litellm - 💡(How to fix) Fix Add Venice models support "venice/grok-code-fast-1" in "model_prices_and_context_window.json" [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
BerriAI/litellm#24229Fetched 2026-04-08 01:09:11
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Participants
Timeline (top)
labeled ×1
RAW_BUFFERClick to expand / collapse

Source: https://docs.venice.ai/api-reference/

We need to update both model_prices_and_context_window.json and model_prices_and_context_window_backup.json to reflect the new model.

Please add Venice models support

https://docs.venice.ai/models/overview

Model list table

Model NameModel IDContextAttributesSizeInput ($/M)Output ($/M)Cache/Notes
MiniMax M2.7minimax-m27198KAnonymizedL$0.38$1.50$0.07 cache
Venice Uncensored 1.1e2ee-venice-uncensored-24b-p32KE2EE, Private, Beta, UncensoredL$0.25$1.15 
Gemma 3 27Be2ee-gemma-3-27b-p40KE2EE, Private, BetaL$0.14$0.50 
GLM 4.7e2ee-glm-4-7-p128KE2EE, Private, BetaL$1.10$4.15 
GLM 4.7 Flashe2ee-glm-4-7-flash-p198KE2EE, Private, BetaL$0.13$0.55 
GPT OSS 20Be2ee-gpt-oss-20b-p128KE2EE, Private, BetaL$0.05$0.19 
GPT OSS 120Be2ee-gpt-oss-120b-p128KE2EE, Private, BetaL$0.13$0.65 
Qwen 2.5 7Be2ee-qwen-2-5-7b-p32KE2EE, Private, BetaL$0.05$0.13 
Qwen3 30B A3Be2ee-qwen3-30b-a3b-p256KE2EE, Private, BetaL$0.19$0.69 
Qwen3 VL 30B A3Be2ee-qwen3-vl-30b-a3b-p128KE2EE, Private, BetaL$0.25$0.90 
GLM 5e2ee-glm-5198KE2EE, Private, BetaL$1.10$4.15 
Qwen3.5 122B A10Be2ee-qwen3-5-122b-a10b128KE2EE, Private, BetaL$0.50$4.00 
Grok 4.20 Betagrok-4-20-beta2.0MAnonymized, BetaL$2.50$7.50$0.25 cache (Higher tier >200K: $5.00/$15.00)
Grok 4.20 Multi-Agent Betagrok-4-20-multi-agent-beta2.0MAnonymized, BetaL$2.50$7.50$0.25 cache (Higher tier >200K: $5.00/$15.00)
Qwen 3.5 9Bqwen3-5-9b256KPrivateL$0.05$0.15 
GPT-5.4openai-gpt-541.0MAnonymized, BetaL$3.13$18.80$0.31 cache
GPT-5.4 Proopenai-gpt-54-pro1.0MAnonymized, BetaL$37.50$225.00Higher tier >272K: $75.00/$337.50
GPT-4oopenai-gpt-4o-2024-11-20128KAnonymizedL$3.13$12.50 
GPT-4o Miniopenai-gpt-4o-mini-2024-07-18128KAnonymizedL$0.19$0.75$0.09 cache
Qwen 3.5 35B A3Bqwen3-5-35b-a3b256KPrivate, BetaL$0.31$1.25$0.16 cache
GPT-5.3 Codexopenai-gpt-53-codex400KAnonymized, BetaL$2.19$17.50$0.22 cache
Venice Role Play Uncensoredvenice-uncensored-role-play128KPrivate, UncensoredL$0.50$2.00 
Gemini 3.1 Pro Previewgemini-3-1-pro-preview1.0MAnonymizedL$2.50$15.00$0.50 cache (Higher tier >200K: $5.00/$22.50)
Claude Sonnet 4.6claude-sonnet-4-61.0MAnonymized, BetaL$3.60$18.00$0.36/$4.50 cache
MiniMax M2.5minimax-m25198KPrivateL$0.34$1.19$0.04 cache
GLM 5zai-org-glm-5198KPrivateL$1.00$3.20$0.20 cache
Claude Opus 4.6claude-opus-4-61.0MAnonymized, BetaL$6.00$30.00$0.60/$7.50 cache
GLM 4.7 Flash Hereticolafangensan-glm-4.7-flash-heretic200KPrivateL$0.14$0.80 
GLM 4.7 Flashzai-org-glm-4.7-flash128KPrivateL$0.13$0.50 
Kimi K2.5kimi-k2-5256KPrivateL$0.56$3.50$0.11 cache
Qwen 3 Coder 480B Turboqwen3-coder-480b-a35b-instruct-turbo256KPrivate, BetaL$0.35$1.50$0.04 cache
NVIDIA Nemotron 3 Nano 30Bnvidia-nemotron-3-nano-30b-a3b128KPrivate, BetaL$0.07$0.30 
Qwen3 VL 235Bqwen3-vl-235b-a22b256KPrivateL$0.25$1.50 
Mistral Small 3.2 24B Instructmistral-small-3-2-24b-instruct256KPrivateL$0.09$0.25 
GLM 4.7zai-org-glm-4.7198KPrivateL$0.55$2.65$0.11 cache
Gemini 3 Flash Previewgemini-3-flash-preview256KAnonymizedL$0.70$3.75$0.07 cache
GPT-5.2openai-gpt-52256KAnonymizedL$2.19$17.50$0.22 cache
Kimi K2 Thinkingkimi-k2-thinking256KPrivateL$0.75$3.20$0.38 cache
Claude Opus 4.5claude-opus-4-5198KAnonymizedL$6.00$30.00$0.60/$7.50 cache
DeepSeek V3.2deepseek-v3.2160KPrivateL$0.33$0.48$0.16 cache
Gemini 3 Pro Previewgemini-3-pro-preview198KAnonymizedL$2.50$15.00$0.63 cache
Grok 4.1 Fastgrok-41-fast1.0MAnonymizedL$0.25$0.63$0.06 cache
MiniMax M2.1minimax-m21198KPrivateL$0.35$1.50$0.04 cache
Grok Code Fast 1grok-code-fast-1256KAnonymizedL$0.25$1.87$0.03 cache
OpenAI GPT OSS 120Bopenai-gpt-oss-120b128KPrivateL$0.07$0.30 
Google Gemma 3 27B Instructgoogle-gemma-3-27b-it198KPrivateM$0.12$0.20 
Hermes 3 Llama 3.1 405bhermes-3-llama-3.1-405b128KPrivateL$1.10$3.00 
Venice Smallqwen3-4b32KPrivate, DeprecatedXS$0.05$0.15 
Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507128KPrivateL$0.45$3.50 
Qwen 3 235B A22B Instruct 2507qwen3-235b-a22b-instruct-2507128KPrivateL$0.15$0.75 
Qwen 3 Next 80bqwen3-next-80b256KPrivateM$0.35$1.90 
Qwen 3 Coder 480bqwen3-coder-480b-a35b-instruct256KPrivateL$0.75$3.00 
Llama 3.3 70Bllama-3.3-70b128KPrivateM$0.70$2.80 
Venice Uncensored 1.1venice-uncensored32KPrivate, UncensoredS$0.20$0.90 
Venice Mediummistral-31-24b128KPrivate, DeprecatedS$0.50$2.00 
Claude Sonnet 4.5claude-sonnet-4-5198KAnonymizedL$3.75$18.75$0.38/$4.69 cache
GPT-5.2 Codexopenai-gpt-52-codex256KAnonymizedL$2.19$17.50$0.22 cache
Llama 3.2 3Bllama-3.2-3b128KPrivateXS$0.15$0.60 
GLM 4.6zai-org-glm-4.6198KPrivateL$0.85$2.75$0.30 cache

