Models

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

lambda_ai · 1049K ctx · 6 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.063 Official list · Lambda AI
Avg price
$0.437 /1M
providers
6
(3 × $0.050 + $0.100) ÷ 4 = $0.063/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.050, 3:1 $0.063, 1:1 $0.075, output only $0.100 per 1M.

The board shows this model's cheapest measured offer ($0.063/1M); the smaller figure under it is the mean of the 8 offers listed below ($0.437/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
lambda_ai Pricebook (LiteLLM) $0.050$0.100 — — — Official list
deepinfra Pricebook (LiteLLM) $0.150$0.600 — — — Official list
requesty Requesty $0.200$0.850 — — — API-measured
together_ai Pricebook (LiteLLM) $0.270$0.850 — — — Official list
novita Pricebook (LiteLLM) $0.270$0.850 — — — Official list
novita HuggingFace Router $0.270$0.850 480ms 40 — API-measured
novita-ai Novita AI $0.270$0.850 — — — API-measured
azure_ai Pricebook (LiteLLM) $1.41$0.350 — — — Official list

Price trend

$0.0625 $0.0625 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-07 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-08 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-09 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-10 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-11 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-12 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-13 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-14 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-15 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-16 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-17 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-18 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-19 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-20 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-21 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-22 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-23 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-24 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-25 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-26 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-27 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-28 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-29 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-30 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-07-31 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-08-01 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-08-02 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-08-03 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-08-04 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M2026-08-05 · O 0.0625 H 0.0625 L 0.0625 C 0.0625 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625 → $0.0625

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/llama-4-maverick-17b-128e-instruct-fp8.json. Free reuse requires attribution to tkx.org.

About

"llama-4-maverick-17b-128e-instruct-fp8" is an AI model, a machine-learning system designed for natural language processing tasks. It is served by multiple inference providers on AI model marketplaces and listed under the organization tag "lambda_ai".

AI-generated summary from public information — is this yours?

FAQ

How much does llama-4-maverick-17b-128e-instruct-fp8 cost?

Cheapest measured offer right now: $0.05/1M input, $0.1/1M output via lambda_ai — across 6 tracked providers, refreshed hourly.

Who serves llama-4-maverick-17b-128e-instruct-fp8?

6 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

Is the price of llama-4-maverick-17b-128e-instruct-fp8 going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings