Summary
The mistral-small-latest entry in model_list.json has stale pricing and context window values. Mistral Small has been updated to "Mistral Small 4" (released March 2025) with significantly different specs.
Current values in catalog
| Field |
Current Value |
Correct Value |
input_cost_per_mil_tokens |
0.06 |
0.15 |
output_cost_per_mil_tokens |
0.18 |
0.60 |
max_input_tokens |
131072 |
262144 |
max_output_tokens |
131072 |
262144 |
Verification
Suggested fix
Update the mistral-small-latest entry in packages/proxy/schema/model_list.json (currently around line 4966):
"mistral-small-latest": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.15,
"output_cost_per_mil_tokens": 0.60,
"displayName": "Mistral Small",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"available_providers": ["mistral"]
}
Summary
The
mistral-small-latestentry inmodel_list.jsonhas stale pricing and context window values. Mistral Small has been updated to "Mistral Small 4" (released March 2025) with significantly different specs.Current values in catalog
input_cost_per_mil_tokensoutput_cost_per_mil_tokensmax_input_tokensmax_output_tokensVerification
mistral-small-latestmatches existing naming convention in catalogSuggested fix
Update the
mistral-small-latestentry inpackages/proxy/schema/model_list.json(currently around line 4966):