Skip to content

fix(ai-proxy): support Anthropic token field names in openai-base driver #13039

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
iakuf wants to merge 3 commits into
base: master
Choose a base branch
from
Open

fix(ai-proxy): support Anthropic token field names in openai-base driver #13039

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7a0b879
fix(ai-proxy): support Anthropic token field names in openai-base driver
Feb 26, 2026
03608d9
fix(ai-proxy): compute total_tokens fallback for Anthropic format in …
Feb 26, 2026
d88f360
fix(ai-proxy): also compute total_tokens fallback in non-streaming path
Feb 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 12 additions & 6 deletions apisix/plugins/ai-drivers/openai-base.lua
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,10 +131,12 @@ local function read_response(conf, ctx, res, response_filter)
core.log.info("got token usage from ai service: ",
core.json.delay_encode(data.usage))
ctx.llm_raw_usage = data.usage
local pt = data.usage.prompt_tokens or data.usage.input_tokens or 0
local ct = data.usage.completion_tokens or data.usage.output_tokens or 0
ctx.ai_token_usage = {
prompt_tokens = data.usage.prompt_tokens or 0,
completion_tokens = data.usage.completion_tokens or 0,
total_tokens = data.usage.total_tokens or 0,
prompt_tokens = pt,
completion_tokens = ct,
total_tokens = data.usage.total_tokens or (pt + ct),
}
ctx.var.llm_prompt_tokens = ctx.ai_token_usage.prompt_tokens
ctx.var.llm_completion_tokens = ctx.ai_token_usage.completion_tokens
Expand Down Expand Up @@ -188,9 +190,13 @@ local function read_response(conf, ctx, res, response_filter)
ctx.ai_token_usage = {}
if type(res_body.usage) == "table" then
ctx.llm_raw_usage = res_body.usage
ctx.ai_token_usage.prompt_tokens = res_body.usage.prompt_tokens or 0
ctx.ai_token_usage.completion_tokens = res_body.usage.completion_tokens or 0
ctx.ai_token_usage.total_tokens = res_body.usage.total_tokens or 0
ctx.ai_token_usage.prompt_tokens = res_body.usage.prompt_tokens
or res_body.usage.input_tokens or 0
ctx.ai_token_usage.completion_tokens = res_body.usage.completion_tokens
or res_body.usage.output_tokens or 0
ctx.ai_token_usage.total_tokens = res_body.usage.total_tokens
or (ctx.ai_token_usage.prompt_tokens
+ ctx.ai_token_usage.completion_tokens)
end
ctx.var.llm_prompt_tokens = ctx.ai_token_usage.prompt_tokens or 0
ctx.var.llm_completion_tokens = ctx.ai_token_usage.completion_tokens or 0
Expand Down
Loading