Codestral vs DeepSeek-Coder-V2 236B
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Codestral da Mistral AI e DeepSeek-Coder-V2 236B da DeepSeek são dois modelos de IA de destaque. O Codestral oferece uma janela de contexto de 256K tokens a $0.20/$0.60 por milhão de tokens, enquanto o DeepSeek-Coder-V2 236B oferece 128K tokens de contexto a $0.14/$0.28 por milhão de tokens. Veja abaixo a comparação completa de benchmarks, latência e custos.
Troque e Compare Qualquer Modelo
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Codestral
Especialista Aberto em CódigoO Codestral da Mistral AI é um modelo de IA projetado para desenvolvimento de software e geração de código com pesos abertos auto-hospedáveis, oferecendo janela de contexto de 256K, velocidade de 110 tokens/s, índice de inteligência de 40/1
$0.20 / 1M
$0.60 / 1M
256K tokens
28%
DeepSeek-Coder-V2 236B
Modelo Base de Pesos AbertosO DeepSeek-Coder-V2 236B da DeepSeek é um modelo de IA projetado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, oferecendo janela de contexto de 128K, velocidade de 74 tokens/s, índice de inteligência de 4
$0.14 / 1M
$0.28 / 1M
128K tokens
42.1%
Principais Diferenças em Resumo
- DeepSeek-Coder-V2 236B is 1.9x 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 74 tok/s.
- DeepSeek-Coder-V2 236B leads on SWE-bench coding (42.1% vs 28.0%).
| Feature | Codestral | DeepSeek-Coder-V2 236B |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 40 | 42 |
Provider | Mistral AI | DeepSeek |
Input Price Cost per million input tokens | $0.20 / 1M | $0.14 / 1M |
Output Price Cost per million output tokens | $0.60 / 1M | $0.28 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $0.14 / 1M | $0.07 / 1M |
Context Window Maximum input + output tokens | 256K tokens~384 A4 pages of text | 128K tokens~192 A4 pages of text |
Max Output Tokens Per single request | 8K | 8K |
Throughput Speed Tokens generated per second | 110 tok/s | 74 tok/s |
SWE-bench Verified Real-world software engineering | 28% | 42.1% |
GPQA Diamond Graduate-level reasoning | 42% | 49.5% |
Cached Input Price Prompt caching discount per 1M tokens | $0.05 / 1M | $0.01 / 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.
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.
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.
Codestral · Strengths & Key Advantages
- Janela de contexto de 256K com limite máximo de saída de 8K tokens (SWE-bench Verified 28% · GPQA Diamond 42%)
- Taxa de transferência rápida de 110 tokens/segundo com latência inicial (TTFT) de 350 ms
- Pesos abertos (22B) para auto-hospedagem local ou em nuvem privada via vLLM, SGLang ou Ollama
Considerations & Trade-offs
- Requer servidores GPU com memória VRAM adequada para execução local em precisão total
- Em derivações científicas extremas, modelos pesados dedicados exclusivamente ao raciocínio oferecem maior profundidade
DeepSeek-Coder-V2 236B · Strengths & Key Advantages
- Janela de contexto de 128K com limite máximo de saída de 8K tokens (SWE-bench Verified 42.1% · GPQA Diamond 49.5%)
- Taxa de transferência rápida de 74 tokens/segundo com latência inicial (TTFT) de 510 ms
- Pesos abertos (236B) para auto-hospedagem local ou em nuvem privada via vLLM, SGLang ou Ollama
Considerations & Trade-offs
- Requer servidores GPU com memória VRAM adequada para execução local em precisão total
- Em derivações científicas extremas, modelos pesados dedicados exclusivamente ao raciocínio oferecem maior profundidade
Token Use & Task Economics
Estimated cost and token consumption to complete one representative agentic task.
| Metric | Codestral | DeepSeek-Coder-V2 236B |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.20 | $0.14 |
Output Tokens / Task Tokens generated per task | 24K | 30K |
Reasoning Tokens / Task Thinking tokens burned per task | 0K | 0K |
Especificações Técnicas
Architecture, release timeline, capabilities, and modalities.
| Feature | Codestral | DeepSeek-Coder-V2 236B |
|---|---|---|
| Official API Model ID (SDK) | codestral-latest | deepseek-chat |
| API Protocol | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI |
| Release Date | 2024-05 | 2024-06 |
| Knowledge Cutoff | May 2024 | December 2023 |
| Architecture | Code-Optimized Transformer with 32K Window | 236B Mixture-of-Experts (21B active) |
| Parameters | 22B | 236B |
| 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 ($0.2/1M in) across full 256K window | Flat rate ($0.14/1M in) across full 128K window |
| Prompt Cache Policy & TTL | Cached input at $0.05/1M tokens | Automatic prefix caching at $0.014/1M (no extra cache-write fee) |
| 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) · 14 GB VRAM (4-bit Quantized) · 47 GB VRAM (Native BF16) | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 146 GB VRAM (4-bit Quantized) · 507 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 |
Codestral vs DeepSeek-Coder-V2 236B: Respostas Rápidas (FAQ)
Which is more intelligent, Codestral or DeepSeek-Coder-V2 236B?
DeepSeek-Coder-V2 236B is more intelligent. It scores 42 compared with 40 on the composite Intelligence Index.
Which model is faster?
Codestral is faster, generating 110 tokens per second compared with 74 tokens per second.
Which model is cheaper to run?
DeepSeek-Coder-V2 236B is cheaper at $0.07 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 0.51s.
Which model has a larger context window?
Codestral has a larger context window, supporting 256K tokens compared with 128K tokens.
Veredito
Tanto Codestral (Indicado para desenvolvimento de software e geração de código com pesos abertos auto-hospedáveis, arquiteturas RAG corporativas e integração escalável via API.) quanto DeepSeek-Coder-V2 236B (Indicado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, arquiteturas RAG corporativas e integração escalável via API.) entregam excelente desempenho: DeepSeek-Coder-V2 236B lidera em inteligência geral e programação, Codestral oferece geração mais rápida e DeepSeek-Coder-V2 236B apresenta o melhor custo-benefício em produção.
Perguntas Frequentes (FAQ)
Qual é melhor para programação e raciocínio, Codestral ou DeepSeek-Coder-V2 236B?+
Nas avaliações de inteligência e código, DeepSeek-Coder-V2 236B leva vantagem. Confira os gráficos SWE-bench e GPQA acima para detalhes.
Qual modelo tem a API mais barata, Codestral ou DeepSeek-Coder-V2 236B?+
O Codestral custa $0.20 / $0.60 por 1M de tokens (entrada/saída) e o DeepSeek-Coder-V2 236B custa $0.14 / $0.28. No custo combinado, DeepSeek-Coder-V2 236B é mais econômico.
Qual modelo possui maior janela de contexto e velocidade?+
O Codestral suporta 256K tokens de contexto contra 128K tokens do DeepSeek-Coder-V2 236B, enquanto Codestral entrega maior velocidade de geração.
Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.
Related reading
- Devstral Small vs. Codestral: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Qwen 2.5 Coder 32B vs. DeepSeek-Coder-V2 236B: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aion-3.0 vs. Aion-Mini: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aion-3.0 vs. Gemini 3.6 Flash: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aion-Mini vs. Laguna XS 2.1: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
- Aya Expanse 32B vs. Llama 3.2 90B Vision: Comparação de Benchmarks, Preços API e Velocidade (2026)Comparar
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: Documentação oficial de API da Mistral AI e DeepSeek e benchmarks independentes (2026).