Skip to content

Pull requests: Helicone/helicone

New pull request New
53 Open 4,887 Closed
53 Open 4,887 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add QuickSilver Pro provider (DeepSeek V3 + R1)
#5659 opened Apr 18, 2026 by raullenchai Loading…
4 tasks
3
feat: add openai/gpt-oss-safeguard-20b pricing for Groq
#5656 opened Apr 9, 2026 by aishanee-sinha Loading…
3 of 18 tasks
3
Feature/add hpc ai provider
#5651 opened Apr 1, 2026 by lioZ129 Loading…
9 of 18 tasks
7
add relaxAI as inference provider
#5649 opened Mar 30, 2026 by bennorris123 Loading…
2
fix(mcp): make API base URLs configurable via env vars
#5644 opened Mar 23, 2026 by ManuelElvir Loading…
1
2
feat: add MiniMax as LLM provider with model registry and cost tracking
#5642 opened Mar 21, 2026 by octo-patch Loading…
3 tasks done
2
feat: translate response_format to Anthropic output_config for structured output
#5640 opened Mar 17, 2026 by 03-CiprianoG Loading…
1
3
fix: alert filter validation for property conditions
#5631 opened Mar 7, 2026 by colegottdank Collaborator Loading…
3 tasks
5
chore(cost): sync Vercel AI Gateway model costs
#5628 opened Mar 4, 2026 by Yshayy Loading…
3
Add cost details for gemini-3.1-flash-lite-preview model
#5627 opened Mar 3, 2026 by charliemday Contributor Loading…
2 of 18 tasks
2
fix(gateway): preserve Responses tool linkage and structured output format
#5624 opened Mar 3, 2026 by ohnoah Contributor • Draft
1
fix: map Responses API text.format to response_format in chat completions conversion
#5621 opened Mar 3, 2026 by ink-the-squid Contributor Loading…
2
prommpt tokens fix
#5619 opened Mar 3, 2026 by chitalian Contributor Loading…
18 tasks
5
feat(cost): add Cerebras inference pricing for all models
#5618 opened Mar 3, 2026 by nspady Loading…
2
feat(cost): add gemini-3.1-flash-image-preview pricing
#5617 opened Mar 2, 2026 by nspady Loading…
2
fix: use inline API key as BYOK fallback in AI Gateway
#5614 opened Mar 1, 2026 by shouryamaanjain Loading…
2 of 3 tasks
1
2
fix: propagate NEXT_PUBLIC_HELICONE_JAWN_SERVICE from docker-compose into env.js
#5613 opened Feb 28, 2026 by shouryamaanjain Loading…
5 tasks
1
2
fix(mcp): handle JSON-serialized object parameters from MCP clients
#5611 opened Feb 27, 2026 by obalais Loading…
1
2
feat(mcp): support custom base URLs via environment variables
#5609 opened Feb 27, 2026 by obalais Loading…
2
feat: add GLM (ZhipuAI) support to playground
#5608 opened Feb 25, 2026 by colegottdank Collaborator Loading…
5
docs(self-host): add Gemini smoke test and Linux troubleshooting
#5607 opened Feb 25, 2026 by Aimaghsoodi • Draft
1
3
fix: extract Anthropic cache_creation_input_tokens without TTL breakdown
#5606 opened Feb 24, 2026 by colegottdank Collaborator Loading…
3 tasks done
5
fix: forward cachedContent parameter in OpenAI-to-Gemini transformation
#5605 opened Feb 24, 2026 by colegottdank Collaborator Loading…
2 tasks done
5
fix: extract thoughtsTokenCount for Gemini thinking models
#5604 opened Feb 24, 2026 by colegottdank Collaborator Loading…
3 tasks done
5
Adjust token costs for Groq GPT models
#5603 opened Feb 23, 2026 by charliemday Contributor Loading…
3 of 18 tasks
2
ProTip! Mix and match filters to narrow down what you’re looking for.