As of August 30, 2026, Sarvam-30B is 67% cheaper per million tokens than Qwen2-VL-72B-Instruct. Qwen2-VL-72B-Instruct is $0.80 / $1.00 per million input/output tokens versus Sarvam-30B at $0.30 / $0.30. Sources: https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct and https://www.sarvam.ai/
Sources: OpenRouter pricing (https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct); Sarvam AI pricing (https://www.sarvam.ai/)
Qwen2-VL-72B-Instruct
Qwen
Input
$0.80
Output
$1.00
Sarvam-30B
Sarvam AI
Input
$0.30
Output
$0.30
Token pricing, specs, and benchmarks side by side
Qwen2-VL-72B-InstructSarvam-30BVerdict
Both models are closely matched on benchmarks. Sarvam-30B has the pricing advantage, making it the better value unless Qwen2-VL-72B-Instruct's specific capabilities are critical to your workflow.
As of August 30, 2026, Sarvam-30B is 67% cheaper on blended LLM API pricing. Sarvam-30B costs $0.30 per million input tokens and $0.30 per million output tokens ($0.60 blended 1M-in + 1M-out). Qwen2-VL-72B-Instruct costs $0.80 / $1.00 per million tokens ($1.80 blended). Sources: https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct and https://www.sarvam.ai/. The cheapest LLM for your app still depends on how many output tokens you generate.
Qwen2-VL-72B-Instruct OpenRouter API pricing is $0.80 input and $1.00 output per million tokens via OpenRouter. Sarvam-30B Sarvam AI API pricing is $0.30 input and $0.30 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-30B has a published SWE-bench Verified score of 34%. Qwen2-VL-72B-Instruct does not have that eval on this page yet.
Qwen2-VL-72B-Instruct supports a 131K token context window, while Sarvam-30B supports 33K tokens. Qwen2-VL-72B-Instruct 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.
Shared benchmark scores for Qwen2-VL-72B-Instruct and Sarvam-30B are still limited. Check the comparison table for the evals each model has published. 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 Qwen2-VL-72B-Instruct and Sarvam-30B are production API models. For cost-sensitive production traffic, Sarvam-30B 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 Qwen2-VL-72B-Instruct through OpenRouter and Sarvam-30B 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 OpenRouter API pricing and Sarvam AI API pricing, quoted per million tokens. Official rate sheets: https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct 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.
Qwen2-VL-72B-Instruct supports up to an unspecified number of output tokens per request, while Sarvam-30B 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.
Neither Qwen2-VL-72B-Instruct nor Sarvam-30B has published throughput data on this page yet. 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 Qwen2-VL-72B-Instruct or Sarvam-30B 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. Qwen2-VL-72B-Instruct costs $0.80/M input and $1.00/M output via OpenRouter. Sarvam-30B costs $0.30/M input and $0.30/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.
