[NA] [BE][FE] chore: sync provider model definitions

[CometActions]

Details

Automated sync of LLM provider model definitions from source APIs and prices JSON.

Sync summary:

## Provider Model Sync

### Openrouter
- Added 3 model(s):
  + arcee-ai/trinity-large-thinking
  + rekaai/reka-edge
  + z-ai/glm-5v-turbo
- Stale 93 model(s) (not in source, manual review needed):
  ? ai21/jamba-mini-1.7
  ? alibaba/tongyi-deepresearch-30b-a3b:free
  ? allenai/molmo-2-8b
  ? allenai/olmo-3-7b-instruct
  ? allenai/olmo-3-7b-think
  ? arcee-ai/afm-4.5b
  ? arliai/qwq-32b-arliai-rpr-v1
  ? arliai/qwq-32b-arliai-rpr-v1:free
  ? deepcogito/cogito-v2-preview-deepseek-671b
  ? deepcogito/cogito-v2-preview-llama-109b-moe
  ? deepcogito/cogito-v2-preview-llama-405b
  ? deepcogito/cogito-v2-preview-llama-70b
  ? deepseek/deepseek-chat-v3-0324:free
  ? deepseek/deepseek-prover-v2
  ? deepseek/deepseek-r1-0528-qwen3-8b
  ? deepseek/deepseek-r1-0528-qwen3-8b:free
  ? deepseek/deepseek-r1-0528:free
  ? deepseek/deepseek-r1-distill-llama-70b:free
  ? deepseek/deepseek-r1-distill-qwen-14b
  ? deepseek/deepseek-r1:free
  ? deepseek/deepseek-v3.1-terminus:exacto
  ? google/gemini-2.0-flash-exp:free
  ? google/gemini-2.5-flash-image-preview
  ? google/gemini-2.5-flash-preview-09-2025
  ? google/gemini-3-pro-preview
  ? kwaipilot/kat-coder-pro
  ? kwaipilot/kat-coder-pro:free
  ? meituan/longcat-flash-chat:free
  ? meta-llama/llama-3.1-405b
  ? meta-llama/llama-3.1-405b-instruct
  ? meta-llama/llama-3.2-90b-vision-instruct
  ? meta-llama/llama-guard-2-8b
  ? microsoft/mai-ds-r1
  ? microsoft/mai-ds-r1:free
  ? microsoft/phi-3-medium-128k-instruct
  ? microsoft/phi-3-mini-128k-instruct
  ? microsoft/phi-3.5-mini-128k-instruct
  ? microsoft/phi-4-multimodal-instruct
  ? microsoft/phi-4-reasoning-plus
  ? mistralai/codestral-2501
  ? mistralai/devstral-small-2505
  ? mistralai/magistral-medium-2506
  ? mistralai/magistral-medium-2506:thinking
  ? mistralai/magistral-small-2506
  ? mistralai/ministral-3b
  ? mistralai/ministral-8b
  ? mistralai/mistral-7b-instruct
  ? mistralai/mistral-7b-instruct-v0.2
  ? mistralai/mistral-7b-instruct-v0.3
  ? mistralai/mistral-7b-instruct:free
  ? mistralai/mistral-nemo:free
  ? mistralai/mistral-small
  ? mistralai/mistral-small-24b-instruct-2501:free
  ? mistralai/mistral-small-3.1-24b-instruct:free
  ? mistralai/mistral-small-3.2-24b-instruct:free
  ? mistralai/mistral-tiny
  ? mistralai/pixtral-12b
  ? moonshotai/kimi-dev-72b
  ? moonshotai/kimi-k2-0905:exacto
  ? moonshotai/kimi-k2:free
  ? moonshotai/kimi-linear-48b-a3b-instruct
  ? neversleep/llama-3.1-lumimaid-8b
  ? neversleep/noromaid-20b
  ? nousresearch/deephermes-3-mistral-24b-preview
  ? openai/chatgpt-4o-latest
  ? openai/codex-mini
  ? openai/gpt-5.2-chat-latest
  ? openai/gpt-oss-120b:exacto
  ? opengvlab/internvl3-78b
  ? openrouter/healer-alpha
  ? openrouter/hunter-alpha
  ? perplexity/sonar-reasoning
  ? qwen/qwen-2.5-72b-instruct:free
  ? qwen/qwen-2.5-coder-32b-instruct:free
  ? qwen/qwen-2.5-vl-7b-instruct
  ? qwen/qwen2.5-vl-32b-instruct:free
  ? qwen/qwen3-14b:free
  ? qwen/qwen3-235b-a22b:free
  ? qwen/qwen3-30b-a3b:free
  ? qwen/qwen3-4b:free
  ? qwen/qwen3-coder:exacto
  ? raifle/sorcererlm-8x22b
  ? reka/reka-edge
  ? stepfun-ai/step3
  ? thedrummer/anubis-70b-v1.1
  ? thudm/glm-4.1v-9b-thinking
  ? tngtech/deepseek-r1t-chimera
  ? tngtech/deepseek-r1t-chimera:free
  ? tngtech/deepseek-r1t2-chimera:free
  ? x-ai/grok-4.1-fast:free
  ? x-ai/grok-4.20-beta
  ? x-ai/grok-4.20-multi-agent-beta
  ? z-ai/glm-4.6:exacto
- Total models: 443 (dropdown: 443)

