Pixtral Large vs Pixtral 12B
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Pixtral Large dari Mistral AI dan Pixtral 12B dari Mistral AI adalah dua model AI unggulan. Pixtral Large menawarkan jendela konteks 128K token dengan harga $2.00/$6.00 per 1 juta token, sedangkan Pixtral 12B menyediakan konteks 128K token seharga $0.15/$0.15 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.
Pixtral Large
AI Multimodal AsliPixtral Large dari Mistral AI adalah model AI yang dirancang untuk pemahaman multimodal asli (teks & visual) serta analisis dokumen kompleks, menghadirkan jendela konteks 128K, kecepatan 70 token/detik, indeks kecerdasan 48/100, serta tarif
$2.00 / 1M
$6.00 / 1M
128K tokens
38.5%
Pixtral 12B
AI Multimodal AsliPixtral 12B dari Mistral AI adalah model AI yang dirancang untuk pemahaman multimodal asli (teks & visual) serta analisis dokumen kompleks, menghadirkan jendela konteks 128K, kecepatan 85 token/detik, indeks kecerdasan 40/100, serta tarif $
$0.15 / 1M
$0.15 / 1M
128K tokens
28%
Perbedaan Utama Sekilas
- 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%).
| Feature | Pixtral Large | Pixtral 12B |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 48 | 40 |
Provider | Mistral AI | Mistral 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 text | 128K tokens~192 A4 pages of text |
Max Output Tokens Per single request | 8K | 8K |
Throughput Speed Tokens generated per second | 70 tok/s | 85 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 |
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.
Pixtral Large · Strengths & Key Advantages
- Jendela konteks 128K dengan kapasitas output maksimum hingga 8K token (SWE-bench Verified 38.5% · GPQA Diamond 55.4%)
- Kecepatan generasi tinggi 70 token/detik dengan latensi token pertama (TTFT) hanya 550 ms
- Bobot terbuka (124B) 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
- Untuk trafik produksi skala besar, disarankan mengaktifkan fitur Prompt Caching dan Batch API guna menghemat biaya
Pixtral 12B · Strengths & Key Advantages
- Jendela konteks 128K dengan kapasitas output maksimum hingga 8K token (SWE-bench Verified 28% · GPQA Diamond 43.8%)
- Kecepatan generasi tinggi 85 token/detik dengan latensi token pertama (TTFT) hanya 450 ms
- Bobot terbuka (12B) 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 | Pixtral Large | Pixtral 12B |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.65 | $0.09 |
Output Tokens / Task Tokens generated per task | 35K | 25K |
Reasoning Tokens / Task Thinking tokens burned per task | 0K | 0K |
Spesifikasi Teknis
Architecture, release timeline, capabilities, and modalities.
| Feature | Pixtral Large | Pixtral 12B |
|---|---|---|
| Official API Model ID (SDK) | pixtral-large-latest | pixtral-12b-latest |
| API Protocol | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI |
| Release Date | 2024-11 | 2024-09 |
| Knowledge Cutoff | October 2024 | August 2024 |
| Architecture | Frontier Vision-Language Transformer | Multimodal Vision-Language Transformer |
| Parameters | 124B | 12B |
| 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 ($2/1M in) across full 128K window | Flat rate ($0.15/1M in) across full 128K window |
| Prompt Cache Policy & TTL | Cached input at $1/1M 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) · 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) · 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 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, vision | text, vision |
| Output Modalities | text | text |
Pixtral Large vs Pixtral 12B: Jawaban Cepat (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.
Kesimpulan
Baik Pixtral Large (Sangat cocok untuk pemahaman multimodal asli (teks & visual) serta analisis dokumen kompleks, sistem RAG perusahaan, dan integrasi API skala produksi.) maupun Pixtral 12B (Sangat cocok untuk pemahaman multimodal asli (teks & visual) serta analisis dokumen kompleks, sistem RAG perusahaan, dan integrasi API skala produksi.) sangat tangguh: Pixtral Large unggul dalam penalaran dan pemrograman, Pixtral 12B memberikan kecepatan generasi token lebih tinggi, dan Pixtral 12B lebih hemat biaya untuk penggunaan API skala besar.
Pertanyaan Umum (FAQ)
Mana yang lebih baik untuk coding dan penalaran, Pixtral Large atau Pixtral 12B?+
Dalam indeks kecerdasan gabungan dan benchmark coding, Pixtral Large memimpin. Lihat skor SWE-bench dan GPQA di atas untuk detailnya.
Berapa perbandingan harga API Pixtral Large vs Pixtral 12B?+
Pixtral Large mengenakan biaya $2.00 / $6.00 per 1M token input/output, sedangkan Pixtral 12B sebesar $0.15 / $0.15. Secara keseluruhan, Pixtral 12B lebih hemat biaya.
Model mana yang memiliki jendela konteks lebih besar dan kecepatan lebih tinggi?+
Pixtral Large mendukung konteks 128K token dibandingkan 128K token pada Pixtral 12B, sementara Pixtral 12B 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
- Pixtral 12B vs Mistral Large 2: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Pixtral 12B vs Qwen 2.5 32B Instruct: Perbandingan Benchmark, Harga API & Kecepatan (2026)Bandingkan
- Pixtral Large vs Aya Expanse 32B: 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
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).