--- title: "Sarvam 105B API: facts and benchmarks | Kendr" canonical: "https://kendr.org/models/kc-sarvam-105b" date_modified: "2026-08-12" profile_kind: "hosted" --- # Sarvam 105B API model profile Sarvam 105B is Sarvam AI's 128K-context native model for reasoning, coding, structured output, and tool-driven agentic workflows across Indian-language use cases. Sarvam 105B is available under the Kendr alias kc-sarvam-105b. Current account availability and customer credit quotes come from Kendr's live public model API and applicable account policy. Sarvam 105B accepts text and returns text. The snapshot records agentic, coding, reasoning, structured output, text generation, tool calling, and tools as capabilities or interfaces. The dated reference snapshot lists $29.28 input and $73.2 output per million tokens. Cached input is $10.98 per million tokens. The separately published provider-route reference is ₹29.28 / ₹73.20 (INR per 1M tokens; cached input ₹10.98/M. No USD rate is inferred.). No comparable third-party benchmark value is present in the 2026-08-14 snapshot. Missing values are not estimated. No comparable popularity rank or traffic share is present in the 2026-08-14 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated. Profile data was reviewed for the 2026-08-12 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated. ## Profile facts - **Profile type:** Kendr API model - **Kendr API alias:** kc-sarvam-105b - **Model developer:** Sarvam AI - **Kendr route provider:** Sarvam AI - **Context window:** 128K - **Snapshot date:** 2026-08-12 - **Reference catalog ID:** sarvam/sarvam-105b ## Context, modalities, and identity Sarvam 105B accepts text and returns text. The snapshot records agentic, coding, reasoning, structured output, text generation, tool calling, and tools as capabilities or interfaces. - **Model developer:** Sarvam AI - **Kendr route provider:** Sarvam AI - **Context window:** 128K - **Maximum output:** Sarvam documents plan-dependent output limits: 4,096 tokens on Starter, 16,384 on Pro, and up to 128,000 on Business. - **Input modalities:** text - **Output modalities:** text - **Knowledge cutoff:** Not disclosed ## Capabilities and supported controls Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route. - **Supported parameters:** max_tokens, reasoning_effort, response_format, stream, temperature, tool_choice, tools, top_p - agentic - coding - reasoning - structured output - text generation - tool calling - tools ## Dated pricing snapshot The dated reference snapshot lists $29.28 input and $73.2 output per million tokens. Cached input is $10.98 per million tokens. The separately published provider-route reference is ₹29.28 / ₹73.20 (INR per 1M tokens; cached input ₹10.98/M. No USD rate is inferred.). Reference figures are dated 2026-08-14; the live Kendr quote can differ by selected provider route, context tier, caching, tools, region, and current rate card. - **Price date:** 2026-08-14 - **Input:** $29.28 per 1M tokens - **Cached input:** $10.98 per 1M tokens - **Output:** $73.2 per 1M tokens ## Benchmark evidence and limitations No comparable third-party benchmark value is present in the 2026-08-14 snapshot. Missing values are not estimated. No independent benchmark values are published here; capabilities follow Sarvam's official model documentation. ## Popularity and market context No comparable popularity rank or traffic share is present in the 2026-08-14 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated. - **Third-party catalog rank:** No verified rank - **Global market share:** Not inferred - **Observation date:** 2026-08-14 ## OpenAI-compatible API example ```bash curl https://api.kendr.org/v1/chat/completions \ -H "Authorization: Bearer $KENDR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"kc-sarvam-105b","messages":[{"role":"user","content":"Hello"}]}' ``` ## Frequently asked questions ### What is Sarvam 105B? Sarvam 105B is Sarvam AI's 128K-context native model for reasoning, coding, structured output, and tool-driven agentic workflows across Indian-language use cases. ### What context window does Sarvam 105B have? The dated profile lists 128K of context. Provider routes, variants, and runtime configuration can impose lower effective limits. ### What benchmark evidence is available for Sarvam 105B? No comparable third-party benchmark value is present in the 2026-08-14 snapshot. Missing values are not estimated. No independent benchmark values are published here; capabilities follow Sarvam's official model documentation. ### What is the Kendr API alias for Sarvam 105B? Use kc-sarvam-105b as the model value. The live public model API and signed-in catalog remain authoritative for route availability and customer credit quotes. ### How is Sarvam 105B priced on Kendr? The dated reference snapshot lists $29.28 input and $73.2 output per million tokens. Cached input is $10.98 per million tokens. The separately published provider-route reference is ₹29.28 / ₹73.20 (INR per 1M tokens; cached input ₹10.98/M. No USD rate is inferred.). Kendr applies one 5% markup to configured provider model cost; the live quote and settled routing receipt are authoritative for a request. ## Sources and evidence dates - [Sarvam 105B official model documentation](https://docs.sarvam.ai/api/getting-started/models/sarvam-105b) — primary, checked 2026-08-14 - [Sarvam AI official pricing](https://docs.sarvam.ai/api/getting-started/pricing) — primary, checked 2026-08-14 - [Sarvam AI Chat Completions API](https://docs.sarvam.ai/api-reference/chat/chat-completions) — primary, checked 2026-08-14 Live Kendr operational availability is published separately at https://api.kendr.org/api/public/models.