Tool-call index
The same model breaks your agent's tool calls 18× more often on some inference providers than on others. Find the best one for your agents.
Give this to your agent ↓
← All models
Mistral · 1 provider · 125k tool calls a day
| # | Provider | | Tool calls
a day | $ in / out
per M | Tokens/s | Uptime |
|---|
| 1 | Mistral# | 5.20% | 18k | $0.70 / $2.10 | 86 | 99.9% |
| 2 | Mistralzdr# | 13.24% | 107k | $0.70 / $2.10 | 87 | 99.9% |
No recommended settings for Mistral Large 4 Every provider breaks 3% of tool calls or more.
Give llms.txt to your agent
Get updates when its successor drops
And which provider to use.
For model makersBroken tool calls carry your model's name
Your users don't see the provider. They see your model failing.
Worst provider13.24%of Mistral Large 4's tool calls fail on Mistral (zdr).
Best to worst3×as often on Mistral (zdr) as on Mistral, its best provider.
Every day15kbroken tool calls a day across its 1 provider.
