Sarvam 105B API

Sarvam's Sarvam 105B, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send sarvam-105b as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: sarvam-105b
Maker: Sarvam
Context window: 131.1K tokens
Input price: $0.054 per million tokens
Output price: $0.213 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.054 input and $0.213 output per million tokens, $0.034 cache read per million tokens, 131.1K tokens of context

Scores

HLE: 11.0, #153 of 273
GPQA: 73.8, #140 of 250
AA-LCR: 0.0, #231 of 237
Terminal-Bench Hard: 1.5, #156 of 166
τ²-Bench: 46.8, #105 of 169
IFBench: 34.4, #146 of 178

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sarvam-105b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Sarvam 105B?: Sarvam 105B is a model from Sarvam.
How much does Sarvam 105B cost?: Offers now ask $0.054 per million input tokens and $0.213 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Sarvam 105B?: The largest offer takes 131,072 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Sarvam 105B do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Sarvam 105B support?: Text → Text.
Which providers serve Sarvam 105B?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Sarvam 105B?: Send "sarvam-105b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Sarvam 105B listed?: The exchange first listed it on 10/5/2026. This is not its release date.