Groq: Yi 34B Chat 3 32K

Model Overview

Property	Value
Model ID	`groq/yi-34b-chat-3-32k`
Name	Yi 34B Chat 3 32K
Parameters	34B

Description

Groq: Yi 34B Chat 3 32K is a language model provided by the provider. This model offers advanced capabilities for natural language processing tasks.

Specifications

Spec	Value
Context Window	32K tokens
Max Completion	8K tokens
Inference Speed	210 tokens/second

Pricing

Type	Price
Input	$0.19 per 1M tokens
Output	$0.29 per 1M tokens

Capabilities

Fast inference engine (Groq LPU)
Cost-effective token processing
Reliable production performance
Streaming support

Limitations

32K token context window
Maximum completion tokens: 8K
No image generation (inference only)

Performance

Groq specializes in rapid inference with industry-leading token throughput. Typical use cases include:

Real-time chat applications
Batch processing with guaranteed latency
High-volume inference workloads
Cost-sensitive deployments

Best Practices

Token Optimization: Craft prompts to minimize token usage while maintaining quality
Streaming: Use streaming responses for real-time applications
Batch Processing: Leverage high TPM limits for batch inference
Context Management: Utilize full context window for complex tasks

Rate Limits

30000 TPM (Tokens Per Minute)
Optimized for high-throughput inference

Features

High-speed token generation (210 tokens/sec)
32K token context window
Suitable for: Chinese model, long context, multilingual support

Integration

Use the standard OpenAI-compatible API endpoint:

curl -X POST https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer $GROQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "groq/yi-34b-chat-3-32k",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Resources

Last updated: December 2025 Source: Groq Official Documentation