameters
Parameters	1T total / 32B active (MoE, 384 experts)	open MoE
Reasoning levels
Reasoning levels	Not verifiedUnverified	low, high, max
Modalities
Modalities	text, image, video	text
License
License	Modified MIT	Not disclosedUnverified
API model id
API model id	kimi-k2.6	Not publishedUnverified
Released
Released	April 20, 2026	February 12, 2026
Artificial Analysis Intelligence Index (2026-09-26)
Artificial Analysis Intelligence Index (2026-09-26)	Winner: 27	22.8

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

2026-09-26
Artificial Analysis (AA-estimated)
Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.
Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check measuredAt.

Pricing tiers

Kimi K2.6: $0.95/$4.00 per MTok on the Moonshot API; cached input $0.16. No documented hard output cap; evals ran 98,304-token generations.

MiniMax M2.5: $0.30/$1.20 per MTok on MiniMax's pay-as-you-go API (cache read $0.03). MiniMax lists M2.5 as a legacy model. Open weights (community license).

BalancedOpen weightsRecord checked September 26, 2026

Kimi K2.6

Kimi K2.6 is Moonshot's open-weight volume workhorse — a 1T MoE with native image/video input at 256K context, the base Kimi K2.7-Code and K3 build on.

Best for

Open-weight volume work
Multimodal input on a budget
Self-hosting at mid size

Watch out

256K context is small next to K3's 1M; video input is experimental (official API only). No documented hard output cap.

BalancedOpen weightsRecord checked September 26, 2026

MiniMax M2.5

MiniMax M2.5 is a legacy open-weight MiniMax MoE with a 204,800-token context.

Best for

Open-weight deployments
Multimodal

Watch out

Legacy: MiniMax's current models are M3 (1M context, multimodal) and M2.7 at the same $0.30/$1.20 price.

When the cheaper one wins

MiniMax M2.5 is cheaper on output at $1.20 per million tokens against $4 for Kimi K2.6 — about 3.3×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

Pricing verified on both sides — Input and output rates are verified for both models.
3/5 core specs verified on both sides — Not published for at least one side: max output, reasoning levels.
1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
Verified within the last 90 days — Newest catalog check was 2 days ago.
Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Kimi K2.6: HuggingFace — Kimi K2.6 model card (accessed 2026-08-29)
Kimi K2.6: Kimi — K2.6 pricing (accessed 2026-08-29)
Kimi K2.6: Moonshot platform pricing (kimi-k2.6) (accessed 2026-09-26)
MiniMax M2.5: MiniMax — M2.5 (accessed 2026-08-29)
MiniMax M2.5: MiniMax — text generation guide (M2.5 204,800 context) (accessed 2026-09-26)
MiniMax M2.5: MiniMax pay-as-you-go pricing (M2.5 $0.30/$1.20, legacy) (accessed 2026-09-26)
MiniMax M2.5: MiniMax — M2.5 release (2026-02-12) (accessed 2026-09-26)

Related comparisons

Diving deeper on one model? Kimi K2.6 · MiniMax M2.5

Common questions

Kimi K2.6 vs MiniMax M2.5

Answered from the verified figures on this page rather than general guidance.

Is Kimi K2.6 or MiniMax M2.5 cheaper for input?

MiniMax M2.5 is cheaper at $0.30 per million input tokens, against $0.95 for Kimi K2.6 — roughly 3.2× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Kimi K2.6 has tiered pricing: $0.95/$4.00 per MTok on the Moonshot API; cached input $0.16. No documented hard output cap; evals ran 98,304-token generations. MiniMax M2.5 has tiered pricing: $0.30/$1.20 per MTok on MiniMax's pay-as-you-go API (cache read $0.03). MiniMax lists M2.5 as a legacy model. Open weights (community license).

Is Kimi K2.6 or MiniMax M2.5 cheaper for output?

MiniMax M2.5 is cheaper at $1.20 per million output tokens, against $4 for Kimi K2.6 — roughly 3.3× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Kimi K2.6 has tiered pricing: $0.95/$4.00 per MTok on the Moonshot API; cached input $0.16. No documented hard output cap; evals ran 98,304-token generations. MiniMax M2.5 has tiered pricing: $0.30/$1.20 per MTok on MiniMax's pay-as-you-go API (cache read $0.03). MiniMax lists M2.5 as a legacy model. Open weights (community license).

Which has the larger context window, Kimi K2.6 or MiniMax M2.5?

Kimi K2.6 accepts 262K tokens against 205K for MiniMax M2.5. This only matters if you routinely send very long documents or large codebases.

Should I use Kimi K2.6 or MiniMax M2.5?

Both sit in the balanced tier, so the choice usually comes down to price and context rather than capability. Kimi K2.6 suits open-weight volume work; MiniMax M2.5 suits open-weight deployments.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

Input price: MiniMax M2.5 costs $0.30 per 1M tokens versus $0.95 for Kimi K2.6 — a 3.2x difference at the headline tier.
Context: Kimi K2.6 takes 262K against 205K for MiniMax M2.5 — only decisive if your prompts approach the smaller window.

Run the model picker Estimate stack cost All model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.