Deepseek
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Source-reported prices are shown in their native units. No missing fee is estimated.
Input
$0.050
USD / 1M input tokens
Output
$0.150
USD / 1M output tokens
A check means the source explicitly lists support; a dash means the source did not publish a value.
Suggestions use deterministic rules: overlapping modalities, a context window within 2×, and shared source-reported signals. No AI-generated recommendations.
Anthropic: Claude Haiku 5.5
anthropic/claude-haiku-5.5
Input
$0.100
Intelligence
N/A
Similar category, context, price or shared benchmark signals.
Anthropic: Claude Haiku 5.5 (batch)
anthropic/claude-haiku-5.5:batch
Input
$0.050
Intelligence
N/A
Similar category, context, price or shared benchmark signals.
Anthropic: Claude Haiku Latest
~anthropic/claude-haiku-latest
Input
$0.100
Intelligence
N/A
Similar category, context, price or shared benchmark signals.
DeepSeek: DeepSeek V4 Flash 0423
deepseek/deepseek-v4-flash
Input
$0.091
Intelligence
N/A
Similar category, context, price or shared benchmark signals.