extent analysis

Fix Plan

To update the model_prices_and_context_window.json and model_prices_and_context_window_backup.json files to reflect the new Venice models, follow these steps:

  1. Add new model entries: Insert the following JSON objects into the files:

    {
      "model_name": "Venice Uncensored 1.1",
      "model_id": "e2ee-venice-uncensored-24b-p",
      "context": 32000,
      "attributes": ["E2EE", "Private", "Beta", "Uncensored"],
      "size": "L",
      "input_price": 0.25,
      "output_price": 1.15
    }

    Add similar entries for other new models, replacing the values as necessary.

  2. Update existing model entries (if necessary): Review the existing models and update their prices, contexts, or attributes if they have changed.

  3. Remove deprecated models (if necessary): If any models are marked as deprecated, consider removing them from the files.

Verification

To verify that the fix worked:

  1. Check file contents: Open the updated model_prices_and_context_window.json and model_prices_and_context_window_backup.json files and verify that the new model entries have been added correctly.
  2. Test model usage: Use the updated models in your application and verify that they are working as expected, with the correct prices and attributes applied.

Extra Tips

  • Make sure to backup the original files before making any changes.
  • Consider automating the process of updating the model files using a script or a CI/CD pipeline.
  • Keep the model files in sync with the latest documentation and pricing information from the model providers.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

litellm - 💡(How to fix) Fix Add Venice models support "venice/grok-code-fast-1" in "model_prices_and_context_window.json" [1 participants]