PROVIDER
Featherless
Published provider information and recorded endpoint observations.
Provider metadata
Retrieved 17 Oct 2026
Models
Uptime · last 24 hours
95.5%
Input $1 / 1M tokens · Output $2.7 / 1M tokens
Context 262,144 tokens · Max output 32,768 tokens
Quantization Fp4 · Status: Active
Parameters: Reasoning, Include reasoning, Max tokens, Temperature, Top p, Stop, Frequency penalty, Presence penalty, Repetition penalty, Top k, Min p, Seed, Response format, Structured outputs, Tools, Tool choice, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$2.7 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.1 / 1M tokens- Inputprompt
$1 / 1M tokens