Llama 4 Maverick

1.05M ctxTextImage Tools

Released Apr 5, 2025 · 121B tokens this week · 5 providers

Overview

Meta's mixture-of-experts flagship, with native image understanding and a very large context window. Competitive on general chat and coding while staying inexpensive on open-weight hosts. A practical frontier substitute when you need weights you can move between providers.

programmingroleplaytranslation

Providers

Reference data — not yet measured from live traffic

PROVIDER		MAX OUT		OUTPUT /M				QUANT
DeepInfraCheapest	1.05M	16K	$0.22	$0.85	480ms	120	98.80%	fp8
Novita AI	524K	16K	$0.23	$0.90	540ms	98	98.60%	fp8
Together AI	1.05M	16K	$0.25	$0.95	195ms	150	99.50%	Full
Fireworks AI	1.05M	16K	$0.25	$0.98	400ms	175	99.60%	Full
Amazon Bedrock	131K	16K	$0.26	$1.02	620ms	105	99.82%	Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

DeepSeek V3.2$0.37

Llama 4 Maverick$0.69

Gemini 3 Flash$1.95

GPT-5.2$10.94

Claude Sonnet 4.5$12.00

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-maverick",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'