ERNIE 4.5 0.3B PT vs DeepSeek V4.1 Flash
At a Glance
| Compare |  ERNIE 4.5 0.3B PTBaidu |  DeepSeek V4.1 FlashDeepSeek |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| CostLower is better · Published-token output estimate | UnrankedNot in the 44-model eligible cohort | #5 of 44$0.022 per LiveBench case |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | Not reported | $0.15DeepSeek ↗ · Sep 10, 2026 |
| Output priceFrom · USD / 1M tokens | Not reported | $0.60Deepinfra ↗ · Sep 21, 2026 |
| Context windowMaximum documented tokens | 131K | 1,049K |
| Model facts checked | Aug 28, 2026View model evidence → | Sep 10, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
Side-by-Side Facts
| Field | ERNIE-4.5-0.3B-PT | DeepSeek-V4.1-Flash |
|---|---|---|
| Developer | Baidu | DeepSeek |
| Family | Ernie 4 5 0 3b Pt | Deepseek V4 1 |
| Model | ERNIE-4.5-0.3B-PT | DeepSeek-V4.1-Flash |
| Version | ERNIE-4.5-0.3B-PT | DeepSeek-V4.1-Flash |
| Lifecycle | active | active |
| Released | Unknown | 2026-09-10 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Context window | 131K | 1,049K |
| Total parameters | 360.7M | 763.2B |
| Active parameters | Unknown | Unknown |
| License | apache-2.0 | mit |
| Open weights | Yes | Yes |
| API available | Unknown | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | DeepSeek (Standard), Deepinfra (Standard), Together Ai (Standard) |
| Capabilities | chat, generation | agents, chat, fim, generation, reasoning, responses, structured_outputs, tools, vision |
| Architecture design | Unknown | Causal Encoder-Decoder (20 encoder + 20 decoder layers) |
| Backbone parameters | Unknown | 552000000000 parameters |
| Active parameters during decode | Unknown | 16000000000 parameters |
| Active parameters during prefill | Unknown | 8000000000 parameters |
| Pre-training corpus | Unknown | 45000000000000 tokens |
| Reasoning effort range | Unknown | 1–100 |
| Routed experts per MoE layer | Unknown | 384 experts |
| Routed experts per token | Unknown | 6 experts |
| Transformer layers | Unknown | 40 layers |
ERNIE 4.5 0.3B PT Capabilities
DeepSeek V4.1 Flash Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
ERNIE-4.5-0.3B-PTBaidu | vs | DeepSeek-V4-FlashDeepSeek | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | ERNIE-4.5-0.3B-PTBaidu | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs | Grok 4.6xAI | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | ERNIE-4.5-0.3B-PTBaidu | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs |  GLM-5.3Z.ai | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs |  Hy4 previewTencent | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs | Seed 2.1 ProByteDance Seed | cross-developer peerstext |
ERNIE-4.5-0.3B-PTBaidu | vs |  Mistral Large 3Mistral AI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
ERNIE 4.5 0.3B PT vs DeepSeek V4.1 Flash FAQs
Is ERNIE 4.5 0.3B PT or DeepSeek V4.1 Flash better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both ERNIE 4.5 0.3B PT and DeepSeek V4.1 Flash, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, ERNIE 4.5 0.3B PT or DeepSeek V4.1 Flash?+
Only DeepSeek V4.1 Flash has a directly sourced input price: $0.15 per million tokens. Only DeepSeek V4.1 Flash has a directly sourced output price: $0.60 per million tokens.
Which has a larger context window, ERNIE 4.5 0.3B PT or DeepSeek V4.1 Flash?+
DeepSeek V4.1 Flash has the larger sourced context window. ERNIE 4.5 0.3B PT supports 131K and DeepSeek V4.1 Flash supports 1,049K.
Which performs better in benchmarks, ERNIE 4.5 0.3B PT or DeepSeek V4.1 Flash?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can ERNIE 4.5 0.3B PT or DeepSeek V4.1 Flash be self-hosted?+
Both models have the same recorded self-hosting status: supported. ERNIE 4.5 0.3B PT is open weight; DeepSeek V4.1 Flash is open weight.
Can ERNIE 4.5 0.3B PT and DeepSeek V4.1 Flash understand images?+
ERNIE 4.5 0.3B PT is not documented with image input; DeepSeek V4.1 Flash is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, ERNIE 4.5 0.3B PT or DeepSeek V4.1 Flash?+
Neither has a larger sourced maximum output. ERNIE 4.5 0.3B PT is — and DeepSeek V4.1 Flash is 393K.
Do ERNIE 4.5 0.3B PT and DeepSeek V4.1 Flash support reasoning and tool use?+
ERNIE 4.5 0.3B PT: none of these features are definitively sourced. DeepSeek V4.1 Flash: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, ERNIE 4.5 0.3B PT or DeepSeek V4.1 Flash?+
ERNIE 4.5 0.3B PT has 0 sourced provider routes; DeepSeek V4.1 Flash has 3, so DeepSeek V4.1 Flash has broader tracked availability.
Which offers better value, ERNIE 4.5 0.3B PT or DeepSeek V4.1 Flash?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.