LLM Reference

Hunyuan Hy3 Preview vs Sarvam 30B

Hunyuan Hy3 Preview (2026) and Sarvam 30B (2026) are frontier reasoning models from Tencent AI Lab and Sarvam.ai. Hunyuan Hy3 Preview ships a 262k-token context window, while Sarvam 30B ships a 66k-token context window. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads. It focuses on practical selection signals rather than broad model-family marketing.

Hunyuan Hy3 Preview fits 4x more tokens; pick it for long-context work and Sarvam 30B for tighter calls.

Decision scorecard

Local evidence first
SignalHunyuan Hy3 PreviewSarvam 30B
Best forreasoning-heavy apps, tool-calling agents, and provider-routed productiontool-calling agents
Decision fitCoding, RAG, and AgentsAgents and JSON / Tool use
Context window262k66k
Cheapest output$0.26/1M tokens-
Provider routes2 tracked0 tracked
Shared benchmarks0 rows0 rows

Decision tradeoffs

Choose Hunyuan Hy3 Preview when...
  • Hunyuan Hy3 Preview has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Hunyuan Hy3 Preview has broader tracked provider coverage for fallback and procurement flexibility.
  • Hunyuan Hy3 Preview uniquely exposes Reasoning in local model data.
  • Local decision data tags Hunyuan Hy3 Preview for Coding, RAG, and Agents.
Choose Sarvam 30B when...
  • Local decision data tags Sarvam 30B for Agents and JSON / Tool use.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Hunyuan Hy3 Preview

$118

Cheapest tracked route/tier: OpenRouter

Sarvam 30B

Unavailable

No complete token price in local provider data

Cost delta unavailable until both models have sourced input and output token prices.

Switch friction

Hunyuan Hy3 Preview -> Sarvam 30B
  • No overlapping tracked provider route is sourced for Hunyuan Hy3 Preview and Sarvam 30B; plan for SDK, billing, or endpoint changes.
  • Check replacement coverage for Reasoning before moving production traffic.
Sarvam 30B -> Hunyuan Hy3 Preview
  • No overlapping tracked provider route is sourced for Sarvam 30B and Hunyuan Hy3 Preview; plan for SDK, billing, or endpoint changes.
  • Hunyuan Hy3 Preview adds Reasoning in local capability data.

Specs

Specification
Released2026-04-222026-03-22
Context window262k66k
Parameters295B30B (2.4B active)
Architecturedense moe hybridmoe
LicenseTencent Hunyuan Community LicenseApache 2.0(OSI)
OpennessOpen weightsOpen source
Commercial useCommercial use with conditionsCommercial use allowed
Knowledge cutoff-2025-06

Pricing and availability

Pricing attributeHunyuan Hy3 PreviewSarvam 30B
Input price$0.07/1M tokens-
Output price$0.26/1M tokens-
Providers-

Capabilities

CapabilityHunyuan Hy3 PreviewSarvam 30B
VisionNoNo
MultimodalNoNo
ReasoningYesNo
Function callingYesYes
Tool useYesYes
Structured outputsNoNo
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark rows are currently sourced for this pair.

Deep dive

The capability footprint differs most on reasoning mode: Hunyuan Hy3 Preview. Both models share function calling and tool use, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.

Pricing coverage is uneven: Hunyuan Hy3 Preview has $0.07/1M input tokens and Sarvam 30B has no token price sourced yet. Provider availability is 2 tracked routes versus 0. Treat unknown pricing as an integration gap, then verify the route you will actually call before estimating production spend.

Choose Hunyuan Hy3 Preview when reasoning depth, larger context windows, and broader provider choice are central to the workload. Choose Sarvam 30B when provider fit are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions. It also helps separate model capability from provider packaging, which can change cost and latency. For teams standardizing a stack, that distinction is often the difference between a benchmark win and a reliable deployment.

FAQ

Which has a larger context window, Hunyuan Hy3 Preview or Sarvam 30B?

Hunyuan Hy3 Preview supports 262k tokens, while Sarvam 30B supports 66k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Is Hunyuan Hy3 Preview or Sarvam 30B open source?

Hunyuan Hy3 Preview is listed under Tencent Hunyuan Community License. Sarvam 30B is listed under Apache 2.0. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.

Which is better for reasoning mode, Hunyuan Hy3 Preview or Sarvam 30B?

Hunyuan Hy3 Preview has the clearer documented reasoning mode signal in this comparison. If reasoning mode is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.

Which is better for function calling, Hunyuan Hy3 Preview or Sarvam 30B?

Both Hunyuan Hy3 Preview and Sarvam 30B expose function calling. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Which is better for tool use, Hunyuan Hy3 Preview or Sarvam 30B?

Both Hunyuan Hy3 Preview and Sarvam 30B expose tool use. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Where can I run Hunyuan Hy3 Preview and Sarvam 30B?

Hunyuan Hy3 Preview is available on OpenRouter and Tencent Cloud TI Platform. Sarvam 30B is available on the tracked providers still being sourced. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

Continue comparing

Last reviewed: 2026-06-07. Data sourced from public model cards and provider documentation.