Devstral Small vs Codestral
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Devstral Small by Mistral AI and Codestral by Mistral AI represent two of the frontier AI models analyzed in our comprehensive 2026 AI benchmark and LLM comparison. In this head-to-head evaluation, we examine API token pricing, context window specifications, inference speed (tokens per second), and empirical reasoning performance. From a pure economic perspective, Devstral Small holds a notable pricing advantage for token ingestion. On output generation, Devstral Small is more economical per million generated tokens. In data-heavy architectures requiring extensive repository or document analysis, Codestral provides an expanded memory horizon with 256K tokens. In latency-sensitive production environments, Codestral leads in tokens-per-second throughput, making it ideal for real-time conversational agents and high-concurrency workflows. Below is the complete empirical head-to-head breakdown across cost, speed, context, and capability matrices.
Troque e Compare Qualquer Modelo
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Devstral Small
Modelo de Pesos AbertosO Devstral Small da Mistral AI é um modelo de inteligência artificial com janela de contexto de 128K tokens e preço de API de $0.15/1M na entrada e $0.45/1M na saída, projetado para programação, raciocínio e automação empresarial.
$0.15 / 1M
$0.45 / 1M
128K tokens
42%
Codestral
Modelo de Pesos AbertosO Codestral da Mistral AI é um modelo de inteligência artificial com janela de contexto de 256K tokens e preço de API de $0.2/1M na entrada e $0.6/1M na saída, projetado para programação, raciocínio e automação empresarial.
$0.20 / 1M
$0.60 / 1M
256K tokens
28%
Principais Diferenças em Resumo
- 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 |
Quem vence em cada categoria?
At-a-glance decision frameworkPontuações de Benchmarks Verificadas
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.
Latência e Tempo de Resposta
Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.
Simulador Interativo de Custo de Tokens
Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.
Devstral Small · Strengths & Key Advantages
- Arquitetura Code-Optimized Autoregressive Transformer avançada da Mistral AI com contexto de 128K tokens
- Excelente relação custo-benefício ($0.15/1M entrada, $0.45/1M saída) e baixa latência
- Forte desempenho em benchmarks de código, análise lógica e tarefas multilíngues
Considerations & Trade-offs
- Cargas de trabalho com contexto máximo exigem monitoramento de custos de tokens
- Requer engenharia de prompt adequada para fluxos de trabalho altamente específicos
Codestral · Strengths & Key Advantages
- Arquitetura Code-Optimized Transformer with 32K Window avançada da Mistral AI com contexto de 256K tokens
- Excelente relação custo-benefício ($0.2/1M entrada, $0.6/1M saída) e baixa latência
- Forte desempenho em benchmarks de código, análise lógica e tarefas multilíngues
Considerations & Trade-offs
- Cargas de trabalho com contexto máximo exigem monitoramento de custos de tokens
- Requer engenharia de prompt adequada para fluxos de trabalho altamente específicos
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 |
Especificações Técnicas
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: Respostas Rápidas (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.
Veredito
Verdict & Model Selection Recommendation: Choose Devstral Small if your priority is Local IDE coding companions, automated unit test generation, and secure on-premise PR reviews. Its performance in demanding tasks justifies its operational token cost. Choose Codestral if your workflow prioritizes VS Code and JetBrains extension backends, automated test generation, and multi-language translation. For large-scale batch processing or customer-facing conversational interfaces, its balance of speed and economics delivers superior ROI.
Perguntas Frequentes (FAQ)
How does Devstral Small compare to Codestral in API token pricing and cost per token?+
Devstral Small costs $0.15 per 1M input tokens and $0.45 per 1M output tokens, whereas Codestral costs $0.20 input and $0.60 output. Overall, Devstral Small is the more cost-effective model for high-volume API pipelines. Both models support prompt caching discounts of up to 90% for repeated prompt prefixes.
Which model has a larger context window: Devstral Small or Codestral?+
Devstral Small supports a context window of 128K tokens (~96k words), while Codestral supports 256K tokens (~192k words). Therefore, Codestral can process more textual data and document context in a single prompt.
Which AI model is better for software engineering and coding: Devstral Small or Codestral?+
Devstral Small scores 42% on SWE-bench Verified while Codestral scores 28%. For autonomous software engineering and multi-file debugging, Devstral Small holds the verified benchmark lead.
What is the difference in reasoning capability and extended thinking between Devstral Small and Codestral?+
Devstral Small is optimized for low-latency direct generation. In contrast, Codestral focuses on standard fast inference.
How does inference speed (tokens per second) compare between Devstral Small and Codestral?+
Devstral Small generates approximately 95 tokens per second, while Codestral delivers 110 tokens per second. In latency-sensitive production environments, Codestral provides faster time-to-first-token (TTFT) and higher streaming response velocity.
Can you implement a tiered LLM routing setup combining Devstral Small and Codestral to optimize costs?+
Yes! High-efficiency architectures route high-frequency routine classification and conversational tasks to Devstral Small to save operational costs, and dynamically escalate complex architectural queries or reasoning tasks to Codestral. This tiered routing pattern cuts overall API bills by up to 70%.
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: Benchmarks, Pricing & Speed ComparisonComparar
- Devstral Small vs GPT-5.1 Codex mini: Benchmarks, Pricing & Speed ComparisonComparar
- Aion-3.0 vs Aion-Mini: Benchmarks, Pricing & Speed ComparisonComparar
- Aion-3.0 vs Gemini 3.6 Flash: Benchmarks, Pricing & Speed ComparisonComparar
- Aion-Mini vs Laguna XS 2.1: Benchmarks, Pricing & Speed ComparisonComparar
- Aya Expanse 32B vs Llama 3.2 90B Vision: Benchmarks, Pricing & Speed ComparisonComparar
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.
Fontes oficiais: GetInfoUs Independent AI Benchmarks & Official API Specs