Devstral Small vs Codestral
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Devstral Small dari Mistral AI dan Codestral dari Mistral AI adalah dua model AI unggulan. Devstral Small menawarkan jendela konteks 128K token dengan harga $0.15/$0.45 per 1 juta token, sedangkan Codestral menyediakan konteks 256K token seharga $0.20/$0.60 per 1 juta token. Berikut perbandingan lengkap benchmark, latensi, dan biayanya.
Ganti & Bandingkan Model Apa Saja
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Devstral Small
Model Agen Otonom & AlatDevstral Small dari Mistral AI adalah model AI yang dirancang untuk alur kerja agen otonom, pemanggilan alat (tool calling), dan otomatisasi multi-langkah, menghadirkan jendela konteks 128K, kecepatan 95 token/detik, indeks kecerdasan 45/10
$0.15 / 1M
$0.45 / 1M
128K tokens
42%
Codestral
Spesialis Kode Open-WeightsCodestral dari Mistral AI adalah model AI yang dirancang untuk pengembangan perangkat lunak dan pembuatan kode dengan bobot terbuka (open-weights), menghadirkan jendela konteks 256K, kecepatan 110 token/detik, indeks kecerdasan 40/100, sert
$0.20 / 1M
$0.60 / 1M
256K tokens
28%
Perbedaan Utama Sekilas
- Devstral Small is 1.3x cheaper for API usage (input + output tokens combined).
- Codestral has a larger context window (256K vs 128K tokens).
- Codestral is faster at 110 tok/s vs 95 tok/s.
- Devstral Small leads on SWE-bench coding (42.0% vs 28.0%).
| Feature | Devstral Small | Codestral |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 45 | 40 |
Provider | Mistral AI | Mistral AI |
Input Price Cost per million input tokens | $0.15 / 1M | $0.20 / 1M |
Output Price Cost per million output tokens | $0.45 / 1M | $0.60 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $0.11 / 1M | $0.14 / 1M |
Context Window Maximum input + output tokens | 128K tokens~192 A4 pages of text | 256K tokens~384 A4 pages of text |
Max Output Tokens Per single request | 16K | 8K |
Throughput Speed Tokens generated per second | 95 tok/s | 110 tok/s |
SWE-bench Verified Real-world software engineering | 42% | 28% |
GPQA Diamond Graduate-level reasoning | 50% | 42% |
Cached Input Price Prompt caching discount per 1M tokens | $0.05 / 1M | $0.05 / 1M |
Siapa Unggul di Mana?
At-a-glance decision frameworkSkor Benchmark Terverifikasi
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.
Latensi & Waktu Respons
Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.
Simulator Biaya Token Interaktif
Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.
Devstral Small · Strengths & Key Advantages
- Jendela konteks 128K dengan kapasitas output maksimum hingga 16K token (SWE-bench Verified 42% · GPQA Diamond 50%)
- Kecepatan generasi tinggi 95 token/detik dengan latensi token pertama (TTFT) hanya 420 ms
- Bobot terbuka (24B) yang siap di-hosting mandiri di GPU lokal atau cloud privat melalui vLLM dan Ollama
Considerations & Trade-offs
- Membutuhkan infrastruktur GPU dengan kapasitas VRAM yang memadai untuk eksekusi lokal presisi penuh
- Pada tugas pembuktian ilmiah tingkat ekstrem, model penalaran berat kelas atas memberikan kedalaman lebih tinggi
Codestral · Strengths & Key Advantages
- Jendela konteks 256K dengan kapasitas output maksimum hingga 8K token (SWE-bench Verified 28% · GPQA Diamond 42%)
- Kecepatan generasi tinggi 110 token/detik dengan latensi token pertama (TTFT) hanya 350 ms
- Bobot terbuka (22B) yang siap di-hosting mandiri di GPU lokal atau cloud privat melalui vLLM dan Ollama
Considerations & Trade-offs
- Membutuhkan infrastruktur GPU dengan kapasitas VRAM yang memadai untuk eksekusi lokal presisi penuh
- Pada tugas pembuktian ilmiah tingkat ekstrem, model penalaran berat kelas atas memberikan kedalaman lebih tinggi
Token Use & Task Economics
Estimated cost and token consumption to complete one representative agentic task.
