As of August 30, 2026, Llama 4 Scout is 76% cheaper per million tokens than Sarvam-105B. Llama 4 Scout is $0.08 / $0.30 per million input/output tokens versus Sarvam-105B at $0.80 / $0.80. Sources: https://llama.meta.com/ and https://www.sarvam.ai/
Sources: Meta pricing (https://llama.meta.com/); Sarvam AI pricing (https://www.sarvam.ai/)
Llama 4 Scout
Meta
Input
$0.08
Output
$0.30
Sarvam-105B
Sarvam AI
Input
$0.80
Output
$0.80
Token pricing, specs, and benchmarks side by side
Each bar is share of the current leader on that eval. Click a row to open the board.
GPQA. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price.
Llama 4 ScoutSarvam-105BVerdict
Llama 4 Scout offers significantly lower pricing, while Sarvam-105B leads on benchmark performance. Your choice depends on whether cost efficiency or raw capability matters more for your use case.
As of August 30, 2026, Llama 4 Scout is 76% cheaper on blended LLM API pricing. Llama 4 Scout costs $0.08 per million input tokens and $0.30 per million output tokens ($0.38 blended 1M-in + 1M-out). Sarvam-105B costs $0.80 / $0.80 per million tokens ($1.60 blended). Sources: https://llama.meta.com/ and https://www.sarvam.ai/. The cheapest LLM for your app still depends on how many output tokens you generate.
Llama 4 Scout Meta API pricing is $0.08 input and $0.30 output per million tokens via Meta. Sarvam-105B Sarvam AI API pricing is $0.80 input and $0.80 output per million tokens via Sarvam AI. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Sarvam-105B has a published SWE-bench Verified score of 45%. Llama 4 Scout does not have that eval on this page yet.
Llama 4 Scout supports a 10M token context window, while Sarvam-105B supports 33K tokens. Llama 4 Scout offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
Sarvam-105B leads on 3 of 3 shared benchmarks versus Llama 4 Scout's 0 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Both Llama 4 Scout and Sarvam-105B are production API models. For cost-sensitive production traffic, Llama 4 Scout has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Yes. Call Llama 4 Scout through Meta and Sarvam-105B through Sarvam AI with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
List rates are the latest published Meta API pricing and Sarvam AI API pricing, quoted per million tokens. Official rate sheets: https://llama.meta.com/ and https://www.sarvam.ai/. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
Llama 4 Scout supports up to 10M output tokens per request, while Sarvam-105B supports up to an unspecified number of output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Llama 4 Scout has a measured throughput of approximately 76.1 tokens/second. Throughput data for Sarvam-105B is not yet available. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Llama 4 Scout or Sarvam-105B from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. Llama 4 Scout costs $0.08/M input and $0.30/M output. Sarvam-105B costs $0.80/M input and $0.80/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
343 models across 36 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
