Llama 3.3 70B

Metallama-3.3-70b

Most popular open model. Great all-rounder.

Best for: General, code, reasoning

At a glance

Context window

128K

Input

$1.19/1M

$0.12/1M cached

Output

$1.19/1M

Speed

medium

Quality tier

strong

Per 1M tokens. All-in pricing, no hidden fees.

Capabilities

Tool calling

Connect to external tools and APIs

Reasoning

Extended thinking for complex problems

Prompt caching

Cache repeated prefixes for 90% discount

Streaming

Real-time token-by-token output

Structured outputs

JSON mode and function calling

Quick start

Get API Key
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.3-70b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Details

CreatorMeta
Model IDllama-3.3-70b
Quality tierstrong
Cost tierbalanced
Input modalityText
Output modalityText
Prompt cachingSupported

Try Llama 3.3 70B now

$0.50 free credits on signup. No credit card required.