Head-to-Head Model Comparison

Pixtral Large vs Pixtral 12B

Benchmarks, API Token Pricing, Context Window & Speed Comparison

Revisado pela equipe de pesquisa do GetInfoUsÚltima revisão: October 2026Política editorial
Partilhar
Related topics (12)
AI CompareAI BenchmarkToken PricingModel CostModel SpecsSWE-bench CodingModel VersusWhich AI ModelLLM Speed & LatencyReasoning ModelsExtended ThinkingPrompt Caching ROI
Pixtral Large vs Pixtral 12B: Benchmarks, Pricing & Speed Comparison

Pixtral Large da Mistral AI e Pixtral 12B da Mistral AI são dois modelos de IA de destaque. O Pixtral Large oferece uma janela de contexto de 128K tokens a $2.00/$6.00 por milhão de tokens, enquanto o Pixtral 12B oferece 128K tokens de contexto a $0.15/$0.15 por milhão de tokens. Veja abaixo a comparação completa de benchmarks, latência e custos.

Comparação Direta (VS)

Troque e Compare Qualquer Modelo

Select any AI models from our verified benchmark database to generate live side-by-side matrices.

Profile
Profile
Multi-Model Arena Stack:
5-Model Matrix Workbench
Popular Matchups:
Mistral AI

Pixtral Large

IA Multimodal Nativa

O Pixtral Large da Mistral AI é um modelo de IA projetado para compreensão multimodal nativa de texto e imagem e leitura visual de documentos, oferecendo janela de contexto de 128K, velocidade de 70 tokens/s, índice de inteligência de 48/10

Intelligence Index48 / 100
Input Token:

$2.00 / 1M

Output Token:

$6.00 / 1M

Context Window:

128K tokens

SWE-bench Verified:

38.5%

Mistral AI

Pixtral 12B

IA Multimodal Nativa

O Pixtral 12B da Mistral AI é um modelo de IA projetado para compreensão multimodal nativa de texto e imagem e leitura visual de documentos, oferecendo janela de contexto de 128K, velocidade de 85 tokens/s, índice de inteligência de 40/100

Intelligence Index40 / 100
Input Token:

$0.15 / 1M

Output Token:

$0.15 / 1M

Context Window:

128K tokens

SWE-bench Verified:

28%

Principais Diferenças em Resumo

  • Pixtral 12B is 22.8x cheaper for API usage (input + output tokens combined).
  • Pixtral 12B is faster at 85 tok/s vs 70 tok/s.
  • Pixtral Large leads on SWE-bench coding (38.5% vs 28.0%).
Need definitions for token pricing, context, or benchmarks?Explore AI Glossary →
FeaturePixtral LargePixtral 12B
Intelligence Index
Composite reasoning & knowledge score (0-100)
4840
Provider
Mistral AIMistral AI
Input Price
Cost per million input tokens
$2.00 / 1M$0.15 / 1M
Output Price
Cost per million output tokens
$6.00 / 1M$0.15 / 1M
Blended Price
Weighted 7:2:1 cache:input:output per 1M
$1.70 / 1M$0.08 / 1M
Context Window
Maximum input + output tokens
128K tokens~192 A4 pages of text128K tokens~192 A4 pages of text
Max Output Tokens
Per single request
8K8K
Throughput Speed
Tokens generated per second
70 tok/s85 tok/s
SWE-bench Verified
Real-world software engineering
38.5%28%
GPQA Diamond
Graduate-level reasoning
55.4%43.8%
Cached Input Price
Prompt caching discount per 1M tokens
$1.00 / 1M$0.05 / 1M

Quem vence em cada categoria?

At-a-glance decision framework
Coding
Pixtral Large
+10.5% SWE-bench lead
Cost
Pixtral 12B
22.8x cheaper monthly runtime
Speed
Pixtral 12B
+21% faster generation
Context
Tied
128K tokens window

Pontuações de Benchmarks Verificadas

Official evaluation metrics verified by independent third-party research labs.

Pixtral LargePixtral 12B
SWE-bench Verified (Autonomous Coding)

Industry benchmark evaluating real-world GitHub issue resolution and multi-file debugging.

38.5%vs28%
GPQA Diamond (Doctorate-Level Science & Math)

Challenging questions created by domain experts to test complex PhD-level reasoning.

55.4%vs43.8%
MMLU-Pro (Multi-task Language Understanding)

Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.

78%vs67.5%
LMSYS Chatbot Arena Elo

Crowdsourced human preference evaluation based on blind, head-to-head model battles.

1295ptsvs1225pts
Terminal-Bench (Agentic Coding & Terminal Use)

Autonomous multi-step tasks executed inside a real command-line terminal environment.

34%vs24%
AIME (Advanced Math Competition)

American Invitational Mathematics Examination — multi-step Olympiad-level reasoning.

65%vs48%
Long-Context Reasoning

Accuracy when reasoning over very large inputs that fill the model context window.

75%vs65%
Generation Speed (Throughput)

Tokens emitted per second during active generation streaming.

70 tok/s vs85 tok/s

Latência e Tempo de Resposta

Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.

