The Inference Directory
Explore directory

Krutrim

Verified

Ola Krutrim AI Studio offers an OpenAI-compatible catalogue of Indian and open models, with GPU and fine-tuning options, hosted in India.

Indian-owned India hosting AI studio
Visit website API docs

At a glance

Record
Legal entity
Krutrim SI Designs Private Limited
Headquarters
Bengaluru, Karnataka, India
Hosting region
India (Bengaluru)
Group
AI studio
SLA
Not published

Summary

Scope

Ola Krutrim AI Studio offers an OpenAI-compatible catalogue of Indian and open models, with GPU and fine-tuning options, hosted in India.

Catalogue refreshed 4 November 2026. Prices exclude 18% GST.

Source: cloud.olakrutrim.com ↗ · Updated Nov 4, 2026

API access

OpenAI-compatible

Bearer

Billing

INR billing with a free tier and no card required.

KYC

Business account

Compliance

ISO 27001SOC 2

Key models

7 listed
gpt-oss-20b 128K · per 1M tokens LLM ₹8 / ₹32 per 1M tokens
gpt-oss-120b 128K · per 1M tokens LLM ₹13 / ₹65 per 1M tokens
gemma-4-E4B-it 131K · per 1M tokens Multimodal ₹3 / ₹8 per 1M tokens
gemma-4-31b-it 262K · per 1M tokens Multimodal ₹9 / ₹33 per 1M tokens
gemma-4-26B-A4B-it 262K · per 1M tokens Multimodal ₹7 / ₹28 per 1M tokens
Qwen3.5-9B 32K · per 1M tokens Multimodal ₹3 / ₹8 per 1M tokens
Qwen3.6-35B-A3B 262K · per 1M tokens Multimodal ₹7 / ₹28 per 1M tokens

Pricing

List rates · local currency · GST excluded
Model Type Input price Caching price Output price
gpt-oss-20b128K · per 1M tokens LLM ₹8 - ₹32
gpt-oss-120b128K · per 1M tokens LLM ₹13 - ₹65
gemma-4-E4B-it131K · per 1M tokens Multimodal ₹3 - ₹8
gemma-4-31b-it262K · per 1M tokens Multimodal ₹9 - ₹33
gemma-4-26B-A4B-it262K · per 1M tokens Multimodal ₹7 - ₹28
Qwen3.5-9B32K · per 1M tokens Multimodal ₹3 - ₹8
Qwen3.6-35B-A3B262K · per 1M tokens Multimodal ₹7 - ₹28

List rates. Cached input shown where published; "-" means the provider does not publish a cache rate. Prices exclude 18% GST where applicable. INR billing with a free tier and no card required.

Infrastructure

Source-backed
RegionIndia
CitiesBengaluru
SLANot published
API basehttps://cloud.olakrutrim.com/v1
AuthBearer
Rate limitNot published.

Access

Billing & API
API basehttps://cloud.olakrutrim.com/v1
AuthBearer
Rate limitNot published.
SLANot published

INR billing with a free tier and no card required.

Compliance

Source-backed
DPAAvailable
ZDRnot_published
Trainingnot_published
RetentionGoverned by agreement or DPA; ZDR is not published.
Certifications
SOC 2 (claimed)ISO 27001 (claimed)
Subprocessors

affiliates

Benchmarks

Coming soon

Coming soon.

Performance

Coming soon
Latency

Time to first token

Median and p95 response times for short and long prompts, measured from repeatable probes rather than vendor claims.

Coming soon
Throughput

Tokens per second

Streaming output rate and request throughput under steady load, with concurrency and context length recorded.

Coming soon
Efficiency

Cost per workload

Blended cost for a fixed workload, including cache reads and output tokens, so speed and price can be compared together.

Coming soon

Independent performance probes are being added. Vendor-reported numbers are not mixed into this section.