| Metric | Devstral Small | Codestral |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.14 | $0.20 |
Output Tokens / Task Tokens generated per task | 30K | 24K |
Reasoning Tokens / Task Thinking tokens burned per task | 0K | 0K |
Spesifikasi Teknis
Architecture, release timeline, capabilities, and modalities.
| Feature | Devstral Small | Codestral |
|---|---|---|
| Official API Model ID (SDK) | devstral-small-latest | codestral-latest |
| API Protocol | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI |
| Release Date | 2025-07 | 2024-05 |
| Knowledge Cutoff | May 2025 | May 2024 |
| Architecture | Code-Optimized Autoregressive Transformer | Code-Optimized Transformer with 32K Window |
| Parameters | 24B | 22B |
| 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) | Flat rate ($0.15/1M in) across full 128K window | Flat rate ($0.2/1M in) across full 256K window |
| Prompt Cache Policy & TTL | Cached input at $0.05/1M tokens | Cached input at $0.05/1M tokens |
| Computer Use / GUI Agent | API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop) | 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 | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools | 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) | Text BPE (~4 chars/token) |
| Quantization & Min GPU VRAM | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 15 GB VRAM (4-bit Quantized) · 52 GB VRAM (Native BF16) | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 14 GB VRAM (4-bit Quantized) · 47 GB VRAM (Native BF16) |
| Safety & Frontier Classification | Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma) | 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 | text |
| Output Modalities | text | text |
Devstral Small vs Codestral: Jawaban Cepat (FAQ)
Which is more intelligent, Devstral Small or Codestral?
Devstral Small is more intelligent. It scores 45 compared with 40 on the composite Intelligence Index.
Which model is faster?
Codestral is faster, generating 110 tokens per second compared with 95 tokens per second.
Which model is cheaper to run?
Devstral Small is cheaper at $0.11 per 1M tokens blended, compared with $0.14 (7:2:1 cache:input:output ratio).
Which model has lower latency?
Codestral has lower latency, with a time to first token of 0.35s compared with 0.42s.
Which model has a larger context window?
Codestral has a larger context window, supporting 256K tokens compared with 128K tokens.
Kesimpulan
Baik Devstral Small (Sangat cocok untuk alur kerja agen otonom, pemanggilan alat (tool calling), dan otomatisasi multi-langkah, sistem RAG perusahaan, dan integrasi API skala produksi.) maupun Codestral (Sangat cocok untuk pengembangan perangkat lunak dan pembuatan kode dengan bobot terbuka (open-weights), sistem RAG perusahaan, dan integrasi API skala produksi.) sangat tangguh: Devstral Small unggul dalam penalaran dan pemrograman, Codestral memberikan kecepatan generasi token lebih tinggi, dan Devstral Small lebih hemat biaya untuk penggunaan API skala besar.
Pertanyaan Umum (FAQ)
Mana yang lebih baik untuk coding dan penalaran, Devstral Small atau Codestral?+
Dalam indeks kecerdasan gabungan dan benchmark coding, Devstral Small memimpin. Lihat skor SWE-bench dan GPQA di atas untuk detailnya.
Berapa perbandingan harga API Devstral Small vs Codestral?+
Devstral Small mengenakan biaya $0.15 / $0.45 per 1M token input/output, sedangkan Codestral sebesar $0.20 / $0.60. Secara keseluruhan, Devstral Small lebih hemat biaya.
Model mana yang memiliki jendela konteks lebih besar dan kecepatan lebih tinggi?+
Devstral Small mendukung konteks 128K token dibandingkan 256K token pada Codestral, sementara Codestral unggul dalam kecepatan output token per detik.
Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.
Related reading
- Codestral vs DeepSeek-Coder-V2 236B: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Devstral Small vs GPT-5.1 Codex mini: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Aion-3.0 vs Aion-Mini: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Aion-3.0 vs Gemini 3.6 Flash: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Aion-Mini vs Laguna XS 2.1: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Aya Expanse 32B vs Llama 3.2 90B Vision: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
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.
Sumber resmi: Dokumentasi API resmi Mistral AI & Mistral AI serta evaluasi benchmark independen (2026).