Context
123K
Max output
12K
Serving providers
1
Cheapest input
$0.28 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy45.6default
GPQA Diamond81%default
Humanity's Last Exam4%default
IFBench39%default
LiveCodeBench47%default
Long-Context Reasoning2%default
MMLU-Pro78%default
Omniscience-35.9default
SciCode31%default
TerminalBench Hard6%default
τ²-bench0%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
NovitaCheapest$0.28$1.101
ComponentUnitStandardBatchCached
Text input/1M tok$0.2800
Text output/1M tok$1.10

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00$1.50Jan 13Jun 22$1.10$0.280

Cost calculator

estimate your monthly spend on this model
$144
estimated / month

Model IDs

copy the exact identifier for your platform
novita/baidu/ernie-4.5-300b-a47b-paddle

Frequently asked questions

Ernie 4.5 300B A47b Paddle pricing, context and availability

How much does Ernie 4.5 300B A47b Paddle cost?

Ernie 4.5 300B A47b Paddle costs $0.28 per 1M input tokens and $1.10 per 1M output tokens at its cheapest provider via Novita.

What is the context window of Ernie 4.5 300B A47b Paddle?

Ernie 4.5 300B A47b Paddle accepts up to 123K tokens of context and can return up to 12K output tokens.

What can Ernie 4.5 300B A47b Paddle do?

Ernie 4.5 300B A47b Paddle supports tool use and structured output.

Other Baidu models

compare pricing across the Baidu lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI