xAI's efficient reasoning model with thinking capabilities at a lower cost point.
Context Window
131K
tokens
Max Output
16K
tokens
Input Price
$0.3
per 1M tokens
Output Price
$0.5
per 1M tokens
Speed
165
tokens/sec
Released
Feb 2025
2025-02-17
Blended Cost
$0.40
per 1M tokens
Value Score
195.0
quality per $
Capabilities
ChatCode GenerationReasoning
Benchmarks
Quality Index
78
MMLU Pro
82.7
HumanEval (Coding)
85.3
MATH
80.1
Arena ELO
1275
Price vs Quality
Cheaper is left, more capable is up. 4 of 69 priced models are both cheaper and score at least as high. Self-host models are left off the price axis — their cost depends on the hardware you run them on, not on tokens.
Context Window in Context
▸ Grok 3 Mini131K
Grok 3131K
Qwen 2.5 72B131K
Qwen 2.5 Coder 32B131K
GPT-4o128K
GPT-4o Mini128K
Mistral Large 2128K
DeepSeek V3128K
Bar length is logarithmic — each full step is 10× the tokens. Shown against the models with the nearest context windows, not the directory extremes.
لا تملك Swfte Connect مفتاحًا لـ Grok 3 Mini، لذا لا يوجد ما يمكن تشغيله هنا. أضف مفتاح المزوّد الخاص بك ثم استدعِ النموذج بالواجهة نفسها المستخدمة مع بقية نماذج هذا الدليل.
Grok 3 Mini is a reasoning AI model by xAI, released on February 17, 2025. It supports a context window of 131K tokens and can generate up to 16K output tokens.
At $0.3 per million input tokens and $0.5 per million output tokens, its blended cost of $0.40/1M tokens makes it one of the most affordable models available. Its value score of 195.0 reflects the balance of quality and cost.
Using Grok 3 Mini with Swfte
Access Grok 3 Mini through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Grok 3 Mini in our AI Playground before integrating.
Deploy a model with Swfte Connect
One gateway, every provider, per-token cost visibility. Swap models without touching your code.