PROVIDER
Sakana AI
Published provider information and recorded endpoint observations.
Uptime · last 24 hours
100.0%
Input $2 / 1M tokens · Output $6 / 1M tokens
Context 1,000,000 tokens · Max output 128,000 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Tools, Tool choice, Structured outputs, Web search options, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$6 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.25 / 1M tokens- Inputprompt
$2 / 1M tokens- Web searchweb_search
0.01Unit not specified in source record
Uptime · last 24 hours
100.0%
Input $5 / 1M tokens · Output $30 / 1M tokens
Context 1,000,000 tokens · Max output 128,000 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Tools, Tool choice, Structured outputs, Web search options, Reasoning effort
Retrieved
Full published price schedule
Published pricing
Base prices
- Outputcompletion
$30 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.5 / 1M tokens- Inputprompt
$5 / 1M tokens- Web searchweb_search
0.01Unit not specified in source record
Override 1
- Outputcompletion
$45 / 1M tokens- Cache readinput_cache_read
$1 / 1M tokens- Min prompt tokensmin_prompt_tokens
272,000 prompt tokens · 272000Condition- Inputprompt
$10 / 1M tokens
Uptime · last 24 hours
100.0%
Input $5 / 1M tokens · Output $30 / 1M tokens
Context 1,000,000 tokens · Max output 128,000 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Tools, Tool choice, Structured outputs, Web search options, Reasoning effort
Retrieved
Full published price schedule
Published pricing
Base prices
- Outputcompletion
$30 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.5 / 1M tokens- Inputprompt
$5 / 1M tokens- Web searchweb_search
0.01Unit not specified in source record
Override 1
- Outputcompletion
$45 / 1M tokens- Cache readinput_cache_read
$1 / 1M tokens- Min prompt tokensmin_prompt_tokens
272,000 prompt tokens · 272000Condition- Inputprompt
$10 / 1M tokens
Uptime · last 24 hours
100.0%
Input $0.95 / 1M tokens · Output $4 / 1M tokens
Context 262,144 tokens · Max output 65,536 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Tools, Tool choice, Structured outputs, Web search options, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$4 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.15 / 1M tokens- Inputprompt
$0.95 / 1M tokens- Web searchweb_search
0.007Unit not specified in source record