Devstral Medium vs GPT-5.1 Codex mini
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Mistral AI 的 Devstral Medium 与 OpenAI 的 GPT-5.1 Codex mini 是当前备受关注的两款主力 AI 模型。Devstral Medium 提供 128K Token 上下文窗口，API 定价为每百万 Token 输入 $0.80 / 输出 $2.40；而 GPT-5.1 Codex mini 提供 400K Token 上下文窗口，定价为每百万 Token 输入 $0.25 / 输出 $2.00。以下为两者的基准测试、延迟与成本全面对比。
切换并对比任意模型
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Devstral Medium
自主智能体与工具专家Mistral AI 推出的 Devstral Medium 是一款专为长周期自主智能体 (Agent)、工具调用与自动化工作流打造的大模型，具备 128K 上下文窗口、75 Token/秒生成速度与 52/100 综合智能指数（每百万 Token $0.8 输入 / $2.4 输出）。
$0.80 / 1M
$2.40 / 1M
128K tokens
51.5%
GPT-5.1 Codex mini
轻量级高性价比模型OpenAI 推出的 GPT-5.1 Codex mini 是一款兼顾极低 API 调用成本与高吞吐效率的轻量级大模型，具备 400K 上下文窗口、180 Token/秒生成速度与 47/100 综合智能指数（每百万 Token $0.25 输入 / $2 输出）。
$0.25 / 1M
$2.00 / 1M
400K tokens
55.5%
核心差异一览
- GPT-5.1 Codex mini is 1.7x cheaper for API usage (input + output tokens combined).
- GPT-5.1 Codex mini has a larger context window (400K vs 128K tokens).
- GPT-5.1 Codex mini is faster at 180 tok/s vs 75 tok/s.
- GPT-5.1 Codex mini leads on SWE-bench coding (55.5% vs 51.5%).
| Feature | Devstral Medium | GPT-5.1 Codex mini |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 52 | 47 |
Provider | Mistral AI | OpenAI |
Input Price Cost per million input tokens | $0.80 / 1M | $0.25 / 1M |
Output Price Cost per million output tokens | $2.40 / 1M | $2.00 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $0.54 / 1M | $0.27 / 1M |
Context Window Maximum input + output tokens | 128K tokens~192 A4 pages of text | 400K tokens~600 A4 pages of text |
Max Output Tokens Per single request | 33K | 128K |
Throughput Speed Tokens generated per second | 75 tok/s | 180 tok/s |
SWE-bench Verified Real-world software engineering | 51.5% | 55.5% |
GPQA Diamond Graduate-level reasoning | 62% | 66.5% |
Cached Input Price Prompt caching discount per 1M tokens | $0.20 / 1M | $0.03 / 1M |
各项指标谁更胜一筹？
At-a-glance decision framework权威基准测试得分对比
Official evaluation metrics verified by independent third-party research labs.
Industry benchmark evaluating real-world GitHub issue resolution and multi-file debugging.
Challenging questions created by domain experts to test complex PhD-level reasoning.
Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.
Crowdsourced human preference evaluation based on blind, head-to-head model battles.
Extremely difficult, closed-ended questions spanning the frontier of human expert knowledge.
Autonomous multi-step tasks executed inside a real command-line terminal environment.
Research-grade coding problems drawn from real scientific and numerical workloads.
Contamination-free competitive programming problems collected continuously over time.
American Invitational Mathematics Examination — multi-step Olympiad-level reasoning.
Accuracy when reasoning over very large inputs that fill the model context window.
Tokens emitted per second during active generation streaming.
延迟与响应速度
Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.
实时 Token 成本模拟器
Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.
Devstral Medium · Strengths & Key Advantages
- 提供 128K 上下文窗口与最高 33K 输出容量，核心基准表现优异（SWE-bench Verified 51.5% · GPQA Diamond 62%）
- 高达 75 Token/秒的生成吞吐量，首字延迟 (TTFT) 仅约 500 毫秒
- 极具竞争力的 API 定价（每百万 Token $0.8 输入 / $2.4 输出），原生支持提示词缓存、函数调用与结构化 JSON 输出
Considerations & Trade-offs
- 闭源专有云端模型，不支持下载权重进行离线本地物理隔离部署
- 在超长链路的前沿科研推导任务上，深度略逊于顶配重型旗舰推理模型
GPT-5.1 Codex mini · Strengths & Key Advantages
- 提供 400K 上下文窗口与最高 128K 输出容量，核心基准表现优异（SWE-bench Verified 55.5% · GPQA Diamond 66.5%）
- 高达 180 Token/秒的生成吞吐量，首字延迟 (TTFT) 仅约 720 毫秒
- 极具竞争力的 API 定价（每百万 Token $0.25 输入 / $2 输出），原生支持提示词缓存、函数调用与结构化 JSON 输出
Considerations & Trade-offs
- 闭源专有云端模型，不支持下载权重进行离线本地物理隔离部署
- 在超长链路的前沿科研推导任务上，深度略逊于顶配重型旗舰推理模型
Token Use & Task Economics
Estimated cost and token consumption to complete one representative agentic task.
| Metric | Devstral Medium | GPT-5.1 Codex mini |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.55 | $0.33 |
Output Tokens / Task Tokens generated per task | 38K | 48K |
Reasoning Tokens / Task Thinking tokens burned per task | 18K | 23K |
技术规格参数
Architecture, release timeline, capabilities, and modalities.
