Cross-model context mobility for heterogeneous agent systems

UnimAI is building a cross-model context and computation layer. Instead of rebuilding the full prompt cache for each model, Relay transfers reusable computational state into the target model's representation space, verifies the reuse boundary, and recomputes only what quality requires.

Share the reusable core. Recompute only the delta.

Both agents receive the same prompt, but only the source performs the full prefill. Relay maps that state into the target's space, and the target resumes from it — selectively recomputing only what is needed to meet the configured quality threshold.

Model Acomputes the task state oncefull prefill — paid onceRelaytranslateverifyfall backModel Bresumes from translated statereused + delta recomputed138 ms · 96.2% quality retained
What today's systems do
Prefix and KV caching in engines like vLLM, SGLang, and LMCache reuse computed state when the same model sees the same prefix again. Reuse is a lookup inside one model's representation space.
Where they stop
A handoff to a different model has no shared representation — different tokenizer, different attention geometry, different hidden dimensions. There is nothing to look up, so the target model performs a full prefill of the whole history.
What Relay adds
Relay maps state between representation spaces, checks the result against a quality threshold, and recomputes only the delta that check demands — falling back to full prefill when a model pair cannot clear the bar.

Prototype benchmarks

Increasing difficulty: scale transfer, then bidirectional transfer, then cross-family translation.

Llama 3.1-70B → Qwen 2.5-7B

Cross family

MethodAccuracyLatency
Llama 70B native44.0%7,328 ms
Qwen 7B native45.7%899 ms
UnimAI KV sharing44.0%138 ms
  • 96% of native accuracy
  • 6.5× faster than Qwen 7B
  • Up to 53× faster than Llama 70B

Qwen 2.5-7B → Qwen 2.5-1.5B

Same family

MethodAccuracyLatency
7B native45.7%899 ms
1.5B native27.6%288 ms
UnimAI KV sharing34.5%53.8 ms
  • +6.9 accuracy points over native 1.5B
  • 5.4× faster than native 1.5B
  • 16.7× faster than 7B

LongBench2 · 116 samples · 16K–32K prompts. Handoff latency covers translation, transfer, assembly, and first-token decoding — it is not standard end-to-end TTFT. The cross-family experiment transfers Llama 3.1-70B KV state into a frozen Qwen 2.5-7B target; the same-family experiment transfers Qwen 2.5-7B state into a frozen Qwen 2.5-1.5B target.

Complex tasks need a team, not one costly model

Decompose the workflow, route each subtask to the best-fit model, and pay premium inference cost only where it adds value.

Reasoning model

$$$

Plan, decide, resolve ambiguity — invoked selectively.

Small + fast model

$

Search, extract, summarize — routine volume stays inexpensive.

Specialist / private model

$$

Code, vision, domain, sensitive data — preserves control.

Best-fit routing buys stronger performance at lower blended cost — and creates a new bottleneck: context must move efficiently across models.

One platform, three ways to adopt it

Relay powers every offering: deployments validate it, and the API scales proven workflows.

License it

UnimAI Relay

Cross-model KV runtime

For inference providers and self-hosted enterprises

Translate · Verify · Fall back

Deploy it

Agent Systems

Production multi-agent workflows

For AI-native and enterprise teams

Plan · Route · Remember · Evaluate

Call it

Managed API

Quality-targeted outcomes

For developers and smaller teams

Cost · Latency · Privacy controls

Become a design partner