Skip to content

fix(litellm): route chatgpt codex via /responses to dodge Cloudflare challenge #469

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
samxu01 wants to merge 1 commit into
base: main
Choose a base branch
from
+14 −8
Open

fix(litellm): route chatgpt codex via /responses to dodge Cloudflare challenge #469

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
22 changes: 14 additions & 8 deletions k8s/helm/commonly/templates/configmaps/litellm-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,12 @@ data:
# paired entry alongside nemotron above.

# --- Codex (chatgpt/ provider) ---
# The `responses/` in `chatgpt/responses/gpt-5.4*` is LOAD-BEARING. Plain
# `chatgpt/gpt-5.4*` routes to /backend-api/codex/chat/completions, which Cloudflare
# serves a JS bot-challenge for (HTML, not JSON) -> the call fails and silently falls
# back to OpenRouter Nemotron. The /responses endpoint is NOT challenged. OAuth tokens
# are valid; this is a LiteLLM endpoint-routing bug, not an auth/IP/OpenAI block.
# See BerriAI/litellm#27175 (workaround) + openclaw#68033 (2026-06).
# NOTE: LiteLLM's chatgpt/ provider reads tokens from auth.json (written by the
# codex-auth-seed init + codex-auth-rotator sidecar). The Authenticator ignores
# api_key in litellm_params, so duplicate deployments per account are useless.
Expand All @@ -85,7 +91,7 @@ data:
model_info:
mode: responses
litellm_params:
model: chatgpt/gpt-5.4
model: chatgpt/responses/gpt-5.4
timeout: 120
input_cost_per_token: 0.0000025
output_cost_per_token: 0.000015
Expand All @@ -94,7 +100,7 @@ data:
model_info:
mode: responses
litellm_params:
model: chatgpt/gpt-5.4
model: chatgpt/responses/gpt-5.4
timeout: 120
input_cost_per_token: 0.0000025
output_cost_per_token: 0.000015
Expand All @@ -104,7 +110,7 @@ data:
model_info:
mode: responses
litellm_params:
model: chatgpt/gpt-5.4-mini
model: chatgpt/responses/gpt-5.4-mini
timeout: 120
input_cost_per_token: 0.00000075
output_cost_per_token: 0.0000045
Expand All @@ -113,7 +119,7 @@ data:
model_info:
mode: responses
litellm_params:
model: chatgpt/gpt-5.4-mini
model: chatgpt/responses/gpt-5.4-mini
timeout: 120
input_cost_per_token: 0.00000075
output_cost_per_token: 0.0000045
Expand All @@ -123,7 +129,7 @@ data:
model_info:
mode: responses
litellm_params:
model: chatgpt/gpt-5.4-nano
model: chatgpt/responses/gpt-5.4-nano
timeout: 120
input_cost_per_token: 0.0000002
output_cost_per_token: 0.00000125
Expand All @@ -132,7 +138,7 @@ data:
model_info:
mode: responses
litellm_params:
model: chatgpt/gpt-5.4-nano
model: chatgpt/responses/gpt-5.4-nano
timeout: 120
input_cost_per_token: 0.0000002
output_cost_per_token: 0.00000125
Expand All @@ -143,15 +149,15 @@ data:
model_info:
mode: responses
litellm_params:
model: chatgpt/gpt-5.4-mini
model: chatgpt/responses/gpt-5.4-mini
input_cost_per_token: 0.00000075
output_cost_per_token: 0.0000045

- model_name: o4-mini
model_info:
mode: responses
litellm_params:
model: chatgpt/gpt-5.4-mini
model: chatgpt/responses/gpt-5.4-mini
input_cost_per_token: 0.00000075
output_cost_per_token: 0.0000045

Expand Down
Loading