Tier: open-weight
Context: 1.0M
Cheapest Host: DeepInfra (Lowest Price)
Llama 4 Maverick (17B-128E MoE) API Pricing Calculator & Cheapest Provider
Live unit economics and multi-provider host arbitrage for Llama 4 Maverick (17B-128E MoE) (meta-llama/llama-4-maverick).
Input tokens cost $0.19/1M, output tokens cost
$0.49/1M, and prompt cache reads drop to
$0.095/1M.
Input / Output / Cache Read
$0.19 / $0.49
Per 1M tokens · Cache Read: $0.095/1M
10,000 DAU Monthly Bill
$3,805/mo
Drops to $2,907/mo at 75% prompt cache hit rate
Speed & Context Spec
175 tok/s
Context: 1,048,576 · Max Out: 16,384
1. Multi-Provider Host Arbitrage Table for Llama 4 Maverick (17B-128E MoE)
Compare every verified inference provider hosting Llama 4 Maverick (17B-128E MoE) by input price, output price, cache read discount, and throughput speed:
| Provider / Endpoint | Input / 1M | Output / 1M | Cache Read / 1M | Throughput | 10K DAU Monthly Bill | Action |
|---|---|---|---|---|---|---|
| DeepInfra (Lowest Price) Lowest Price | $0.19 | $0.49 | $0.095 | 148 tok/s | $3,805/mo | Deploy (Get $50 Free API Credits) → |
| Fireworks AI | $0.22 | $0.88 | $0.11 | 175 tok/s | $5,306/mo | Deploy ($50 Free FireAttention Credits) → |
| Together AI | $0.27 | $0.85 | $0.135 | 160 tok/s | $5,850/mo | Deploy ($25 Free Inference Credits) → |
2. Monthly SaaS Spend by DAU Scale & Prompt Cache Hit Rate
Exact monthly spend projections across 1,000 DAU, 10,000 DAU, and 50,000 DAU with 0%, 50%, 75%, and 90% prompt caching:
| Active Users (DAU) | Uncached (0% Hit) | 50% Cache Hit | 75% Cache Hit (RAG) | 90% Cache Hit (Agents) |
|---|---|---|---|---|
| 1,000 DAU (1.55B tok/mo) | $380.52/mo | $320.67/mo | $290.75/mo | $272.79/mo |
| 10,000 DAU (15.5B tok/mo) | $3,805/mo | $3,207/mo | $2,907/mo | $2,728/mo |
| 50,000 DAU (77.4B tok/mo) | $19,026/mo | $16,034/mo | $14,537/mo | $13,640/mo |
3. Frequently Asked Questions (Llama 4 Maverick (17B-128E MoE))
How much does the Llama 4 Maverick (17B-128E MoE) API cost per 1M tokens?
Llama 4 Maverick (17B-128E MoE) (DeepInfra) costs $0.19 per 1M input tokens, $0.49 per 1M output tokens, and $0.095 per 1M cached input tokens. Its context window is 1.0M (1,048,576 tokens) with 16,384 max output tokens.
What is the cheapest inference provider for Llama 4 Maverick (17B-128E MoE)?
Among 3 verified endpoints, DeepInfra (Lowest Price) offers the lowest blended pricing at $0.19/1M input and $0.49/1M output (148 tok/s). For maximum throughput, Fireworks AI delivers 175 tokens/sec.
How much does Llama 4 Maverick (17B-128E MoE) cost per month at 1,000, 10,000, and 50,000 DAU?
On a standard SaaS production workload (12 requests/user/day, 3,500 input + 800 output tokens), Llama 4 Maverick (17B-128E MoE) costs $380.52/month at 1,000 DAU, $3,805/month at 10,000 DAU, and $19,026/month at 50,000 DAU. Enabling 75% prompt caching reduces the 10,000 DAU bill to $2,907/month.
4. Compare Llama 4 Maverick (17B-128E MoE) Against Alternative Models
Llama 4 Maverick (17B-128E MoE) vs DeepSeek V3 (0324)
Side-by-side DAU cost & cache savings →
Llama 4 Maverick (17B-128E MoE) vs GPT-4o
Side-by-side DAU cost & cache savings →
Llama 3.3 70B Instruct vs Llama 4 Maverick (17B-128E MoE)
Side-by-side DAU cost & cache savings →
DeepSeek V3 (0324) Pricing Calculator
$0.24/1M in · $0.79/1M out →
Claude 3.7 Sonnet Pricing Calculator
$3.00/1M in · $15.00/1M out →
GPT-4o Pricing Calculator
$2.50/1M in · $10.00/1M out →
Gemini 2.5 Pro Pricing Calculator
$1.25/1M in · $10.00/1M out →
DeepSeek R1 (671B Reasoning) Pricing Calculator
$0.50/1M in · $2.15/1M out →
OpenAI o3-mini Pricing Calculator
$1.10/1M in · $4.40/1M out →