### Openai
- Stale 15 model(s) (not in source, manual review needed):
  ? chatgpt-4o-latest
  ? gpt-4-0125-preview
  ? gpt-4-0314
  ? gpt-4-1106-preview
  ? gpt-4-turbo-2024-04-09
  ? gpt-4-turbo-preview
  ? gpt-4o-2024-05-13
  ? gpt-4o-2024-08-06
  ? gpt-4o-2024-11-20
  ? gpt-4o-mini-2024-07-18
  ? o1-2024-12-17
  ? o1-mini
  ? o1-mini-2024-09-12
  ? o1-preview
  ? o1-preview-2024-09-12
- Deprecated 4 model(s) (past deprecation_date, excluded from dropdown):
  ✗ gpt-4-0125-preview
  ✗ gpt-4-0314
  ✗ gpt-4-0613
  ✗ gpt-4-1106-preview
- Total models: 62 (dropdown: 19)

### Anthropic
- Stale 2 model(s) (not in source, manual review needed):
  ? claude-3-7-sonnet-20250219
  ? claude-sonnet-4-5
- Deprecated 1 model(s) (past deprecation_date, excluded from dropdown):
  ✗ claude-3-7-sonnet-20250219
- Total models: 10 (dropdown: 8)

### Gemini
- Stale 6 model(s) (not in source, manual review needed):
  ? aqa
  ? gemini-1.0-pro
  ? gemini-1.5-flash-latest
  ? gemini-1.5-pro-latest
  ? gemini-pro-vision
  ? text-embedding-004
- Deprecated 2 model(s) (past deprecation_date, excluded from dropdown):
  ✗ gemini-3-pro-preview
  ✗ text-embedding-004
- Total models: 21 (dropdown: 10)

### Vertexai
- Stale 9 model(s) (not in source, manual review needed):
  ? vertex_ai/gemini-2.0-flash-001
  ? vertex_ai/gemini-2.0-flash-lite-001
  ? vertex_ai/gemini-2.5-flash
  ? vertex_ai/gemini-2.5-flash-lite-preview-06-17
  ? vertex_ai/gemini-2.5-flash-preview-04-17
  ? vertex_ai/gemini-2.5-pro
  ? vertex_ai/gemini-2.5-pro-exp-03-25
  ? vertex_ai/gemini-2.5-pro-preview-03-25
  ? vertex_ai/gemini-2.5-pro-preview-05-06
- Total models: 12 (dropdown: 7)

Change checklist

• User facing
• Documentation update

Issues

• NA

AI-WATERMARK

AI-WATERMARK: yes

• If yes:
  • Tools: GitHub Actions (sync_provider_models.yml)
  • Model(s): N/A (scripted automation)
  • Scope: Automated model list sync
  • Human verification: Requires manual review before merge

Testing

• Script dry-run passed in CI
• Changes are add-only; stale/deprecated models flagged for manual review

Documentation

N/A

[github-actions]

Backend Tests - Integration Group 11

225 tests   224 ✅  4m 21s ⏱️
 44 suites    0 💤
 44 files      1 ❌

For more details on these failures, see this check.

Results for commit 0c4744e.