of Kimi K2.5's tool calls fail on Amazon Bedrock.
Updated October 29, 2026
Tool-call index
Not all models are served equally by all providers. On a typical model, the worst provider breaks tool calls 19× as often as the best. Find the best one for your agents.
| # | Provider | Broken tool calls | Tool calls a day | $ in / out per M | Tokens/s | Uptime |
|---|---|---|---|---|---|---|
| 1 | SiliconFlowint4# | 0.17% | 11k | $0.50 / $2.50 | 22 | 100.0% |
| 2 | AtlasCloudint4# | 1.25% | 3.0k | $0.49 / $2.50 | 43 | 97.8% |
| 3 | Venice# | 2.44% | 8.0k | $0.53 / $3.33 | 36 | 99.9% |
| 4 | NovitaAI# | 3.61% | 4.1k | $0.57 / $2.85 | 42 | 99.1% |
| 5 | Amazon Bedrock# | 6.65% | 4.4k | $0.60 / $3.00 | 97 | 100.0% |
Recommended OpenRouter settings for Kimi K2.5
{
"provider": {
"order": [
"siliconflow/int4",
"atlas-cloud/int4",
"venice"
],
"ignore": [
"novita",
"amazon-bedrock/us-east-2"
]
}
}Point your agent at llms.txt
Get updates when its successor drops
And which provider to use.
For model makers
Broken tool calls carry your model's name
Releasing a model? Test it before launch.
as often on Amazon Bedrock as on SiliconFlow (int4), its best provider.
broken tool calls a day across its 5 providers.