LLM Reference
Baidu Qianfan

Baidu Qianfan

Researched 67d agoPlatformTier 2

Baidu

RAGAgentsLong contextVisionClassificationJSON / Tool useAIChina

Baidu Qianfan offers 10 tracked models (10 with output token pricing). This catalog covers rag, agents, and long context; open any model detail page for benchmarks, batch tiers, and migration prompts.

Covers 6 workload areas across 10 tracked models; last verified 2026-06-29.

Use it for

  • Teams comparing token and batch pricing across this provider's models
  • Operators routing rag, agents, and long context workloads through this API

Do not use it for

  • Final benchmark picks without opening the relevant model detail page

Tracked models

10

Models available through this provider

Priced output routes

10

Models with output token pricing tracked

Cheapest output

$0.059

ERNIE Lite Pro on this route

Batch-ready models

0

No batch pricing tracked

Latest model release

2026-05-09

118d since newest release

Freshness

2026-06-29

Researched 67d ago

stale

Information

TypePlatform
TierTier 2
Models10
CompanyBaidu
Founded2000
Beijing, China

Baidu Qianfan is Baidu Intelligent Cloud's foundation model and Agent development platform, providing hosted API access to ERNIE and Qianfan models for text generation, reasoning, multimodal understanding, embeddings, and agent workflows.

Where this host wins

  • RAG: 4 tracked models with ruler / needle retrieval benchmarks.
  • Agentic: 6 tracked models with BFCL, tau-bench, and SWE-bench tool-use coverage.
  • Long-context: 6 tracked models with context-token or InfiniteBench-class signal.
  • Vision: 6 tracked models with multimodal benchmark coverage.

Getting started

Verify: quotas and regions in the linked vendor documentation.

Platform Overview

Baidu Qianfan provides native hosted access to Baidu's ERNIE model lineup, including ERNIE 5.1, through model service APIs and the Qianfan console. The platform documents OpenAI-compatible access patterns, model lists, rate limits, and token-based pricing for online inference.

Available Models(10)

View all →

All models available as Serverless

ModelInput (per 1M)Output (per 1M)
ERNIE 5.1$0.59$2.65
ERNIE 5.0$0.89$3.54
ERNIE X1.1$0.15$0.59
ERNIE 4.5 Turbo$0.12$0.47
ERNIE 4.5 Turbo VL$0.44$1.33
ERNIE X1 Turbo$0.15$0.59
ERNIE 4.5$0.59$2.36
ERNIE X1$0.30$1.18
ERNIE Lite Pro$0.03$0.059
ERNIE Speed Pro$0.044$0.089

Where else to run this