Model comparison

Kimi K2.7 Code vs Qwen3-235B-A22B

Moonshot AI against Qwen, 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 K2.7 Code

Balanced · Open weights

Qwen

Qwen3-235B-A22B

Balanced · Open weights

AI model capability comparison
Specification	Kimi K2.7 Code	Qwen3-235B-A22B
Provider
Provider	Moonshot AI	Qwen
Tier
Tier	Balanced	Balanced
Context window
Context window	Winner: 262K	128K
Max output
Max output	Not verifiedUnverified	33K
Input / 1M tokens
Input / 1M tokens	$0.95	Winner: $0.70
Output / 1M tokens
Output / 1M tokens	$4	Winner: $2.80
Weights
Weights	Open	Open
Parameters
Parameters	1T total / 32B active (MoE)	235B total / 22B active (MoE)
Reasoning levels
Reasoning levels	Not verifiedUnverified	low, high, max
Modalities
Modalities	text, image, video	text
License
License	Modified MIT	Apache 2.0
API model id
API model id	kimi-k2.7-code	qwen3-235b-a22b
Released
Released	June 12, 2026	April 29, 2025
Artificial Analysis Intelligence Index (2026-09-26)
Artificial Analysis Intelligence Index (2026-09-26)	Winner: 25.8	9.5

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 (Reasoning, 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 K2.7 Code: $0.95/$4.00 per MTok — same rates as K2.6; cached input $0.19. Coding-focused build of the K2.6 recipe (1T total / 32B active).

Qwen3-235B-A22B: Model Studio International $0.70 input / $2.80 output per MTok (non-thinking); thinking-mode output $8.40. Open weights (Apache 2.0) for self-hosting; 32,768-token recommended output.

BalancedOpen weightsRecord checked September 26, 2026

Kimi K2.7 Code

Kimi K2.7 Code is Moonshot's coding-specialised build of K2.6 — same 1T MoE and 256K context, tuned for agentic coding workflows.

Best for

Agentic coding on open weights
Kimi ecosystem teams
Repo-scale refactors at K2.6 rates

Watch out

256K context matches K2.6, not K3's 1M; appears on the DeepSWE and CursorBench boards at mid-table scores.

BalancedOpen weightsRecord checked September 26, 2026

Qwen3-235B-A22B

Qwen3-235B-A22B is Alibaba's widely deployed open-weight MoE — 235B/22B, strong price-performance.

Best for

Open-weight deployments
Self-hosting
Multilingual

Watch out

Needs multi-GPU for the 235B total; hosted rates vary.

When the cheaper one wins

Qwen3-235B-A22B is cheaper on output at $2.80 per million tokens against $4 for Kimi K2.7 Code — about 1.4×. 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 K2.7 Code: Kimi K2.7 Code model page (accessed 2026-08-29)
Kimi K2.7 Code: Moonshot platform — K2.7 Code pricing (accessed 2026-08-29)
Kimi K2.7 Code: Kimi — K2.7 Code released and open-sourced (2026-06-12) (accessed 2026-09-26)
Kimi K2.7 Code: Cloudflare Workers AI changelog — Kimi K2.7 Code (2026-06-12) (accessed 2026-09-26)
Qwen3-235B-A22B: HuggingFace — Qwen3-235B-A22B (accessed 2026-08-29)
Qwen3-235B-A22B: Qwen — Qwen3 (accessed 2026-08-29)
Qwen3-235B-A22B: Alibaba Cloud Model Studio pricing (qwen3-235b-a22b $0.70/$2.80, thinking $8.40) (accessed 2026-09-26)

Related comparisons

Diving deeper on one model? Kimi K2.7 Code · Qwen3-235B-A22B

Common questions

Kimi K2.7 Code vs Qwen3-235B-A22B

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

Is Kimi K2.7 Code or Qwen3-235B-A22B cheaper for input?

Qwen3-235B-A22B is cheaper at $0.70 per million input tokens, against $0.95 for Kimi K2.7 Code — roughly 1.4× 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 K2.7 Code has tiered pricing: $0.95/$4.00 per MTok — same rates as K2.6; cached input $0.19. Coding-focused build of the K2.6 recipe (1T total / 32B active). Qwen3-235B-A22B has tiered pricing: Model Studio International $0.70 input / $2.80 output per MTok (non-thinking); thinking-mode output $8.40. Open weights (Apache 2.0) for self-hosting; 32,768-token recommended output.

Is Kimi K2.7 Code or Qwen3-235B-A22B cheaper for output?

Qwen3-235B-A22B is cheaper at $2.80 per million output tokens, against $4 for Kimi K2.7 Code — roughly 1.4× 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 K2.7 Code has tiered pricing: $0.95/$4.00 per MTok — same rates as K2.6; cached input $0.19. Coding-focused build of the K2.6 recipe (1T total / 32B active). Qwen3-235B-A22B has tiered pricing: Model Studio International $0.70 input / $2.80 output per MTok (non-thinking); thinking-mode output $8.40. Open weights (Apache 2.0) for self-hosting; 32,768-token recommended output.

Which has the larger context window, Kimi K2.7 Code or Qwen3-235B-A22B?

Kimi K2.7 Code accepts 262K tokens against 128K for Qwen3-235B-A22B. This only matters if you routinely send very long documents or large codebases.

Should I use Kimi K2.7 Code or Qwen3-235B-A22B?

Both sit in the balanced tier, so the choice usually comes down to price and context rather than capability. Kimi K2.7 Code suits agentic coding on open weights; Qwen3-235B-A22B 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: Qwen3-235B-A22B costs $0.70 per 1M tokens versus $0.95 for Kimi K2.7 Code — a 1.4x difference at the headline tier.
Context: Kimi K2.7 Code takes 262K against 128K for Qwen3-235B-A22B — 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.