| Feature | Devstral Medium | GPT-5.1 Codex mini |
|---|---|---|
| Official API Model ID (SDK) | devstral-medium-latest | gpt-5-1-codex-mini |
| API Protocol | Mistral AI REST API (OpenAI-Compatible) | OpenAI Responses API & Chat Completions v1 |
| Release Date | 2025-07 | 2025-11 |
| Knowledge Cutoff | May 2025 | October 2024 |
| Architecture | High-Capacity Agentic Code Transformer | Compact code-specialised reasoning model |
| Parameters | Confidential (~70B) | Confidential |
| Enterprise Rate Limits (RPM / TPM) | 5,000 – 15,000 RPM (Production Tier) · 800,000 – 2,000,000 TPM | 10,000 – 30,000 RPM (Tier 5 Enterprise) · 800,000 – 2,000,000 TPM |
| Long-Context Tier (>128K/200K) | Flat rate ($0.8/1M in) across full 128K window | Flat rate ($0.25/1M in) across full 400K window |
| Prompt Cache Policy & TTL | Cached input at $0.2/1M tokens | Automatic prefix caching at $0.025/1M (no extra cache-write fee) |
| Computer Use / GUI Agent | API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop) | Supported (Screen coordinate grounding, browser & desktop GUI action loops) |
| MCP & Parallel Tool Calling | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema |
| Web Search Grounding & Sandbox | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools | Native Web Search tool + Hosted Code Interpreter & File Search RAG |
| Official Fine-Tuning Support | API Prompt Engineering & RAG Distillation | Supervised Fine-Tuning (SFT), Direct Preference (DPO) & Reinforcement Fine-Tuning (RFT) |
| Multimodal Token Billing | Text BPE (~4 chars/token) | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) |
| Quantization & Min GPU VRAM | Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster) · Zero Local VRAM Required (100% Serverless Cloud API) | Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster) · Zero Local VRAM Required (100% Serverless Cloud API) |
| Safety & Frontier Classification | Mistral AI Production Safety & Alignment Verified | OpenAI Preparedness Framework Audited & System Card Published |
| Enterprise Compliance (ZDR/HIPAA/SOC2) | SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier | SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier |
| Input Modalities | text | text, vision |
| Output Modalities | text | text |
Devstral Medium vs GPT-5.1 Codex mini: 常见问题解答 (FAQ)
Which is more intelligent, Devstral Medium or GPT-5.1 Codex mini?
Devstral Medium is more intelligent. It scores 52 compared with 47 on the composite Intelligence Index.
Which model is faster?
GPT-5.1 Codex mini is faster, generating 180 tokens per second compared with 75 tokens per second.
Which model is cheaper to run?
GPT-5.1 Codex mini is cheaper at $0.27 per 1M tokens blended, compared with $0.54 (7:2:1 cache:input:output ratio).
Which model has lower latency?
Devstral Medium has lower latency, with a time to first token of 0.50s compared with 0.72s.
Which model has a larger context window?
GPT-5.1 Codex mini has a larger context window, supporting 400K tokens compared with 128K tokens.
综合结论
综合来看，Devstral Medium（适合：专为长周期自主智能体 (Agent)、工具调用与自动化工作流打造的任务、企业级 RAG 检索增强生成、自动化智能体工作流与高可靠 API 集成。）与 GPT-5.1 Codex mini（适合：兼顾极低 API 调用成本与高吞吐效率的轻量级任务、企业级 RAG 检索增强生成、自动化智能体工作流与高可靠 API 集成。）各具优势：Devstral Medium 在综合智能与编程基准测试中表现更强，GPT-5.1 Codex mini 拥有更快的 Token 生成速度，而 GPT-5.1 Codex mini 则在规模化 API 部署中具备更高的成本效益。
常见问题 (FAQ)
在编程和深度推理方面，Devstral Medium 和 GPT-5.1 Codex mini 哪个更强？+
在综合智能指数与编程基准评测中，Devstral Medium 表现占优。建议结合上方的 SWE-bench Verified 与 GPQA Diamond 跑分根据具体场景选择。
Devstral Medium 与 GPT-5.1 Codex mini 的 API 价格哪个更便宜？+
Devstral Medium 的 API 价格为输入 $0.80 / 输出 $2.40（每百万 Token），GPT-5.1 Codex mini 为输入 $0.25 / 输出 $2.00。综合混合成本来看，GPT-5.1 Codex mini 更具性价比。
哪款模型拥有更大的上下文窗口和更快的响应速度？+
Devstral Medium 支持 128K Token 上下文窗口，而 GPT-5.1 Codex mini 支持 400K Token。在流式生成速度方面，GPT-5.1 Codex mini 的吞吐表现更快。
Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.
Related reading
- Devstral Small vs GPT-5.1 Codex mini：基准测试、API 价格与速度全面对比 (2026)对比
- GPT-5.1 Codex mini vs GPT-5-Codex：基准测试、API 价格与速度全面对比 (2026)对比
- GPT-5.1 Codex vs GPT-5.1 Codex mini：基准测试、API 价格与速度全面对比 (2026)对比
- North Mini Code vs GPT-5.1 Codex mini：基准测试、API 价格与速度全面对比 (2026)对比
- Qwen3-Coder 30B-A3B Instruct vs Devstral Medium：基准测试、API 价格与速度全面对比 (2026)对比
- Qwen3 Coder Flash vs Devstral Medium：基准测试、API 价格与速度全面对比 (2026)对比
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
数据来源: Mistral AI 与 OpenAI 官方 API 文档、模型发布说明及独立基准测试报告 (2026)。