Sarvam 105B

fastrouter/sarvam/sarvam-105b · family sarvam · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.07Blended $/1M (3:1)

$0.04Input $/1M

$0.16Output $/1M

$0.201M in + 1M out

—Cache read $/1M

#654 of 5,000Cheapest rank

Provider: FastRouter (fastrouter)
Context: 131,072 tokens
Max output: 131,072 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“Sarvam 105B” is offered by 2 providers — cheapest-effective first. This one (FastRouter) is the cheapest.

Provider	Input	Output	Blended	Context
FastRouter (this)	$0.04	$0.16	$0.07	131k
NanoGPT	$0.045	$0.177	$0.08	131k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at FastRouter and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"sarvam/sarvam-105b","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):