Gemma 4 31B vs Mistral Small 4
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Google 的 Gemma 4 31B 与 Mistral AI 的 Mistral Small 4 是当前备受关注的两款主力 AI 模型。Gemma 4 31B 提供 262.1K Token 上下文窗口，API 定价为每百万 Token 输入 $0.00 / 输出 $0.00；而 Mistral Small 4 提供 256K Token 上下文窗口，定价为每百万 Token 输入 $0.10 / 输出 $0.30。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.
Gemma 4 31B
开源权重推理大模型Google 推出的 Gemma 4 31B 是一款通过大规模强化学习训练、支持私有化部署的开源权重推理大模型，具备 262K 上下文窗口、80 Token/秒生成速度与 81/100 综合智能指数（免费开源权重）。
$0.00 / 1M
$0.00 / 1M
262.1K tokens
68.5%
Mistral Small 4
超高速低延迟推理Mistral AI 推出的 Mistral Small 4 是一款面向实时交互对话、高并发路由与极低延迟生产环境的超高速大模型，具备 256K 上下文窗口、120 Token/秒生成速度与 48/100 综合智能指数（每百万 Token $0.1 输入 / $0.3 输出）。
$0.10 / 1M
$0.30 / 1M
256K tokens
44.5%
核心差异一览
- Gemma 4 31B is 1.0x cheaper for API usage (input + output tokens combined).
- Gemma 4 31B has a larger context window (262K vs 256K tokens).
- Mistral Small 4 is faster at 120 tok/s vs 80 tok/s.
- Gemma 4 31B leads on SWE-bench coding (68.5% vs 44.5%).
| Feature | Gemma 4 31B | Mistral Small 4 |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 81 | 48 |
Provider | Mistral AI | |
Input Price Cost per million input tokens | $0.00 / 1M | $0.10 / 1M |
Output Price Cost per million output tokens | $0.00 / 1M | $0.30 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $0.00 / 1M | $0.07 / 1M |
Context Window Maximum input + output tokens | 262.1K tokens~393 A4 pages of text | 256K tokens~384 A4 pages of text |
Max Output Tokens Per single request | 33K | 16K |
Throughput Speed Tokens generated per second | 80 tok/s | 120 tok/s |
SWE-bench Verified Real-world software engineering | 68.5% | 44.5% |
GPQA Diamond Graduate-level reasoning | 77% | 56% |
Cached Input Price Prompt caching discount per 1M tokens | $0.00 / 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.
Autonomous multi-step tasks executed inside a real command-line terminal environment.
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.
Gemma 4 31B · Strengths & Key Advantages
- 提供 262K 上下文窗口与最高 33K 输出容量，核心基准表现优异（SWE-bench Verified 68.5% · GPQA Diamond 77%）
- 高达 80 Token/秒的生成吞吐量，首字延迟 (TTFT) 仅约 480 毫秒
- 开放模型权重 (31B)，支持通过 vLLM、SGLang 或 Ollama 在私有 GPU 集群上本地部署与微调
Considerations & Trade-offs
- 在本地以满血精度运行需要较高的 GPU 显存 (VRAM) 与运维基础设施
- 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
Mistral Small 4 · Strengths & Key Advantages
- 提供 256K 上下文窗口与最高 16K 输出容量，核心基准表现优异（SWE-bench Verified 44.5% · GPQA Diamond 56%）
- 高达 120 Token/秒的生成吞吐量，首字延迟 (TTFT) 仅约 340 毫秒
- 开放模型权重 (24B)，支持通过 vLLM、SGLang 或 Ollama 在私有 GPU 集群上本地部署与微调
Considerations & Trade-offs
- 在本地以满血精度运行需要较高的 GPU 显存 (VRAM) 与运维基础设施
- 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 | Gemma 4 31B | Mistral Small 4 |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.00 | $0.12 |
Output Tokens / Task Tokens generated per task | 12K | 28K |
Reasoning Tokens / Task Thinking tokens burned per task | 6K | 12K |
技术规格参数
Architecture, release timeline, capabilities, and modalities.
