Gemini 4 Carbon vs GPT-6.1 Terra

vs

什么时候选哪个

输入不超过 272000 token 时,gemini-4-carbon 支持音频、视频输入与搜索接地。若更看重较低的输入输出费用、更大的输出上限或关闭推理的选项,可选 gpt-6.1-terra。

Benchmark 成绩

GPT-6.1 Terra:公布了 9 项成绩,但每一项测过的其他模型都太少,没法比较。

高于同类均值无更高分Gemini 4 Carbon12 / 1210 / 12
Gemini 4 Carbon GPT-6.1 Terra 其他参测模型 同类均值 ★ 没有模型得分更高
FrontierSWE 2 Proximal leaderboard, Carbon report
61.2%
N/A
OSWorld 2.1 82 offline tasks, partial score. Gemini: best of 3. Peers: published evaluations
81.5%
N/A
AutomationBench (Zapier) Zapier private set
没有模型得分更高 53.9%
N/A
GraphWalks BFS (F1) 256k to 1M tokens, 200 tasks, Google evaluation
没有模型得分更高 96.2%
N/A
Blueprint-Bench 2 Similarity score, Andon Labs leaderboard
没有模型得分更高 58.6%
N/A
Vending-Bench 2 (USD) Andon Labs leaderboard, Carbon report · 5422-16484
没有模型得分更高 16484
N/A
Chartography No tools, Carbon report
没有模型得分更高 72.5%
N/A

供应商公布: Google Google

价格

Gemini 4 Carbon GPT-6.1 Terra Δ
输入 / 1M token $2 $1 2×
输出 / 1M token $10 $5 2×
缓存读取 / 1M token $0.1 $0.05 2×
缓存写入 - 1.25x (30m) / 2.5x (12h) -

价格取自构建时的实时目录,最新价格见各模型页面。 主表显示基础档。提示词长度可能改变整次请求的费率,各模型页有完整价目。

GPT-6.1 Terra · 按输入长度分档的价格

整次请求按输入长度所在档位计费。价格单位为美元/百万 token。

输入 token 数输入输出
0 - 272,000 $1 $5
272,001 - 1,050,000 $2 $7.5

两个模型所处的位置:全部 86 个按同一单位计费的聊天模型的每 1M token 输入价分布(对数刻度)

能力

Gemini 4 Carbon GPT-6.1 Terra
工具调用 是 是
思考控制 始终开启 可配置
结构化输出 是 是
提示词缓存 隐式(自动) 隐式 + 显式
缓存有效期 未公布 at least 30m by default, 12h option on the Responses API
最小缓存前缀 4,096 个 token 1,024 个 token

规格

Gemini 4 Carbon GPT-6.1 Terra
输入模态 文本 图像 音频 视频 文本 图像
输出模态 文本 文本
发布日期 2026-11-10 2026-10-26
知识截止日期 2026-03 2026-06
上下文窗口 1,048,576 1,050,000
最大输出 65,536 128,000
思考参数 thinking_level reasoning.effort
可选值
thinking_level
  • low
  • medium
  • high

"minimal" and thinking_budget return 400

reasoning.effort
  • none
  • low
  • medium
  • high
  • xhigh
  • max
默认值 medium medium

规格照录自各供应商的文档;供应商没有公布的项目,对应的行直接省略,不做推断。 完整来源: Gemini 4 Carbon · GPT-6.1 Terra

同一条提示词,两个模型,经网关实测

提示词 Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. 检查 恰好 3 句

Gemini 4 Carbon 通过 · 3 sentences

Enabling reasoning instructs the AI to generate a lengthy, behind-the-scenes "thought process" to verify its logic before delivering a final answer. Because our vendor bills us based on total output volume, we are charged for all of that invisible scratchpad work in addition to the visible response, effectively doubling the compute consumed per query. Moving forward, we can control this cost by restricting reasoning strictly to complex, high-stakes workflows where higher accuracy justifies the premium, while routing routine tasks back to standard, lower-cost models.

输出 908 tok (+799 思考) 延迟 18.0 s

GPT-6.1 Terra 通过 · 3 sentences

Enabling reasoning caused the model to process additional internal tokens before producing each answer, even though those tokens are not visible to users. Those tokens are generally billable, increasing the cost per request and potentially doubling the bill even if usage stayed the same. To confirm the cause, compare request counts, model pricing, and token usage—including reasoning tokens—before and after the change.

