Llama 4 Maverick
Meta's mixture-of-experts model with 17B active parameters and 128 experts. Strong multimodal and multilingual performance.
1M
tokens
33K
tokens
$0.2
per 1M tokens
$0.6
per 1M tokens
135
tokens/sec
Apr 2025
2025-04-05
$0.40
per 1M tokens
200.0
quality per $
Capabilities
Benchmarks
Price vs Quality
Context Window in Context
- ▸ Llama 4 Maverick1M
- GPT-4.11M
- Gemini 2.5 Pro1M
- Gemini 2.0 Flash1M
- GPT-5.51M
- GPT-5.5 Pro1M
- Claude Opus 4.71M
- Gemini 3.1 Pro1M
Compare With
Open Source: Licensed under Llama 4 Community
Pas encore sur notre gateway
Llama 4 Maverick est à poids ouverts : vous pouvez donc l'exécuter vous-même. Swfte Connect transforme votre déploiement en un endpoint géré qui parle la même API que tous les autres modèles de cet annuaire.
curl https://api.swfte.com/agents/v2/gateway/chat/completions \
-H "Authorization: Bearer $SWFTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "meta:llama-4-maverick-17b-128e",
"messages": [{"role": "user", "content": "Hello"}]
}'About Llama 4 Maverick
Llama 4 Maverick is a balanced AI model by Meta, released on April 5, 2025. It supports a context window of 1000K tokens and can generate up to 33K output tokens.
At $0.2 per million input tokens and $0.6 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 200.0 reflects the balance of quality and cost.
Llama 4 Maverick is available as an open-source model under the Llama 4 Community license, meaning you can self-host it for predictable costs or use it through API providers like Swfte Connect.
Using Llama 4 Maverick with Swfte
Access Llama 4 Maverick 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 Llama 4 Maverick in our AI Playground before integrating.