New Sign up free, 10 calls on us. Up to $1, no card needed.

GPT-6 Luna vs Kimi K2.7 Code

vs

Which one, when

gpt-6-luna is the cheaper and roomier option: $0.1 input and $0.5 output per million against $0.95 and $4 for kimi-k2.7-code (9.5x input, 8x output), with a 1050000-token context and 128000 max output versus 256000 and 32768, plus the option to disable thinking. Pick kimi-k2.7-code when your inputs include video, which it accepts and gpt-6-luna does not; otherwise both cover text and image in, text out, with code, tools and reasoning. Cache reads are $0.01 versus $0.19, widening the gap further on workloads that reuse long prompts.

Benchmarks

Above averageGPT-6 Lunaonly 1 comparableKimi K2.7 Code1 / 5
GPT-6 Luna Kimi K2.7 Code other models measured peer average no peer scored higher
DeepSWE 1.1
66.6%
N/A
MCP-Atlas
N/A
76%

Vendor-published: Alibaba (Qwen) Anthropic DeepSeek Google Moonshot OpenAI Z.ai

Pricing

GPT-6 Luna Kimi K2.7 Code Δ
Input / 1M tokens $0.1 $0.95 0.11×
Output / 1M tokens $0.5 $4 0.13×
Cache read / 1M tokens $0.01 $0.19 0.053×
Cache write no separate charge - -

Rates from the live catalog at build time; each model page carries the current card.

Where they sit - input price per 1M tokens across all 74 chat models on this billing unit (log scale)

GPT-6 Luna · $0.1 Kimi K2.7 Code · $0.95
$0.05 · Qwen3 VL Flash $30 · GPT-5.4 Pro

Capabilities

GPT-6 Luna Kimi K2.7 Code
Tool use yes yes
Thinking control configurable always on
Structured output yes -
Prompt caching implicit (automatic) implicit (automatic)
Cache lifetime 5-10m, up to 1h not published
Minimum cached prefix 1024 tokens not published

Specs

GPT-6 Luna Kimi K2.7 Code
Input modalities text image text image video
Output modalities text text
Released 2026-09-22 2026-06
Knowledge cutoff 2026-05 -
Context window 1.1M 256K
Max output 128K 33K
Thinking parameter reasoning.effort
  • thinking.type
  • thinking.keep
Accepted values
reasoning.effort
  • none
  • low
  • medium
  • high
  • xhigh
  • max
type
  • accepts only enabled
keep
  • accepts only all
Default medium thinking on with Preserved Thinking on

Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: GPT-6 Luna · Kimi K2.7 Code

One prompt, both models - measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

GPT-6 Luna passed · 3 sentences

Enabling reasoning typically makes the model process more information and generate more internal tokens before producing its answer. Because usage is billed by tokens—and reasoning may also route requests to a more expensive model—the cost per request can rise sharply. If request volume stayed similar, that higher cost per request could explain why the bill doubled.

out 117 tok (+48 thinking) latency 3.4 s

Kimi K2.7 Code passed · 3 sentences

Enabling reasoning mode causes the model to generate an internal chain-of-thought before producing each answer, and that hidden reasoning text is billed like any other output. Those extra reasoning tokens typically add up to much more than the final response itself, so every API call now costs significantly more than before. Because our overall usage volume did not change, the doubled bill reflects that each query consumes roughly twice as many billable tokens.

out 259 tok (+174 thinking) latency 5.4 s

Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

GPT-6 Luna passed · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` The original code counted matching *adjacent pairs* rather than items, so a run of length `n` was reported as `n - 1`, and a single-item input returned `0`. This version counts the current item as part of each run and updates `best` at every index, including the last; it returns `0` for an empty input.

out 514 tok (+356 thinking) latency 6.9 s

Kimi K2.7 Code passed · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` The bug is that the function counts *transitions* between equal neighbors instead of counting the items themselves, so a single-element list never enters the loop and returns `0` instead of `1`. Likewise, resetting `cur` to `0` on a mismatch forgets the current item that starts a new run, which causes runs that end at the last index to be undercounted. Initializing both `best` and `cur` to `1` and resetting `cur` to `1` fixes both issues.

out 410 tok (+222 thinking) latency 9.4 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

GPT-6 Luna passed · 5/5 fields, guidance "Withheld pending the Q4 close"

{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":null,"guidance":"Withheld pending the Q4 close"}

out 161 tok (+119 thinking) latency 21.7 s

Kimi K2.7 Code passed · 5/5 fields, guidance "withheld pending the Q4 close"

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "withheld pending the Q4 close" } ```

out 721 tok (+663 thinking) latency 13.2 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

GPT-6 Luna passed · 120 words, 0 banned, 1 question

Introducing Prompt Cache, a new API gateway feature that recognizes repeat prompt prefixes and reuses provider-side cached context across supported models. Teams can route requests to different AI providers while preserving eligible cache hits, reducing redundant input processing and helping lower latency and token costs. Configure cache policies in one place, monitor hit rates by provider, and keep existing client integrations unchanged. The gateway applies provider-specific rules automatically, so developers do not need to build separate caching logic for each endpoint. Which workflows could benefit from faster responses and predictable spend? Prompt Cache is available today in preview for eligible accounts, with usage details, supported providers, and setup guidance in the dashboard. Start with one route, compare results, then expand.

out 959 tok (+813 thinking) latency 14.6 s

Kimi K2.7 Code passed · 120 words, 0 banned, 1 question

We're introducing Prompt Cache for our API Gateway, a new capability that stores prompt responses across multiple AI providers. By caching replies, you reduce redundant calls, lower latency, and cut costs without changing how you build. Teams using several model providers can now reuse identical prompt results instantly, keeping traffic consistent and budgets predictable. Responses are keyed by provider, model, and exact prompt, so you always get the right result. Configure TTL, hit thresholds, and eviction rules from a single dashboard. It fits into your existing routing and requires no code changes. Setup takes minutes and works with your current endpoints. Want to see how much latency and spend you can trim? Check the docs to enable Prompt Cache today.

out 2375 tok (+2235 thinking) latency 38.6 s

Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.

Switch between them with one line

Both ids are in every tab below - the highlighted pair of lines is the only edit. Same endpoint, same key, same request shape.

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="gpt-6-luna",
    # model="kimi-k2.7-code",  # uncomment this line, comment the one above
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

Get your API key →

FAQ

Which is cheaper, GPT-6 Luna or Kimi K2.7 Code?

GPT-6 Luna is cheaper on input / 1m tokens ($0.1 vs $0.95, 9.5× apart). Other rows may point the other way - the table above carries the full card, and real cost depends on your mix.

Can I A/B test GPT-6 Luna against Kimi K2.7 Code without two integrations?

Yes. Both are served through the same OpenAI-compatible endpoint with one API key - switching is a one-line model-string change, so you can route a fraction of traffic to each and compare bills directly.

Do GPT-6 Luna and Kimi K2.7 Code support prompt caching?

Yes - both bill cached reads below their input rate, so warm-prefix workloads cost less than the list rates suggest. The exact cache-read rows are in the pricing table above.

Related comparisons

From our measured studies