Try Bifrost Enterprise free for 14 days.
Request access

sarvam-105b Cost Calculator - Sarvam

Calculate the cost of using sarvam-105b from Sarvam for your AI applications

Pricing data last updated:

sarvam-105b Cost Calculator

Mode: Chat

Max: 128,000 tokens

Max: 128,000 tokens

Cost Breakdown

Input Cost$0.00015957
Output Cost$0.00063830
Total Cost$0.00079787

Pricing Details

Input: $0.0000001596 per token
Output: $0.0000006383 per token
[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

Model Specifications

Capabilities

✓Function Calling
✓Reasoning

Limits

Max Input Tokens128,000
Max Output Tokens128,000

About sarvam-105b

sarvam-105b is a chat model from Sarvam, one of 7 chat models they offer. It is priced at $0.16 per 1M input tokens and $0.64 per 1M output tokens, ranking 1398 out of 5562 chat models by cost and cheaper than 75% of models in this category. sarvam-105b supports function calling, reasoning, prompt caching, structured output. It accepts up to 128K input tokens.

Pricing Information

Input Cost$0.16 per 1M tokens
Output Cost$0.64 per 1M tokens

Note: Use the interactive calculator above to estimate costs for your specific usage patterns.

Technical Specifications

Maximum Input Tokens128,000
Maximum Output Tokens128,000

Pro Tip

Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 128,000 input tokens. The maximum output length is 128,000 tokens.

Model Capabilities

✓Function Calling - Execute custom functions and tools
✓Advanced Reasoning - Complex problem-solving capabilities
✓Prompt Caching - Optimize repeated prompts
✓System Messages - Configure model behavior
✓Parallel Function Calling - Execute multiple functions simultaneously
✓Response Schema - Structured output formatting

How sarvam-105b Pricing Compares

At $0.16 per 1M input tokens and $0.64 per 1M output tokens, sarvam-105b ranks 1398 out of 5562 chat models by input cost. It is more affordable compared to the median of $0.47 for chat models, and is cheaper than 75% of models in this category.

sarvam-105b is one of 7 Sarvam chat models, with support for function calling, reasoning, prompt caching, structured output.

ModelProviderInput / 1M tokensOutput / 1M tokensvs sarvam-105b
qwen3.8-flashDashscope$0.15$0.47-6%
qwen3.8-omni-flashDashscope$0.15$0.47-6%
qwen3.8-flashQwen Ai Platform$0.15$0.47-6%

Alternatives to sarvam-105b

Similar chat models from other providers

Dashscope
qwen3.8-flash
$0.15/1M input
-6% vs sarvam-105b
Dashscope
qwen3.8-omni-flash
$0.15/1M input
-6% vs sarvam-105b
Qwen Ai Platform
qwen3.8-flash
$0.15/1M input
-6% vs sarvam-105b
Qwen Ai Platform
qwen3.8-omni-flash
$0.15/1M input
-6% vs sarvam-105b
Sail
Gemma-4-31B-IT-NVFP4
$0.14/1M input
-12% vs sarvam-105b

Frequently Asked Questions

Is sarvam-105b cheaper than qwen3.8-flash?

No. sarvam-105b costs $0.16 per 1M input tokens while qwen3.8-flash costs $0.15 per 1M input tokens, making qwen3.8-flash 6% more affordable for input. However, sarvam-105b may offer different capabilities or performance characteristics that justify the price difference.

How does sarvam-105b pricing compare to the average chat model?

sarvam-105b input pricing is $0.16 per 1M tokens, which is 66% below the median of $0.47 for chat models. It ranks 1398 out of 5562 chat models by input cost, making it cheaper than 75% of models in this category. For output, it costs $0.64 per 1M tokens compared to the median of $1.56.

What makes sarvam-105b different from other Sarvam models?

Among Sarvam's 7 chat models, sarvam-105b ranks 3 by input cost.

What are the best alternatives to sarvam-105b?

The most comparable chat models to sarvam-105b are: qwen3.8-flash from Dashscope ($0.15/1M input tokens); qwen3.8-omni-flash from Dashscope ($0.15/1M input tokens); qwen3.8-flash from Qwen Ai Platform ($0.15/1M input tokens); qwen3.8-omni-flash from Qwen Ai Platform ($0.15/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.

How do I calculate sarvam-105b costs?

sarvam-105b is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.16 and generating 1M output tokens costs $0.64.