80 lines
2.9 KiB
C++
80 lines
2.9 KiB
C++
#include "meta/usage.h"
|
|||
|
|
|
||
|
|
#include <cstdlib>
|
||
|
|
|
||
|
|
#include "meta/catalog.h"
|
||
|
|
|
||
|
|
namespace molo::meta {
|
||
|
|
|
||
|
|
MetaUsage MetaUsage::from_responses(const Json& u) {
|
||
|
|
MetaUsage m;
|
||
|
|
m.input_tokens = JsonX::num(u, "input_tokens");
|
||
|
|
m.output_tokens = JsonX::num(u, "output_tokens");
|
||
|
|
m.total_tokens = JsonX::num(u, "total_tokens", m.input_tokens + m.output_tokens);
|
||
|
|
m.cached_tokens = JsonX::path_num(u, "input_tokens_details.cached_tokens");
|
||
|
|
m.reasoning_tokens = JsonX::path_num(u, "output_tokens_details.reasoning_tokens");
|
||
|
|
m.images_processed = JsonX::num(u, "images_processed");
|
||
|
|
m.video_frames_processed = JsonX::num(u, "video_frames_processed");
|
||
|
|
return m;
|
||
|
|
}
|
||
|
|
|
||
|
|
MetaUsage MetaUsage::from_chat(const Json& u) {
|
||
|
|
MetaUsage m;
|
||
|
|
m.input_tokens = JsonX::num(u, "prompt_tokens");
|
||
|
|
m.output_tokens = JsonX::num(u, "completion_tokens");
|
||
|
|
m.total_tokens = JsonX::num(u, "total_tokens", m.input_tokens + m.output_tokens);
|
||
|
|
m.cached_tokens = JsonX::path_num(u, "prompt_tokens_details.cached_tokens");
|
||
|
|
m.reasoning_tokens = JsonX::path_num(u, "completion_tokens_details.reasoning_tokens");
|
||
|
|
return m;
|
||
|
|
}
|
||
|
|
|
||
|
|
MetaUsage MetaUsage::from_messages(const Json& u) {
|
||
|
|
MetaUsage m;
|
||
|
|
m.input_tokens = JsonX::num(u, "input_tokens");
|
||
|
|
m.output_tokens = JsonX::num(u, "output_tokens");
|
||
|
|
m.total_tokens = m.input_tokens + m.output_tokens;
|
||
|
|
m.cached_tokens = JsonX::num(u, "cache_read_input_tokens");
|
||
|
|
m.reasoning_tokens = JsonX::path_num(u, "output_tokens_details.thinking_tokens");
|
||
|
|
return m;
|
||
|
|
}
|
||
|
|
|
||
|
|
llm::Usage MetaUsage::to_neutral() const {
|
||
|
|
llm::Usage u;
|
||
|
|
u.input_tokens = static_cast<int>(input_tokens);
|
||
|
|
u.output_tokens = static_cast<int>(output_tokens);
|
||
|
|
u.total_tokens = static_cast<int>(total_tokens);
|
||
|
|
u.cached_tokens = static_cast<int>(cached_tokens);
|
||
|
|
u.reasoning_tokens = static_cast<int>(reasoning_tokens);
|
||
|
|
return u;
|
||
|
|
}
|
||
|
|
|
||
|
|
double MetaUsage::cost_usd(const std::string& model) const {
|
||
|
|
const ModelInfo* info = ModelCatalog::find(model);
|
||
|
|
if (!info || info->kind != ModelKind::kText || info->input_per_m <= 0) return -1.0;
|
||
|
|
long fresh = input_tokens > cached_tokens ? input_tokens - cached_tokens : 0;
|
||
|
|
return (static_cast<double>(cached_tokens) * info->cached_per_m +
|
||
|
|
static_cast<double>(fresh) * info->input_per_m +
|
||
|
|
static_cast<double>(output_tokens) * info->output_per_m) / 1e6;
|
||
|
|
}
|
||
|
|
|
||
|
|
namespace {
|
||
|
|
long header_long(const clients::HeaderMap& h, const char* name) {
|
||
|
|
auto v = h.get(name);
|
||
|
|
if (!v || v->empty() || v->size() > 18) return -1;
|
||
|
|
for (char c : *v)
|
||
|
|
if (c < '0' || c > '9') return -1;
|
||
|
|
return std::strtol(v->c_str(), nullptr, 10);
|
||
|
|
}
|
||
|
|
} // namespace
|
||
|
|
|
||
|
|
RateLimits RateLimits::from_headers(const clients::HeaderMap& h) {
|
||
|
|
RateLimits r;
|
||
|
|
r.limit_tokens = header_long(h, "x-ratelimit-limit-tokens");
|
||
|
|
r.remaining_tokens = header_long(h, "x-ratelimit-remaining-tokens");
|
||
|
|
r.limit_requests = header_long(h, "x-ratelimit-limit-requests");
|
||
|
|
r.remaining_requests = header_long(h, "x-ratelimit-remaining-requests");
|
||
|
|
return r;
|
||
|
|
}
|
||
|
|
|
||
|
|
} // namespace molo::meta
|