Time to First Token (TTFT)Lower is better
Pixtral Large0.55s
Pixtral 12B0.45s
Est. End-to-End Response (500 tokens)TTFT + generation time
Pixtral Large7.69s
Pixtral 12B6.33s

Simulador Interativo de Custo de Tokens

Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.

100K / day
10K500K1M
30K / day
5K150K300K
50% cached
0% (Cold)50%90% (Warm)
Pixtral Large Monthly API Bill
$9.90 / month
$2/1M in · $6/1M out
Pixtral 12B Monthly API Bill
$0.43 / month
$0.15/1M in · $0.15/1M out
Pixtral 12B saves approximately $9.46 / month (96%) under this workload.22.8x Savings

Pixtral Large · Strengths & Key Advantages

  • Janela de contexto de 128K com limite máximo de saída de 8K tokens (SWE-bench Verified 38.5% · GPQA Diamond 55.4%)
  • Taxa de transferência rápida de 70 tokens/segundo com latência inicial (TTFT) de 550 ms
  • Pesos abertos (124B) 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
  • Para alto volume de requisições, recomenda-se ativar o cache de prompts e a Batch API para reduzir custos

Pixtral 12B · Strengths & Key Advantages

  • Janela de contexto de 128K com limite máximo de saída de 8K tokens (SWE-bench Verified 28% · GPQA Diamond 43.8%)
  • Taxa de transferência rápida de 85 tokens/segundo com latência inicial (TTFT) de 450 ms
  • Pesos abertos (12B) 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.

MetricPixtral LargePixtral 12B
Cost per Task
Estimated USD to finish one task
$0.65$0.09
Output Tokens / Task
Tokens generated per task
35K25K
Reasoning Tokens / Task
Thinking tokens burned per task
0K0K

Especificações Técnicas

Architecture, release timeline, capabilities, and modalities.

FeaturePixtral LargePixtral 12B
Official API Model ID (SDK)pixtral-large-latestpixtral-12b-latest
API ProtocolOpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGIOpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Release Date2024-112024-09
Knowledge CutoffOctober 2024August 2024
ArchitectureFrontier Vision-Language TransformerMultimodal Vision-Language Transformer
Parameters124B12B
Enterprise Rate Limits (RPM / TPM)Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed CloudUnlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
Long-Context Tier (>128K/200K)Flat rate ($2/1M in) across full 128K windowFlat rate ($0.15/1M in) across full 128K window
Prompt Cache Policy & TTLCached input at $1/1M tokensCached input at $0.05/1M tokens
Computer Use / GUI AgentAPI / 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 CallingNative MCP Client/Server ready · Parallel function calling · 100% Strict JSON SchemaNative MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & SandboxSupported via external Tavily/Exa Search & E2B/Docker Sandbox toolsSupported via external Tavily/Exa Search & E2B/Docker Sandbox tools
Official Fine-Tuning SupportFull 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 BillingText 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 VRAMBF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 77 GB VRAM (4-bit Quantized) · 267 GB VRAM (Native BF16)BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 7 GB VRAM (4-bit Quantized) · 26 GB VRAM (Native BF16)
Safety & Frontier ClassificationOpen-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 Control100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Input Modalitiestext, visiontext, vision
Output Modalitiestexttext

Pixtral Large vs Pixtral 12B: Respostas Rápidas (FAQ)

Which is more intelligent, Pixtral Large or Pixtral 12B?

Pixtral Large is more intelligent. It scores 48 compared with 40 on the composite Intelligence Index.

Which model is faster?

Pixtral 12B is faster, generating 85 tokens per second compared with 70 tokens per second.

Which model is cheaper to run?

Pixtral 12B is cheaper at $0.08 per 1M tokens blended, compared with $1.70 (7:2:1 cache:input:output ratio).

Which model has lower latency?

Pixtral 12B has lower latency, with a time to first token of 0.45s compared with 0.55s.

Veredito

Tanto Pixtral Large (Indicado para compreensão multimodal nativa de texto e imagem e leitura visual de documentos, arquiteturas RAG corporativas e integração escalável via API.) quanto Pixtral 12B (Indicado para compreensão multimodal nativa de texto e imagem e leitura visual de documentos, arquiteturas RAG corporativas e integração escalável via API.) entregam excelente desempenho: Pixtral Large lidera em inteligência geral e programação, Pixtral 12B oferece geração mais rápida e Pixtral 12B apresenta o melhor custo-benefício em produção.

Perguntas Frequentes (FAQ)

Qual é melhor para programação e raciocínio, Pixtral Large ou Pixtral 12B?+

Nas avaliações de inteligência e código, Pixtral Large leva vantagem. Confira os gráficos SWE-bench e GPQA acima para detalhes.

Qual modelo tem a API mais barata, Pixtral Large ou Pixtral 12B?+

O Pixtral Large custa $2.00 / $6.00 por 1M de tokens (entrada/saída) e o Pixtral 12B custa $0.15 / $0.15. No custo combinado, Pixtral 12B é mais econômico.

Qual modelo possui maior janela de contexto e velocidade?+

O Pixtral Large suporta 128K tokens de contexto contra 128K tokens do Pixtral 12B, enquanto Pixtral 12B entrega maior velocidade de geração.

AI Terminology & Guide
Explore Glossary →

Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.

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 Mistral AI e benchmarks independentes (2026).