litellm - 💡(How to fix) Fix [Bug]: Pricing Bug [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#25890Fetched 2026-04-17 08:28:16
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
0
Participants
Timeline (top)
labeled ×2mentioned ×1subscribed ×1

Code Example

take a look at key value 

{
  "model_name": "vertex_ai/claude-opus-4-7-global",
  "litellm_params": {
    "vertex_project": "cl368614",
    "vertex_location": "global",
    "use_in_pass_through": false,
    "use_litellm_proxy": false,
    "merge_reasoning_content_in_choices": false,
    "model": "vertex_ai/claude-opus-4-7"
  },
  "model_info": {
    "id": "8fd8af43ae96b2d06512cc818b7f2d13b5822c1ff8f84e170039222fc87df2f8",
    "db_model": false,
    "access_groups": [
      "vertex-global"
    ],
    "access_via_team_ids": [
      "cf-3911-4ca1-bdf0-f4f889e149b7",
      "d06f9d45ae"
    ],
    "direct_access": true,
    "key": "vertex_ai/claude-opus-4",
    "max_tokens": 32000,
    "max_input_tokens": 200000,
    "max_output_tokens": 32000,
    "input_cost_per_token": 0.000015,
    "input_cost_per_token_flex": null,
    "input_cost_per_token_priority": null,
    "cache_creation_input_token_cost": 0.00001875,
    "cache_creation_input_token_cost_above_200k_tokens": null,
    "cache_read_input_token_cost": 0.0000015,
    "cache_read_input_token_cost_above_200k_tokens": null,
    "cache_read_input_token_cost_above_272k_tokens": null,
    "cache_read_input_token_cost_flex": null,
    "cache_read_input_token_cost_priority": null,
    "cache_creation_input_token_cost_above_1hr": null,
    "input_cost_per_character": null,
    "input_cost_per_token_above_128k_tokens": null,
    "input_cost_per_token_above_200k_tokens": null,
    "input_cost_per_token_above_272k_tokens": null,
RAW_BUFFERClick to expand / collapse

Check for existing issues

  • I have searched the existing issues and checked that my issue is not a duplicate.

What happened?

vertex_ai/claude-opus-4.-7 pricing is not displayed even if the price is correct in the pricing file

instead litellm us the price from vertex_ai/claude-opus-4

@ishaan-berri

Steps to Reproduce

  1. declare the model
  2. check in gui

Relevant log output

take a look at key value 

{
  "model_name": "vertex_ai/claude-opus-4-7-global",
  "litellm_params": {
    "vertex_project": "cl368614",
    "vertex_location": "global",
    "use_in_pass_through": false,
    "use_litellm_proxy": false,
    "merge_reasoning_content_in_choices": false,
    "model": "vertex_ai/claude-opus-4-7"
  },
  "model_info": {
    "id": "8fd8af43ae96b2d06512cc818b7f2d13b5822c1ff8f84e170039222fc87df2f8",
    "db_model": false,
    "access_groups": [
      "vertex-global"
    ],
    "access_via_team_ids": [
      "cf-3911-4ca1-bdf0-f4f889e149b7",
      "d06f9d45ae"
    ],
    "direct_access": true,
    "key": "vertex_ai/claude-opus-4",
    "max_tokens": 32000,
    "max_input_tokens": 200000,
    "max_output_tokens": 32000,
    "input_cost_per_token": 0.000015,
    "input_cost_per_token_flex": null,
    "input_cost_per_token_priority": null,
    "cache_creation_input_token_cost": 0.00001875,
    "cache_creation_input_token_cost_above_200k_tokens": null,
    "cache_read_input_token_cost": 0.0000015,
    "cache_read_input_token_cost_above_200k_tokens": null,
    "cache_read_input_token_cost_above_272k_tokens": null,
    "cache_read_input_token_cost_flex": null,
    "cache_read_input_token_cost_priority": null,
    "cache_creation_input_token_cost_above_1hr": null,
    "input_cost_per_character": null,
    "input_cost_per_token_above_128k_tokens": null,
    "input_cost_per_token_above_200k_tokens": null,
    "input_cost_per_token_above_272k_tokens": null,

What part of LiteLLM is this about?

Proxy

What LiteLLM version are you on ?

last staging

Twitter / LinkedIn details

No response

extent analysis

TL;DR

The issue can be resolved by verifying the model_name and litellm_params configuration to ensure they match the expected pricing model.

Guidance

  • Check the model_name in the log output to ensure it matches the expected model name vertex_ai/claude-opus-4-7.
  • Verify that the litellm_params configuration, specifically the model field, is set to the correct model name vertex_ai/claude-opus-4-7.
  • Review the pricing file to ensure that the price is correctly configured for the vertex_ai/claude-opus-4-7 model.
  • Investigate why the litellm is using the price from vertex_ai/claude-opus-4 instead of vertex_ai/claude-opus-4-7.

Notes

The issue seems to be related to a mismatch between the expected model name and the actual model name used by litellm. The provided log output shows that the model_name is vertex_ai/claude-opus-4-7-global, but the litellm_params configuration has a model field set to vertex_ai/claude-opus-4.

Recommendation

Apply workaround: Verify and correct the model_name and litellm_params configuration to ensure they match the expected pricing model. This should resolve the issue with the pricing not being displayed correctly.

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 [Bug]: Pricing Bug [1 participants]