Llama 4 Scout 17B-16E pricing calculator
Meta's mixture-of-experts Llama 4 model with 17B active parameters. Pricing shown is DeepInfra's serverless rate.
- Input
- $0.10 / 1M
- Cached input
- —
- Output
- $0.30 / 1M
- Context window
- 320K
- Batch API
- No
- Reasoning
- No
Workload
Quick presets
1,000 tokens ≈ 750 English words.
Pro / Agent mode
Caching, batch, multi-turn loops, reasoning tokens
Cost comparison
Cheapest / month
$5.86
Mistral Small 3.2 24B
Most expensive / month
$8.21
Llama 4 Scout 17B-16E
Tokens / request
1.5K in
400 out (cheapest model)
| Remove | |||||
|---|---|---|---|---|---|
| Mistral Small 3.2 24BCheapestMistral via DeepInfra · $0.075 / $0.20 | $0.00019 | $0.1925 | $5.86 | $70.26 | |
| DeepSeek V4 Flash (open weights)DeepSeek via DeepInfra · $0.09 / $0.18 | $0.00021 | $0.207 | $6.30 | $75.55 | |
| Qwen3 32BAlibaba via DeepInfra · $0.08 / $0.28 | $0.00023 | $0.232 | $7.06 | $84.68 | |
| Llama 4 Scout 17B-16EMeta via DeepInfra · $0.10 / $0.30 | $0.00027 | $0.27 | $8.21 | $98.55 |
Monthly = daily × 30.42. Prices are list prices for the standard context tier. Long-context surcharges, regional pricing and taxes are not included.Official pricing ↗
What Llama 4 Scout 17B-16E costs for common workloads
Monthly estimates using the presets above, at list price.
| Workload | Per request / session | Monthly | Yearly |
|---|---|---|---|
| Small Chatbot1K chats/day, short prompts | $0.00015 | $4.56 | $54.75 |
| RAG App5K queries/day, 4K-token retrieved context | $0.00052 | $79.09 | $949.00 |
| Coding Agent200 sessions/day × 25 turns | $0.1275 | $775.71 | $9,308 |
| Enterprise Scale250K requests/day, batched | $0.00035 | $2,662 | $31,938 |
Official pricing ↗ (Meta via DeepInfra) · API model ID meta-llama/Llama-4-Scout-17B-16E-Instruct
Llama 4 Scout 17B-16E pricing FAQ
How much does Llama 4 Scout 17B-16E cost per 1M tokens?
Llama 4 Scout 17B-16E via DeepInfra costs $0.10 per 1M input tokens and $0.30 per 1M output tokens. Prices were last verified on Nov 21, 2026.
How much does one Llama 4 Scout 17B-16E request cost?
A typical request with 1,000 input tokens and 500 output tokens costs about $0.00025. At 1,000 such requests per day that is $7.61 per month.
Does Llama 4 Scout 17B-16E support prompt caching?
Llama 4 Scout 17B-16E via DeepInfra has no discounted cached-input price listed, so every input token is billed at the full rate.
Is there a Batch API discount for Llama 4 Scout 17B-16E?
No 50% batch discount is listed for Llama 4 Scout 17B-16E via DeepInfra.
What is the context window of Llama 4 Scout 17B-16E?
Llama 4 Scout 17B-16E supports up to 320K tokens of context.
Is Llama 4 Scout 17B-16E cheaper than Qwen3 32B?
For a 1,000-in / 500-out request, Llama 4 Scout 17B-16E costs $0.00025 and Qwen3 32B costs $0.00022, so Qwen3 32B is 12% cheaper. Quality, speed and caching behaviour differ, so compare on your own workload above.
More AI cost tools
LLM API & Agent Cost Calculator
Compare per-request, monthly and yearly cost across 30+ models, with caching, batch and multi-turn agent modelling.
Open calculator →GBGPU & VRAM Calculator
See exactly how much VRAM a model needs (weights + KV cache + overhead) and which GPUs or Macs it fits on.
Open calculator →$/minVoice Agent Cost Calculator
Cost per minute and per call for STT + LLM + TTS + telephony voice agent stacks.
Open calculator →break-evenAPI vs Self-Hosting Break-Even
Find the monthly token volume where renting a dedicated GPU beats paying per token.
Open calculator →