ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
xAI
Proprietary API xAI · grok-4.3 · Text+Image+PDF

Grok 4.3 (1M Context) Official Specifications, Pricing & Benchmarks

1M-context reasoning workhorse from xAI with ultra-competitive $2.50/1M output cost.

📋 Grok 4.3 (1M Context) Official API & System Card Specifications

Verified against official xAI developer documentation & pricing

API Model ID: grok-4.3

1. Identity & Capabilities

API Spec
API Model ID
grok-4.3
Release Date
2026-04-17
Weight License
Proprietary (Undisclosed)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
1,000,000 tokens (1000K)
Max Output Tokens
64,000 tokens
Input Modalities
Text + Image + PDF
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 1.25
Cached Input / 1M
$ 0.2 -84%
Output / 1M Tokens
$ 2.5
Tiered Pricing Notes
≤200K ($1.25/$2.50, $0.20 cached); >200K ($2.50/$5.00)

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1485 AA Index 49
🧠 Reasoning
GPQA Diamond 86.5 %

PhD-level Google-proof science reasoning questions

📚 Knowledge
MMLU-Pro 85.4 %

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.

💻 Coding
LiveCodeBench v6 83.2 %

LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code.

🤖 Agentic
TAU2-Bench 80.5 %

Dual-control conversational tool-use benchmark

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Long-Context Analysis Mode
temperature=0.6 top_p=0.95 max_tokens=30,000

📊 Grok 4.3 (1M Context) Full Benchmark Scorecard

1 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

Closest Self-Hostable Open-Weight Alternatives to Grok 4.3 (1M Context)

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Grok 4.3 (1M Context) open-source or proprietary?

Grok 4.3 (1M Context) (grok-4.3) is a proprietary commercial model by xAI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Grok 4.3 (1M Context)?

Grok 4.3 (1M Context) supports 1000K input context and 64,000 max output tokens, priced at $1.25/1M input ($0.2/1M cached) and $2.5/1M output.