Llama 4 Maverick 17b 128e Instruct Fp8

Name: Llama 4 Maverick 17b 128e Instruct Fp8 — independent benchmark scores
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Lambda AiChat131K context· released 2025-04-05Floating alias

lambda_ai/llama-4-maverick-17b-128e-instruct-fp8

Estimate cost Compare

Prices as of 2026-07-14 · rev 179affb· unknown is shown as unknown, never $0.00

Value position50th pctile GPQAno cheaper model matches it on GPQA

Data confidence4/4 exactbenchmarks measured on this exact model · prices 2026-07-14

Cost / request$0.00011K in · 500 out

Input / M$0.05

Output / M$0.10

Context131K131,072 tokens

Max output8K8,192 tokens

Capability fingerprint

independent benchmarks, grouped by domain · higher is better · not our measurement

Reasoning

GPQA Diamondgraduate-level science reasoning

56%50th pctile

exact modeloptimized runEpoch evaluations · Llama 4 Maverick

Mathematics

MATH Lvl 5hard competition math

73%63rd pctile

exact modeloptimized runEpoch evaluations · Llama 4 Maverick

AIME (OTIS mock)olympiad math

20%36th pctile

exact modeloptimized runEpoch evaluations · Llama 4 Maverick

FrontierMathresearch-level math

1%25th pctile

exact modeloptimized runEpoch evaluations · Llama 4 Maverick

peer median · percentile ranks this model among distinct comparable models (deduped — one entry per model, not per provider) scored on that benchmark · exact model / family proxy per row.

Source: Epoch AI — “AI Benchmarking Hub” (epoch.ai), CC-BY (Epoch AI). Some rows carry an upstream leaderboard (shown per row); Aider & Terminal-Bench are additionally Apache-2.0. Each benchmark measures a different thing on a different scale — rows are not comparable across domains, and a score is not a guarantee of quality on your task.

Cost vs quality

where Llama 4 Maverick 17b 128e Instruct Fp8 sits among GPQA-scored models

Each dot is a model with a GPQA Diamond score, priced at a 1K-in / 500-out request; Llama 4 Maverick 17b 128e Instruct Fp8 is highlighted. The shaded corner holds models that are both cheaper and higher-scoring; the dashed staircase is the value frontier. Hover any dot for its model.

Pricing

Input · fresh prompt tokens	$0.05 / M
Output · generated tokens	$0.10 / M
Cache read · cached-input hit	unknown
Cache write · cache creation	unknown
Reasoning · thinking tokens	unknown

Model info

Provider: Lambda Ai
Catalog key: lambda_ai/lambda_ai/llama-4-maverick-17b-128e-instruct-fp8
Identifier: Floating alias (may re-point over time)
Type: Chat
Max input: 131,072 tokens
Max output: 8,192 tokens
Released: 2025-04-05
Knowledge cutoff: 2024-08
Weights: Open weights
Price snapshot: 2026-07-14 · rev 179affb

Pricing from TokenTriage's resolved price artifact (TokenTriage resolved price artifact (internal/pricing/data/prices.json)); capability + model metadata is third-party (LiteLLM model_prices_and_context_window.json, models.dev). Unknown means unstated, not absent.

Capabilities

2 documented as supported

Input & output

✓Visionmodels.dev

?PDF input

?Audio input

?Audio output

API behaviour

?Streaming

?Structured output

?Prompt caching

✕Reasoningmodels.dev

Agents & tools

✓Function calling

✓Parallel tool calls

?Web search

?Computer use

✓ supported ·✕ not supported ·? not documented ·⚠ sources disagree. A models.dev tag means the LiteLLM catalog was silent and an independent source supplied the value (lower confidence); ? is never silently turned into a confident ✕.

Open weights

verified Hugging Face repo · facts from the model's safetensors index

Parameters: 401.6B
Architecture: Llama4ForConditionalGeneration
Native precision: F8_E4M3 (ships pre-quantized)

Native size: 417 GB

License: otherCommercial use — conditional
Repository: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

Source: Hugging Face Hub — facts read from the model repo as of 2026-07-30. Each fact carries the model's own repo license (shown above); TokenTriage neither hosts nor relicenses the weights.

Estimate a request

disjoint token buckets · input = fresh (uncached) tokens

Preset

Input tokens

Output tokens

Cached input

Cache write

Reasoning

Requests / month

Cost / request—

Projected / month—

How output length drives the bill

at a 1K-token prompt · cost scales linearly with output

Output tokens overtake input spend at ~500 tokens for this model — past that, generation is your bill, whatever the headline input price says. Computed by the same cost engine as the estimate above.

Compare Llama 4 Maverick 17b 128e Instruct Fp8 with other models →

Route to Llama 4 Maverick 17b 128e Instruct Fp8

OpenAI-compatible · one base URL

curl https://YOUR-TOKENTRIAGE-HOST/v1/chat/completions \
  -H "Authorization: Bearer $TOKENTRIAGE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "lambda_ai/lambda_ai/llama-4-maverick-17b-128e-instruct-fp8",
    "messages": [{"role": "user", "content": "Hello"}]
  }'from openai import OpenAI

client = OpenAI(
    base_url="https://YOUR-TOKENTRIAGE-HOST/v1",
    api_key="YOUR_TOKENTRIAGE_KEY",
)

resp = client.chat.completions.create(
    model="lambda_ai/lambda_ai/llama-4-maverick-17b-128e-instruct-fp8",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Point your existing OpenAI client at your TokenTriage host and pass the catalog key as the model. TokenTriage attributes the real cost per request and can route to a cheaper model once it's proven just as good on your traffic.

Data & API

machine-readable · rev 179affb

Pull this model's pricing, capabilities, benchmarks and cross-source provenance programmatically — every field carries the snapshot rev, and unknown is null, never 0. Free to reuse with attribution: benchmarks & Capabilities Index © Epoch AI (CC-BY (Epoch AI)); human-preference Elo © LMArena (CC-BY-4.0); capability & price cross-check via models.dev v2 (MIT) · Portkey (MIT) · TrueFoundry (MIT); open-weights facts via Hugging Face (per-repo license).

lambda-ai-lambda-ai-llama-4-maverick-17b-128e-instruct-fp8.json lambda-ai-lambda-ai-llama-4-maverick-17b-128e-instruct-fp8.csv

A price is a guess until it meets your traffic.

This page tells you what Llama 4 Maverick 17b 128e Instruct Fp8 charges per token. TokenTriage tells you what it costs on your real requests — and cuts the bill only after proving a cheaper model is just as good.

See the product Back to directory