How to fix this
Option 1 — Add pricing in the workflow frontmatter:
models:
providers:
anthropic:
models:
'claude-opus-5':
cost:
input: "0e0" # $0.00 per million input tokens
output: "0e0" # $0.00 per million output tokens
Use the provider key matching your engine: github-copilot (Copilot), anthropic (Claude), openai (Codex), or google (Gemini). Only input and output are required; the rest default to zero (or output for reasoning).
Option 2 — Map the model to a known model using the models field:
If claude-opus-5 is an alias for a model already in the built-in pricing table, use the models frontmatter field to provide the mapping:
models:
'claude-opus-5':
- claude-sonnet-4-5
Option 3 — Switch to a model already in the built-in pricing table:
Replace claude-opus-5 in the workflow frontmatter with a model name that the AWF pricing system recognizes (e.g. claude-sonnet-4-5, gpt-4.1, gemini-2.0-flash).
2026-07-28T08:33:03.773Z [ERROR] API error (attempt 1/11): 400 400 Model "claude-opus-5" has no AI credits pricing and no default pricing is configured. Set apiProxy.defaultAiCreditsPricing in the AWF config (e.g. {"input": 3.0, "output": 15.0}) to provide a fallback rate, or add the model to the pricing table.
2026-07-28T08:33:03.773Z [WARN] [server-fallback] 400 attributed (unattributed) — stripping and retrying
2026-07-28T08:33:03.774Z [DEBUG] [API:timing] dispatching to firstParty model=claude-opus-5[1m]
2026-07-28T08:33:03.775Z [DEBUG] [API REQUEST] /v1/messages source=sdk
2026-07-28T08:33:03.795Z [DEBUG] [mcp-registry] Loaded 294 official MCP URLs (legacy)
2026-07-28T08:33:03.959Z [ERROR] API error (attempt 1/11): 400 400 Model "claude-opus-5" has no AI credits pricing and no default pricing is configured. Set apiProxy.defaultAiCreditsPricing in the AWF config (e.g. {"input": 3.0, "output": 15.0}) to provide a fallback rate, or add the model to the pricing table.
{"type":"assistant","message":{"id":"e629caf3-656a-4e12-a7ce-39a27c345e19","container":null,"model":"<synthetic>","role":"assistant","stop_details":null,"stop_reason":"stop_sequence","stop_sequence":"","type":"message","usage":{"input_tokens":0,"output_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":null,"cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":null,"iterations":null,"speed":null},"content":[{"type":"text","text":"API Error: 400 Model \"claude-opus-5\" has no AI credits pricing and no default pricing is configured. Set apiProxy.defaultAiCreditsPricing in the AWF config (e.g. {\"input\": 3.0, \"output\": 15.0}) to provide a fallback rate, or add the model to the pricing table."}],"context_management":null},"parent_tool_use_id":null,"session_id":"f8ef2dce-978e-4649-aae2-ecc82d307055","uuid":"68e1fc04-5985-44e1-a4bf-39e61f5a6a0b","timestamp":"2026-07-28T08:33:03.961Z","error":"unknown","is_api_error_message":true}
{"is_error":true,"duration_api_ms":0,"num_turns":1,"stop_reason":"stop_sequence","session_id":"f8ef2dce-978e-4649-aae2-ecc82d307055","total_cost_usd":0,"usage":{"input_tokens":0,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":0,"server_tool_use":{"web_search_requests":0,"web_fetch_requests":0},"service_tier":"standard","cache_creation":{"ephemeral_1h_input_tokens":0,"ephemeral_5m_input_tokens":0},"inference_geo":"","iterations":[],"speed":"standard"},"modelUsage":{},"permission_denials":[],"terminal_reason":"api_error","fast_mode_state":"off","fast_mode_disabled_reason":"disabled_by_env","subtype":"success","api_error_status":400,"result":"API Error: 400 Model \"claude-opus-5\" has no AI credits pricing and no default pricing is configured. Set apiProxy.defaultAiCreditsPricing in the AWF config (e.g. {\"input\": 3.0, \"output\": 15.0}) to provide a fallback rate, or add the model to the pricing table.","type":"result","duration_ms":598,"uuid":"27890df3-d6e8-4bb5-b8de-033e4ee8948c"}
2026-07-28T08:33:03.960Z [ERROR] Error in API request: 400 Model "claude-opus-5" has no AI credits pricing and no default pricing is configured. Set apiProxy.defaultAiCreditsPricing in the AWF config (e.g. {"input": 3.0, "output": 15.0}) to provide a fallback rate, or add the model to the pricing table.
2026-07-28T08:33:03.967Z [DEBUG] LSP server manager shut down successfully
Workflow Failure
Workflow: Daily Rendering Scripts Verifier
Branch: main
Run: https://github.com/github/gh-aw/actions/runs/30342547715
Warning
Model has no AI credits pricing: The agent failed because model
claude-opus-5is not in the built-in pricing table and no default fallback pricing is configured. The AWF API proxy rejected every inference request with HTTP 400.This is a configuration issue — retrying will not help. The model must have pricing before the workflow can run.
How to fix this
Option 1 — Add pricing in the workflow frontmatter:
Use the provider key matching your engine:
github-copilot(Copilot),anthropic(Claude),openai(Codex), orgoogle(Gemini). Onlyinputandoutputare required; the rest default to zero (oroutputforreasoning).Option 2 — Map the model to a known model using the
modelsfield:If
claude-opus-5is an alias for a model already in the built-in pricing table, use themodelsfrontmatter field to provide the mapping:Option 3 — Switch to a model already in the built-in pricing table:
Replace
claude-opus-5in the workflow frontmatter with a model name that the AWF pricing system recognizes (e.g.claude-sonnet-4-5,gpt-4.1,gemini-2.0-flash).Warning
Engine Failure: The
claudeengine terminated unexpectedly.Last agent output:
Action Required
Assign this issue to an agent to debug and fix the issue.
Debug with any coding agent
Use this prompt with any coding agent (GitHub Copilot, Claude, Gemini, etc.):
Manually invoke the agent
Debug this workflow failure using your favorite Agent CLI and the
agentic-workflowsprompt.agentic-workflowsskill from.github/skills/agentic-workflows/SKILL.mdor https://github.com/github/gh-aw/blob/main/.github/skills/agentic-workflows/SKILL.mddebug the agentic workflow daily-rendering-scripts-verifier failure in https://github.com/github/gh-aw/actions/runs/30342547715Tip
Stop reporting this workflow as a failure
To stop a workflow from creating failure issues, set
report-failure-as-issue: falsein its frontmatter: