# Compare India inference performance: TPS, TTFT, cost [Directory Indian Inference](/india/) [Overview](/india/)[Models](/india/models/)[Compare prices](/india/models/compare/)[Performance](/india/compare/)[Guide](/india/inference-guide/) [Directories](/directories/) › [Indian Inference](/india/) › Performance Compare India inference performance We tested the same Indian models on JarvisLabs, Sarvam AI, and E2E Networks Blaze. These are single-stream probes with recorded prompts and sample sizes, not vendor speed claims. TTFT, end-to-end TPS, fixed-workload cost, and reliability stay separate. 3 providers 21 model tests 7 to 8 November 2026 Single stream Fastest TPS **654.6** Sarvam AI · Sarvam 105B ConversationsMay be chunk-batched. Best value **34.5** E2E Networks Blaze · GLM 5.3 Flash · TPS per ₹ Fastest first answer **114ms** Sarvam AI · Gemma 4 31B Reliability **90.5%** 228/252 tool calls · 99.2% structured Provider summary ## Who is fast, who is cheap, who is reliable. Each provider is judged on the models it actually serves. E2E does not offer GLM 5.3, so that model is not used for the three-provider comparison. Provider Models Fastest model TPS Best value TPS per ₹ First answer Reliability [JarvisLabs](/india/providers/jarvislabs/) 8 Nemotron 3.5 Super VL 120B **365.5** DeepSeek V4.1 Flash **18.1** DeepSeek V4.1 Flash Cyber · 323 ms 96/96 tools · 96/96 structured [Sarvam AI](/india/providers/sarvam-ai/) 6 Sarvam 105B Conversations **654.6** GLM 5.3 Flash **7.9** Gemma 4 31B · 114 ms 72/72 tools · 72/72 structured [E2E Networks Blaze](/india/providers/e2e-networks/) 7 GLM 5.3 Flash **459** GLM 5.3 Flash **34.5** Gemma 4 26B A4B · 115 ms 60/84 tools · 82/84 structured [JarvisLabs](/india/providers/jarvislabs/) 8 models Fastest Nemotron 3.5 Super VL 120B TPS 365.5 Best value DeepSeek V4.1 Flash TPS per ₹ 18.1 First answer DeepSeek V4.1 Flash Cyber · 323 ms Reliability 96/96 tools · 96/96 structured [Sarvam AI](/india/providers/sarvam-ai/) 6 models Fastest Sarvam 105B Conversations TPS 654.6 Best value GLM 5.3 Flash TPS per ₹ 7.9 First answer Gemma 4 31B · 114 ms Reliability 72/72 tools · 72/72 structured [E2E Networks Blaze](/india/providers/e2e-networks/) 7 models Fastest GLM 5.3 Flash TPS 459 Best value GLM 5.3 Flash TPS per ₹ 34.5 First answer Gemma 4 26B A4B · 115 ms Reliability 60/84 tools · 82/84 structured Throughput and latency ## The same model behaves differently on each provider. TPS p50 is end-to-end completion tokens divided by total request time. TTFT p50 is the first token, which can include reasoning before any answer text. [![TPS and TTFT for DeepSeek V4.1 Flash, GLM 5.3 Flash, Gemma 4 31B, and GLM 5.3 across JarvisLabs, Sarvam AI, and E2E Networks Blaze](/images/charts/india-performance-tps-ttft.webp)](/images/charts/india-performance-tps-ttft.webp) **TPS and TTFT.** JarvisLabs is rust, Sarvam is teal, E2E Networks Blaze is blue. E2E does not offer GLM 5.3. [Open full chart ↗](/images/charts/india-performance-tps-ttft.webp) Speed and cost ## Faster is not always better value. Cost is 1M input tokens plus 250K output tokens at list rates. The side table keeps TPS, cost, and TPS per ₹ visible together. [![TPS versus fixed-workload cost for DeepSeek V4.1 Flash, GLM 5.3 Flash, and Gemma 4 31B on JarvisLabs, Sarvam AI, and E2E Networks Blaze](/images/charts/india-performance-tps-cost.webp)](/images/charts/india-performance-tps-cost.webp) **TPS vs cost.** Upper-left is better. E2E wins TPS per ₹ on DeepSeek and GLM 5.3 Flash. JarvisLabs wins Gemma 4 31B and GLM 5.3. [Open the full TPS vs cost table ↗](/images/charts/india-performance-cost-table.webp) Method ## What the numbers mean. These are repeatable probes, not a load test. The same prompt set and sample rules were used for each provider. Latency ### TTFT and first answer TTFT is the first non-empty streamed delta, including reasoning. First answer is the first content delta after reasoning. Short prompt is 287 to 313 input tokens. Long prompt is about 12K input tokens. Throughput ### End-to-end TPS TPS is completion tokens divided by total request time, including TTFT. Decode TPS excludes TTFT and is shown only as a secondary number. The decode prompt asks for the integers 1 to 100. Value ### Fixed workload cost Cost is 1M input tokens plus 250K output tokens at list rates, excluding GST and cache hits. TPS per ₹ divides end-to-end TPS by that fixed-workload cost. Reliability ### Tools and structured output Six tool cases and six JSON-schema cases, two samples each. Tool calls are checked for valid JSON, known tool names, and expected argument values. Structured output is checked against the schema. n=6 to 12 per cell. Single stream, 1.5 seconds between requests, default reasoning. No concurrency and no load testing. Sarvam 105B Conversations may be chunk-batched and is excluded from best-value picks. E2E Qwen3.5-9B has about 8K effective context on this route. Read next ## Pick the model, then pick the provider. Use the provider profiles for pricing, compliance, and model access. Use the India inference guide for the pricing and comparison method. [Compare model prices](/india/models/compare/) [Read the India guide](/india/inference-guide/)