DeepSeek V4 Pro (0813) vs GPT-6 Astra
什么时候选哪个
对于需要长响应的基于文本的任务，请选择 deepseek-v4-pro-0813，因为它支持 393216 的最大输出，并且每百万 token 的输入成本仅为 $1.32，输出仅为 $3.96。如果你的工作负载需要图像输入和视觉能力，或者需要其略大一些的 1050000 token 上下文窗口，请选择 gpt-6-astra。这些附加能力伴随着价格的急剧上涨，因为 gpt-6-astra 收取每百万输入 token $10 和每百万输出 token $50 的费用。
Benchmark 成绩
6 项两边都有成绩。
供应商公布： Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
价格
| DeepSeek V4 Pro (0813) | GPT-6 Astra | Δ | |
|---|---|---|---|
| 输入 / 1M token | $1.32 | $10 | 0.13× |
| 输出 / 1M token | $3.96 | $50 | 0.079× |
| 缓存读取 / 1M token | $0.132 | $1 | 0.13× |
| 缓存写入 | 不单独收费 | 不单独收费 | - |
价格取自构建时的实时目录，最新价格见各模型页面。
两个模型所处的位置：全部 79 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
| DeepSeek V4 Pro (0813) | GPT-6 Astra | |
|---|---|---|
| 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（自动） |
| 缓存有效期 | no fixed TTL (evicted when unused) | 5-10m, up to 1h |
| 最小缓存前缀 | 未公布 | 1024 个 token |
规格
| DeepSeek V4 Pro (0813) | GPT-6 Astra | |
|---|---|---|
| 输入模态 | 文本 | 文本 图像 |
| 输出模态 | 文本 | 文本 |
| 发布日期 | 2026-08-13 | 2026-09-03 |
| 知识截止日期 | - | 2026-04 |
| 上下文窗口 | 1M | 1.1M |
| 最大输出 | 393K | 128K |
| 思考参数 | reasoning_effort | reasoning.effort |
| 可选值 | reasoning_effort
| reasoning.effort
|
| 默认值 | - | 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： DeepSeek V4 Pro (0813) · GPT-6 Astra
同一条提示词，两个模型，经网关实测
DeepSeek V4 Pro (0813) 通过 · 3 sentences
Enabling reasoning causes the model to generate a hidden chain-of-thought with many additional tokens before producing the final answer, which sharply increases compute consumption per request. Those extra reasoning tokens are billed at the same or higher rates, so total usage doubled even though the volume of final outputs stayed similar. We can control this by adjusting reasoning effort, setting token limits, or routing only complex requests through reasoning mode.
输出 308 tok (+226 思考) 延迟 5.1 s
GPT-6 Astra 通过 · 3 sentences
Enabling reasoning makes the model do more work per request, often generating internal reasoning tokens that are billed even though they do not appear in the final answer. If traffic, model choice, and pricing stayed the same, those extra tokens likely explain why our bill doubled—not longer answers or more users. We should verify the usage breakdown, then reserve higher reasoning levels for tasks where improved results justify the added cost.
输出 283 tok (+196 思考) 延迟 17.2 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。
DeepSeek V4 Pro (0813) 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 else: cur = 1 best = max(best, cur) return best ``` The bug is that `cur` was initialized to `0` and only counted adjacent matching pairs, so a run of length `n` produced `n - 1` (or `0` for a single element) instead of `n`. The code also reset to `0` on a change, when the new run should start at length `1`. Initializing `cur` and `best` to `1` fixes both the single-element case and runs ending at the last index.
输出 1315 tok (+1130 思考) 延迟 16.9 s
GPT-6 Astra 通过 · 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 counts equal adjacent pairs rather than items, so every nonempty run is undercounted by one: a single-element input returns `0`, and a run of three equal items returns `2`. Starting and resetting `cur` to `1` counts the first item of each run, while the empty-input check preserves a result of `0`. Updating `best` after each iteration includes runs ending at the last index without needing a final flush; the original also updated during trailing runs, but undercounted them.
输出 321 tok (+131 思考) 延迟 13.5 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。
DeepSeek V4 Pro (0813) 通过 · 5/5 fields, guidance null
{"company":"Meridian Robotics","quarter":"September quarter","revenue_usd_m":412,"growth_pct":11.0,"guidance":null}
输出 2155 tok (+2121 思考) 延迟 26.0 s
GPT-6 Astra 通过 · 5/5 fields, guidance "Formal guidance is withheld pending the "
{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": null, "growth_pct": "eleven and change", "guidance": "Formal guidance is withheld pending the Q4 close." }
输出 329 tok (+267 思考) 延迟 16.9 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。
DeepSeek V4 Pro (0813) 通过 · 121 words, 0 banned, 1 question
Introducing cross-provider prompt caching in our API gateway. Send a prompt once, and the gateway stores its computed prefix across Anthropic, OpenAI, and other LLM providers. Subsequent requests with the same prompt hit the cache, cutting latency and token costs while keeping outputs consistent across routing decisions and provider failovers. Teams can route identical prompts between providers without reprocessing shared context or lengthy system instructions. How much could you save on repeated prompt prefixes? The cache respects provider-specific key formats, handles TTLs automatically, and works with streaming and batch requests. Enable it with one configuration flag—no changes to your application code. Available today on all plans. Monitor cache hit rates, token savings, and provider-specific performance metrics in the live dashboard.
输出 2845 tok (+2694 思考) 延迟 25.5 s
GPT-6 Astra 通过 · 120 words, 0 banned, 1 question
Introducing Cross Provider Prompt Cache, a new API gateway feature that reuses eligible prompt content across supported AI providers. Why pay to process the same context every time? Configure caching once at the gateway, then route requests between models while keeping shared instructions, reference material, and conversation prefixes ready for reuse. Caching controls let teams set expiration windows, isolate tenants, and exclude sensitive content. Cache analytics show hit rates, estimated savings, and latency trends, helping developers tune performance with confidence. Existing routing policies continue to work, so adoption fits your current architecture. Start with a single application, measure the results, and expand as needed. Available today in the dashboard and API, with documentation and examples to guide your first deployment.
输出 665 tok (+516 思考) 延迟 19.3 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="deepseek-v4-pro-0813",
# model="gpt-6-astra", # 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)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "deepseek-v4-pro-0813",
// model: "gpt-6-astra", // 取消注释此行，注释上一行
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro-0813",
# "model": "gpt-6-astra", # 取消注释此行，注释上一行
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "deepseek-v4-pro-0813",
// Model: "gpt-6-astra", // 取消注释此行，注释上一行
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("deepseek-v4-pro-0813")
// .model("gpt-6-astra") // 取消注释此行，注释上一行
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));常见问题
DeepSeek V4 Pro (0813) 和 GPT-6 Astra 哪个更便宜？
按「输入 / 1M token」算，DeepSeek V4 Pro (0813) 更便宜（$1.32 对 $10，相差 7.6×）。其他计费项的结论可能相反，完整价格见上方表格，实际成本取决于你的用量构成。
不用分别集成两次，就能对 DeepSeek V4 Pro (0813) 和 GPT-6 Astra 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。
DeepSeek V4 Pro (0813) 和 GPT-6 Astra 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。