Skip to content
Source
Sign inSign up
TanStack/schemas

Missing rate cards: Together, Cohere, Gemini, and Mistral chat rows #111

Send to my agent
Closedtombeckenham opened this issue 0 comments
tombeckenhamcommented

Problem

#73 added pricing sources. Some chat rows still have pricing: null.

Measured on GET /v1/models?pricing=1 on 2026-10-03:

ProviderChat rows without a cardExamples
together112 / 187agentica-org/DeepCoder-14B-Preview, allenai/Molmo-7B-D-0924
cohere17 / 17command-a-03-2025, command-a-plus-05-2026
gemini16 / 43antigravity-preview-09-2026, aqa
mistral15 / 33magistral-medium-latest, glm-5-2, labs-leanstral-1-5
openai4 / 107gpt-5-search-api, gpt-3.5-turbo-16k
byteplus2 / 13deepseek-v4-1-flash-260910

Also, no Groq card (6) and no Together card (75) has a cache_read_tokens rate.

Ask

  1. Add a pricing source for Cohere.
  2. Find why 112 Together chat rows have no card when 75 do.
  3. Fill the Mistral and Gemini rows where the provider's price page lists the model. Leave preview models with no published price as null.
  4. Check whether Groq and Together publish a cached-input price. If they do, add it.

Acceptance

  • GET /v1/status shows a non-zero counts.priced for cohere.
  • GET /v1/models/mistral/magistral-medium-latest returns a rate card.
  • Together priced / models is above 90%, or the unpriced rows are ones Together does not price per token.
  1. tombeckenham added labelsbug

  2. tombeckenham closed this

Sign in to join this conversation.