Model profile
Sarvam
New in 2026

Sarvam 105B (Reasoning)

Sarvam 105B (Reasoning) is a budget-priced text-first model from Sarvam with balanced runtime profile, partial context coverage, and the clearest fit around agent workflows / reasoning.

Best for: Agent workflows / ReasoningBalanced latencyN/A contextBudget pricing
Intelligence
18.2

Benchmark blend

Coding
9.8

Dev workflow signal

Context
N/A

N/A

Input Price
$0.00

Budget tier

Decision snapshot
38

Sarvam 105B (Reasoning) currently reads as a budget text-first option with partially published context and a balanced runtime profile.

Overall profile
Use-case specific
Best for
Agent workflows / Reasoning
Latency tier
Balanced
Price tier
Budget
Source coverage
OpenRouterArtificial Analysis

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
18.2
18

General reasoning and benchmark headroom.

Limited
Speed
79 tok/s
57

TTFT 1.92s

Situational
Context
N/A
N/A

How much prompt and task state can stay in view.

Unavailable
Price
$0.00
86

$0.00 output / 1M

Efficient

Editorial Profile

Sarvam 105B (Reasoning) in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Use-case specificCoding score 10Math score N/A

The Sarvam 105B (Reasoning) AI model by Sarvam.

Identity

Sarvam text-first profile

Positioning

Agent workflows / Reasoning with partially published context and balanced runtime.

Cost posture

Efficient spend profile. More comfortable for sustained prompt volume if the capability fit is right.

Strengths
  • The available source data suggests a balanced profile rather than one dominant edge.

Tradeoffs
  • Budget-friendly input pricing is a strength, but raw capability may vary by workload.

  • Latency is balanced rather than ultra-fast, which is fine for most workflows but not the snappiest tier.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

  • Context limits are only partially published, so long-session planning needs extra validation.

Best fit
  • Focused chat, retrieval-augmented flows, and narrower production tasks.

Explore Next

Similar profiles worth opening next

Sarvam

Sarvam 30B (Reasoning)

Intelligence
12.4
Context
N/A
Input Price
$0.00
Sarvam

Sarvam M (Reasoning)

Intelligence
8.4
Context
N/A
Input Price
$0.00

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

General intelligence

Broad reasoning, knowledge depth, and flagship benchmark posture.

Intelligence Index
18.2
GPQA
73.8%
HLE
10.1%
Coding

Software implementation, debugging quality, and coding benchmark signal.

Coding Index
9.8
SciCode
26.4%
Agent / tool use

Long-horizon execution quality and interactive benchmark evidence.

IFBench
34.4%
TAU2
46.8%
TerminalBench Hard
1.5%
LCR
0.0%

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
N/A
Vision
Text-first
Price architecture
Input
per 1M input tokens
$0.00
Output
per 1M output tokens
$0.00
Blended
AA 3:1 mix
$0.00

This model is relatively efficient on price. It is the easier fit when sustained prompt volume matters.

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.