Llama-4-Maverick-17B-128E-Instruct-FP8
Vercel AI GatewayOpen weights
Llama-4-Maverick-17B-128E-Instruct-FP8 by Vercel AI Gateway costs $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 128K-token context window.
Pricing
Input (per 1M tokens)
$0.00
Output (per 1M tokens)
$0.00
Cached input (per 1M)
—
Specifications
- Provider
- Vercel AI Gateway
- Context window
- 128K tokens
- Parameters
- —
- Released
- Apr 2025
- Open weights
- Yes
- Frontier model
- No
Benchmarks
- FrontierMath
- 0.690
- GPQA Diamond
- 67.0
Speed & latency
Time to first token
1.53s
Output speed
36 tok/s
Fastest host: novita (via hf-router).
Compare Llama-4-Maverick-17B-128E-Instruct-FP8 with…
Llama-4-Maverick-17B-128E-Instruct-FP8 vs Grok Code Fast 1$0.00/1MLlama-4-Maverick-17B-128E-Instruct-FP8 vs Gemma 4 31B IT$0.00/1MLlama-4-Maverick-17B-128E-Instruct-FP8 vs DeepSeek R1 Distill Qwen 1.5B$0.00/1MLlama-4-Maverick-17B-128E-Instruct-FP8 vs Qwen3-Max-Preview$0.00/1MLlama-4-Maverick-17B-128E-Instruct-FP8 vs Codestral 25.01$0.00/1MLlama-4-Maverick-17B-128E-Instruct-FP8 vs Llama 3.1 405B Instruct$0.00/1M
FAQ
How much does Llama-4-Maverick-17B-128E-Instruct-FP8 cost?
Llama-4-Maverick-17B-128E-Instruct-FP8 is priced at $0.00 per 1M input tokens and $0.00 per 1M output tokens. Output tokens cost more than input.
What is Llama-4-Maverick-17B-128E-Instruct-FP8's context window?
Llama-4-Maverick-17B-128E-Instruct-FP8 supports a context window of 128K tokens — the maximum prompt plus response length it can handle in a single request.
Is Llama-4-Maverick-17B-128E-Instruct-FP8 open weight?
Yes — Llama-4-Maverick-17B-128E-Instruct-FP8 has openly available weights.
Data as of 2026-10-15. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.