PROVIDER
Ionstream
Published provider information and recorded endpoint observations.
Models
Uptime · last 24 hours
100.0%
Input $0.27 / 1M tokens · Output $1.1 / 1M tokens
Context 1,048,576 tokens · Max output 943,718 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Max tokens, Temperature, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Top p, Top k, Frequency penalty, Presence penalty, Stop, Seed, Logit bias, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$1.1 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.005 / 1M tokens- Inputprompt
$0.27 / 1M tokens
Uptime · last 24 hours
100.0%
Input $0.27 / 1M tokens · Output $1.1 / 1M tokens
Context 1,048,576 tokens · Max output 943,718 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Max tokens, Temperature, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Top p, Top k, Frequency penalty, Presence penalty, Stop, Seed, Logit bias, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$1.1 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.005 / 1M tokens- Inputprompt
$0.27 / 1M tokens
Uptime · last 24 hours
99.9%
Input $0.37 / 1M tokens · Output $2.93 / 1M tokens
Context 1,048,576 tokens · Max output 943,718 tokens
Status: Active
Parameters: Reasoning, Include reasoning, Max tokens, Temperature, Response format, Tools, Tool choice, Structured outputs, Logprobs, Top logprobs, Top p, Top k, Frequency penalty, Presence penalty, Stop, Seed, Logit bias, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$2.93 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.088 / 1M tokens- Inputprompt
$0.37 / 1M tokens
Uptime · last 24 hours
99.7%
Input $0.0893 / 1M tokens · Output $2.35 / 1M tokens
Context 262,144 tokens · Max output 65,536 tokens
Quantization FP8 · Status: Active
Parameters: Reasoning, Include reasoning, Max tokens, Temperature, Response format, Structured outputs, Tools, Tool choice, Logprobs, Top logprobs, Top p, Top k, Frequency penalty, Presence penalty, Repetition penalty, Stop, Seed, Logit bias, Reasoning effort
Retrieved
Full published price schedule
Published pricing
- Outputcompletion
$2.35 / 1M tokens- Discountdiscount
0Unit not specified in source record- Cache readinput_cache_read
$0.085 / 1M tokens- Inputprompt
$0.0893 / 1M tokens