输出 196 tok (+115 思考) 延迟 4.6 s

指令遵循(恰好三句,数得出来)、受众适配(对 CFO 说话的口吻),以及下方 token 计数暴露出的隐藏思考计费差额。

提示词 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. 检查 修复通过测试

Gemini 4 Carbon 通过 · 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 original function counts the number of matching adjacent *transitions* rather than the number of *elements* in a run because `best` and `cur` are initialized and reset to `0` instead of `1`. Because a single item on its own already forms a run of length `1`, starting at `0` causes every non-empty result to be short by one: single-element lists (where the loop never executes) and lists with no duplicates return `0` instead of `1`, and any run of $k$ equal items—including one ending at the last index—only increments `cur` $k - 1$ times, making it appear as though the final element of the run was missed. […]

输出 1411 tok (+1131 思考) 延迟 32.7 s

GPT-6.1 Terra 通过 · 8/8 cases

```python def longest_run(xs): if len(xs) == 0: 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 every nonempty run was undercounted by one, including a single-element input. It did update `best` for matches at the last index, but still undercounted those runs. The fix starts each run at length one and updates `best` as the run grows.

输出 331 tok (+172 思考) 延迟 6.3 s

修复是否真的正确(能运行)、解释的信息密度,以及在一个范围明确的任务上的 token 效率。

提示词 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. 检查 合法 JSON,严格符合 schema

Gemini 4 Carbon 通过 · 5/5 fields, guidance null

```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": null, "growth_pct": null, "guidance": null } ```

输出 3338 tok (+3281 思考) 延迟 61.6 s

GPT-6.1 Terra 通过 · 5/5 fields, guidance "Withheld pending the Q4 close"

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

输出 317 tok (+261 思考) 延迟 6.9 s

是否严守 schema(不臆造字段)、能否顶住幻觉压力(原文明说暂不给出 guidance),以及结构化输出路径的差异。

提示词 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. 检查 120 词,0 个禁用词

Gemini 4 Carbon 通过 · 120 words, 0 banned, 1 question

Are your engineering teams paying multiple AI vendors to generate identical responses? Today, we are introducing Universal Prompt Caching for our flagship API Gateway. When applications route traffic across providers like OpenAI, Anthropic, and Mistral, duplicate queries drain budgets and degrade user experiences. Our new unified caching layer intercepts incoming prompts directly at the network edge. If an identical request was previously fulfilled by any connected model, the gateway delivers the stored response in milliseconds, completely bypassing external API calls. This practical upgrade cuts monthly token expenses substantially while accelerating overall application speed. Best of all, deployment requires zero complex code changes. Simply activate this capability inside your gateway configuration dashboard today to start reducing latency and infrastructure costs immediately.

输出 2620 tok (+2480 思考) 延迟 31.1 s

GPT-6.1 Terra 通过 · 120 words, 0 banned, 1 question

Meet Prompt Cache, a new API gateway feature that stores reusable prompts across providers, helping teams reduce latency and control costs without changing how they build. When a request matches a cached prompt, the gateway retrieves the stored result instead of sending the same work again. Need to route traffic between models or vendors? Prompt Cache works across supported providers, giving your applications a consistent caching layer as your stack evolves. Set expiration policies, monitor cache performance, and choose which requests qualify through familiar gateway controls. Your team can spend less time repeating requests and more time improving the experiences customers rely on. Start using Prompt Cache today and make every request work harder for your application and your budget.

输出 579 tok (+440 思考) 延迟 9.1 s

是否守住约束(字数预算、禁用词表、只能有一个问句)、文风特征,以及长度控制。

改一行代码就能在两个模型之间切换

下方每个标签页里都有两个模型 ID,高亮的那两行是唯一要改的地方。端点不变,API key 不变,请求结构也不变。

from openai import OpenAI

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

resp = client.chat.completions.create(
    model="gemini-4-carbon",
    # model="gpt-6.1-terra",  # 取消注释此行,注释上一行
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

获取 API key →

常见问题

Gemini 4 Carbon 和 GPT-6.1 Terra 哪个更便宜?

主表显示基础档。提示词长度可能改变整次请求的费率,各模型页有完整价目。

不用分别集成两次,就能对 Gemini 4 Carbon 和 GPT-6.1 Terra 做 A/B 测试吗?

可以。两个模型走同一个 OpenAI 兼容端点,用同一个 API key,切换时只要改一行里的模型名,所以可以给两个模型各分一部分流量,直接对比账单。

Gemini 4 Carbon 和 GPT-6.1 Terra 支持提示词缓存吗?

支持。两个模型的缓存读取价都低于各自的输入价,所以前缀能反复命中缓存的负载,实际成本会比按官网价估算的低。具体的缓存读取价见上方价格表。

相关对比

我们的实测研究