| Feature | Gemma 4 31B | Mistral Small 4 |
|---|---|---|
| Official API Model ID (SDK) | models/gemma-4-31b | mistral-small-4-latest |
| API Protocol | Google Gemini API (generateContent) + OpenAI-Compatible SDK | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI |
| Release Date | 2026-04 | 2026-03 |
| Knowledge Cutoff | January 2026 | January 2026 |
| Architecture | Dense open reasoning transformer with native thinking | Next-Gen Compact Multimodal Transformer |
| Parameters | 31B | 24B |
| Enterprise Rate Limits (RPM / TPM) | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud |
| Long-Context Tier (>128K/200K) | Free across full context window (only KV-cache VRAM scales) | Flat rate ($0.1/1M in) across full 256K window |
| Prompt Cache Policy & TTL | Automatic prefix KV-caching in vLLM / SGLang (0 cost) | Cached input at $0.03/1M tokens |
| Computer Use / GUI Agent | Supported (Screen coordinate grounding, browser & desktop GUI action loops) | API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop) |
| 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 | Built-in Google Search Grounding + Managed Python Code Execution Sandbox | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools |
| Official Fine-Tuning Support | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) |
| Multimodal Token Billing | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) |
| Quantization & Min GPU VRAM | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 19 GB VRAM (4-bit Quantized) · 67 GB VRAM (Native BF16) | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 15 GB VRAM (4-bit Quantized) · 52 GB VRAM (Native BF16) |
| Safety & Frontier Classification | Google DeepMind Frontier Safety Framework Verified | Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma) |
| Enterprise Compliance (ZDR/HIPAA/SOC2) | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control |
| Input Modalities | text, vision | text, vision |
| Output Modalities | text | text |
Gemma 4 31B vs Mistral Small 4: 常见问题解答 (FAQ)
Which is more intelligent, Gemma 4 31B or Mistral Small 4?
Gemma 4 31B is more intelligent. It scores 81 compared with 48 on the composite Intelligence Index.
Which model is faster?
Mistral Small 4 is faster, generating 120 tokens per second compared with 80 tokens per second.
Which model is cheaper to run?
Gemma 4 31B is cheaper at $0.00 per 1M tokens blended, compared with $0.07 (7:2:1 cache:input:output ratio).
Which model has lower latency?
Mistral Small 4 has lower latency, with a time to first token of 0.34s compared with 0.48s.
Which model has a larger context window?
Gemma 4 31B has a larger context window, supporting 262.1K tokens compared with 256K tokens.
综合结论
综合来看，Gemma 4 31B（适合：通过大规模强化学习训练、支持私有化部署的开源权重推理任务、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 Mistral Small 4（适合：面向实时交互对话、高并发路由与极低延迟生产环境的超高速任务、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：Gemma 4 31B 在综合智能与编程基准测试中表现更强，Mistral Small 4 拥有更快的 Token 生成速度，而 Gemma 4 31B 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，Gemma 4 31B 和 Mistral Small 4 哪个更强？+
在综合智能指数与编程基准评测中，Gemma 4 31B 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。
Gemma 4 31B 与 Mistral Small 4 的 API 价格哪个更便宜？+
Gemma 4 31B 的 API 价格为输入 $0.00 / 输出 $0.00（每百万 Token），Mistral Small 4 为输入 $0.10 / 输出 $0.30。综合混合成本来看，Gemma 4 31B 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？+
Gemma 4 31B 支持 262.1K Token 上下文窗口，而 Mistral Small 4 支持 256K Token。在流式生成速度方面，Mistral Small 4 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
- Gemma 4 31B vs Gemma 4 26B A4B：基准测试、API 价格与速度全面对比 (2026)对比
- Gemma 4 31B vs Llama 3.3 70B：基准测试、API 价格与速度全面对比 (2026)对比
- Gemma 4 E2B vs Gemma 4 31B：基准测试、API 价格与速度全面对比 (2026)对比
- Mistral Small 4 vs Claude Haiku 5.5：基准测试、API 价格与速度全面对比 (2026)对比
- Mistral Small 4 vs GPT-4.1 mini：基准测试、API 价格与速度全面对比 (2026)对比
- Nemotron 3 Nano Omni 30B A3B Reasoning vs Mistral Small 4：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: Google 与 Mistral AI 官方 API 文档、模型发布说明及独立基准测试报告 (2026)。