Model comparison
GPT-5.6 Luna vs Kimi K2.6
OpenAI against Moonshot AI, compared on context, price, and verified benchmark results.
Catalog record checked August 12, 2026; individual provider fields may change.
OpenAI
GPT-5.6 Luna
Budget
Moonshot AI
Kimi K2.6
Budget · Open weights
| Specification | GPT-5.6 Luna | Kimi K2.6 |
|---|---|---|
| Provider | OpenAI | Moonshot AI |
| Tier | Budget | Budget |
| Context window | Winner: 1.05M | 262K |
| Max output | 128K | Not verified |
| Input / 1M tokens | Winner: $0.20 | $0.95 |
| Output / 1M tokens | Winner: $1.20 | $4 |
| Weights | Closed | Open |
| Parameters | Not disclosed | 1T total / 32B active (MoE) |
| Reasoning levels | none, low, medium, high, xhigh, max | Not verified |
| Modalities | text, image | text, image, video |
| Released | July 9, 2026 | April 21, 2026 |
| Artificial Analysis Intelligence Index [max] (2026-08-08) | Winner: 52 | 45 |
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.
Pricing tiers: GPT-5.6 Luna: Prompts above 272K tokens bill at 2× input and 1.5× output; cache writes are 1.25× the input rate. · Kimi K2.6: Cache-hit input is $0.16 / MTok; cache-miss input is $0.95 / MTok; output $4.00 / MTok (Moonshot list).
GPT-5.6 Luna
OpenAI's cheapest tier, built for high-volume work where unit cost matters more than frontier quality. From Aug 2026 also the ChatGPT Free/Go default with unlimited text chats + Think for harder questions.
Best for
- Classification
- Summarisation
- High-volume chat
- ChatGPT Free/Go default
Watch out
The bare `gpt-5.6` alias routes to Sol at 25x the input price — specify the full id. ChatGPT Free→Luna is consumer Chat only; Work/Codex/API Luna builds did not change with the Aug 6 Chat refresh.
Kimi K2.6
Open-weight mixture-of-experts model priced well below the closed frontier tiers.
Best for
- Cost-sensitive volume
- Self-hosting
- Avoiding vendor lock-in
Watch out
262K context is among the smaller windows here — a real constraint on long-document work.
Benchmark
DeepSWE 1.1 in context
Only GPT-5.6 Luna has a published DeepSWE 1.1 result. It is shown against the wider field, with cost per completed task alongside the score.
Local leader
Claude Opus 5 [max]
74%
Rows shown
24
Highest published reasoning effort per model (not best Pass@1)
Snapshot date
2026-08-13
Mirrored from deepswe.datacurve.ai
Better is toward the top-right (higher pass rate, lower cost). X-axis is reversed to match DeepSWE’s public chart. v1.1 uses average cost / tokens / steps; v1 uses published medians.
| # | Model | Pass@1 | Cost / task | Tokens / task | Steps / task |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 [max] | 74% | $11.84 | 118k | 99 |
| 2 | GPT-5.6 Sol [max] | 73% | $8.39 | 60k | 61 |
| 3 | Claude Fable 5 [max] | 70% | $21.63 | 119k | 88 |
| 4 | GPT-5.6 Terra [max] | 70% | $4.95 | 72k | 76 |
| 5 | Kimi K3 [max] | 69% | $4.65 | 82k | 98 |
| 6 | GPT-5.6 Luna [max] | 67% | $3.03 | 73k | 102 |
| 7 | GPT-5.5 [xhigh] | 67% | $7.23 | 46k | 82 |
| 8 | Grok 4.6 [xhigh] | 67% | $5.50 | 71k | 87 |
| 9 | Gemini 3.7 Flash [high] | 65% | $2.18 | 107k | 125 |
| 10 | DeepSeek V4-Pro [max] | 63% | $0.24 | 106k | 155 |
| 11 | Claude Opus 4.8 [max] | 59% | $13.22 | 135k | 120 |
| 12 | Qwen3.8-Max [xhigh] | 58% | $3.73 | 95k | 111 |
| 13 | Muse Spark 1.2 [xhigh] | 55% | $3.70 | 99k | 101 |
| 14 | Claude Sonnet 5 [max] | 54% | $26.40 | 214k | 268 |
| 15 | Grok 4.5 [high] | 54% | $2.42 | 36k | 61 |
| 16 | DeepSeek V4-Flash [max] | 53% | $0.10 | 108k | 153 |
| 17 | Muse Spark 1.1 [xhigh] | 53% | $2.36 | 74k | 96 |
| 18 | GPT-5.4 [xhigh] | 52% | $5.65 | 71k | 70 |
| 19 | Gemini 3.6 Flash [high] | 47% | $4.42 | 96k | 117 |
| 20 | GLM 5.2 [max] | 44% | $3.92 | 78k | 129 |
| 21 | Gemini 3.5 Flash [high] | 36% | $3.45 | 76k | 105 |
| 22 | Kimi K2.7 Code | 31% | $2.82 | 59k | 149 |
| 23 | Claude Sonnet 4.6 [high] | 30% | $5.52 | 76k | 134 |
| 24 | Gemini 3.1 Pro [high] | 12% | $2.14 | 28k | 76 |
DeepSWE “Best” picks the highest published reasoning effort per model (not the highest pass rate). Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.
Common questions
GPT-5.6 Luna vs Kimi K2.6
Answered from the verified figures on this page rather than general guidance.
Is GPT-5.6 Luna or Kimi K2.6 cheaper for input?
GPT-5.6 Luna is cheaper at $0.20 per million input tokens, against $0.95 for Kimi K2.6 — roughly 4.7× 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 Luna has tiered pricing: Prompts above 272K tokens bill at 2× input and 1.5× output; cache writes are 1.25× the input rate. Kimi K2.6 has tiered pricing: Cache-hit input is $0.16 / MTok; cache-miss input is $0.95 / MTok; output $4.00 / MTok (Moonshot list).
Is GPT-5.6 Luna or Kimi K2.6 cheaper for output?
GPT-5.6 Luna 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; GPT-5.6 Luna has tiered pricing: Prompts above 272K tokens bill at 2× input and 1.5× output; cache writes are 1.25× the input rate. Kimi K2.6 has tiered pricing: Cache-hit input is $0.16 / MTok; cache-miss input is $0.95 / MTok; output $4.00 / MTok (Moonshot list).
Which has the larger context window, GPT-5.6 Luna or Kimi K2.6?
GPT-5.6 Luna accepts 1.05M tokens against 262K for Kimi K2.6. This only matters if you routinely send very long documents or large codebases.
Should I use GPT-5.6 Luna or Kimi K2.6?
Both sit in the budget tier, so the choice usually comes down to price and context rather than capability. GPT-5.6 Luna suits classification; Kimi K2.6 suits cost-sensitive volume.
Can I self-host GPT-5.6 Luna or Kimi K2.6?
Kimi K2.6 publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. GPT-5.6 Luna is a closed model whose supported access paths are controlled by its provider.
Next step
Choosing between them
Tier and workload decide this more reliably than a leaderboard position does.
If both sit in the same tier, the decision usually comes down to context window and output price rather than headline capability — output tokens dominate real bills.
If one is a step up within the same provider, the useful question is whether your hardest task actually fails on the cheaper tier. Most production volume — classification, extraction, summarization — does not.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Muse Code, or Lovable? Compare agentic harnesses · Latest releases.