Skip to main content
AI Choice Engine

Model comparison

GPT-5.6 Terra vs Kimi K2.7 Code

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

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

OpenAI

GPT-5.6 Terra

Balanced

vs

Moonshot AI

Kimi K2.7 Code

Balanced · Open weights

AI model capability comparison
SpecificationGPT-5.6 TerraKimi K2.7 Code
ProviderOpenAIMoonshot AI
TierBalancedBalanced
Context windowWinner: 1.05M262K
Max output128KNot verifiedUnverified
Input / 1M tokens$2Winner: $0.95
Output / 1M tokens$12Winner: $4
WeightsClosedOpen
Parametersmid-tier reasoning model1T total / 32B active (MoE)
Reasoning levelsnone, low, medium, high, xhigh, maxNot verifiedUnverified
Modalitiestext, imagetext, image, video
LicenseNot disclosedUnverifiedModified MIT
API model idgpt-5.6-terrakimi-k2.7-code
ReleasedJuly 9, 2026June 12, 2026
Artificial Analysis Intelligence Index [max] (2026-09-26)42.1Not verifiedUnverified
Artificial Analysis Intelligence Index (2026-09-26)Not verifiedUnverified25.8
SWE-bench Verified (2026-09-01)95.4Not verifiedUnverified
Terminal-Bench 2.1 (2026-07-09)87.4Not verifiedUnverified
LiveBench (2026-09-05)77.9Not verifiedUnverified

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

    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.

  • 2026-09-05
    LiveBench official leaderboard (benchmark-owned), max effort

    Contamination-resistant general capability across reasoning, coding, math, data analysis, and language, with monthly question refreshes.

    Comparable with caveatRolling question set: observations months apart measure different question mixes. Record the measurement date and compare within ~1 month windows.

  • 2026-09-01
    vals.ai SWE-bench Verified leaderboard (independent, mini-swe-agent bash-only) (independent; official SWE-bench not published)

    Real GitHub issue resolution: does the model's patch pass the hidden tests.

    Comparable with caveatPost-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.

  • 2026-07-09
    OpenAI GPT-5.6 announcement (vendor; chart transcribed by Vellum)

    Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.

    Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.

Pricing tiers

GPT-5.6 Terra: Launch list was $2.50/$15; cut to $2/$12 on 2026-07-30. Above 272K input the whole request bills 2x input / 1.5x output. Cached input $0.20/MTok; cache writes 1.25x input; batch $1/$6.

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).

BalancedRecord checked September 26, 2026

GPT-5.6 Terra

GPT-5.6 Terra delivers roughly GPT-5.5-class quality at about half the cost, with the full 1.05M-token context.

Best for

  • Cost-sensitive production
  • Mixed reasoning workloads
  • High-volume agents

Watch out

GPT-6 Sol ($2/$10) now costs less than Terra ($2/$12) and scores higher — route frontier work to GPT-6 Sol. Terra has no named successor and is still served.

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.

When the cheaper one wins

Kimi K2.7 Code is cheaper on output at $4 per million tokens against $12 for GPT-5.6 Terra — about 3.0×. 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. On DeepSWE 1.1, Kimi K2.7 Code is 30.5% Pass@1 at $2.82/task versus GPT-5.6 Terra at 69.6% / $4.95/task. 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.

Related comparisons

Diving deeper on one model? GPT-5.6 Terra · Kimi K2.7 Code

Common questions

GPT-5.6 Terra vs Kimi K2.7 Code

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

Is GPT-5.6 Terra or Kimi K2.7 Code cheaper for input?
Kimi K2.7 Code is cheaper at $0.95 per million input tokens, against $2 for GPT-5.6 Terra — roughly 2.1× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-5.6 Terra has tiered pricing: Launch list was $2.50/$15; cut to $2/$12 on 2026-07-30. Above 272K input the whole request bills 2x input / 1.5x output. Cached input $0.20/MTok; cache writes 1.25x input; batch $1/$6. 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).
Is GPT-5.6 Terra or Kimi K2.7 Code cheaper for output?
Kimi K2.7 Code is cheaper at $4 per million output tokens, against $12 for GPT-5.6 Terra — roughly 3.0× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; GPT-5.6 Terra has tiered pricing: Launch list was $2.50/$15; cut to $2/$12 on 2026-07-30. Above 272K input the whole request bills 2x input / 1.5x output. Cached input $0.20/MTok; cache writes 1.25x input; batch $1/$6. 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).
Which has the larger context window, GPT-5.6 Terra or Kimi K2.7 Code?
GPT-5.6 Terra accepts 1.05M tokens against 262K for Kimi K2.7 Code. This only matters if you routinely send very long documents or large codebases.
Should I use GPT-5.6 Terra or Kimi K2.7 Code?
Both sit in the balanced tier, so the choice usually comes down to price and context rather than capability. GPT-5.6 Terra suits cost-sensitive production; Kimi K2.7 Code suits agentic coding on open weights.
Can I self-host GPT-5.6 Terra or Kimi K2.7 Code?
Kimi K2.7 Code publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. GPT-5.6 Terra is a closed model whose supported access paths are controlled by its provider.

Next step

Choosing between them

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

  • Input price: Kimi K2.7 Code costs $0.95 per 1M tokens versus $2 for GPT-5.6 Terra — a 2.1x difference at the headline tier.
  • Context: GPT-5.6 Terra takes 1.05M against 262K for Kimi K2.7 Code — only decisive if your prompts approach the smaller window.
  • Measured capability: GPT-5.6 Terra leads Artificial Analysis Intelligence Index 42.1 to 25.8 (measured 2026-09-26).
  • Deployment: Kimi K2.7 Code publishes weights you can self-host; the other is API-only.
Run the model pickerEstimate stack costAll model comparisons

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