# Exa launches Agent Ultra, a high-compute deep-research API tier

> Exa released Agent Ultra, a new maximum-effort tier of its Agent API for exhaustive list building and entity enrichment, claiming it beats Opus 5.5, GPT-6 Astra, and Perplexity Agent at max effort on four research benchmarks — vendor-run, 6

- **Topic**: Models
- **Published**: 2026-09-27T08:37:05.448Z
- **Canonical URL**: https://highsignal.sh/stories/exa-launches-agent-ultra-a-high-compute-deep-research-api-tier-6de3bade

## Why It Matters

Exa is selling exhaustive, citation-backed research as a metered API rather than an open model. Its pitch is cost-per-task, not raw accuracy — the benchmarks come from Exa's own harness, so the efficiency claims are the part most in need of outside verification.

## Key Findings & Analysis

### What Exa released

Exa launched Agent Ultra, the highest effort tier of its Exa Agent API, aimed at research that must run to exhaustion: large list building, entity enrichment, and questions needing thousands of sources. Agent splits a task into subtasks, assigning subagents to research several domains at once and routing frontier models to steps that need them and faster models elsewhere; Ultra is the mode that spends the most compute. Exa says Ultra typically finishes complex tasks in about 30 minutes, with very hard tasks taking up to 3 hours.

### Availability and pricing

Agent Ultra is live today on the Exa API by setting effort: 'ultra', and is also reachable through OpenAI compatibility mode on /responses. It is hosted-only: not open weights, not self-hostable. It uses the standard Agent run endpoint, supporting outputSchema, input.data, and streaming. Pricing is metered at standard Agent usage rates, up to a default $20 per run, with early finishes costing less. Budget controls include maxCostDollars ($1–$100) and maxDurationSeconds (300–10,800). A stop call ends a run early, keeps its results, and bills usage to that point; SDK polling helpers time out after 1 hour by default.

### Benchmarks — vendor-reported, not independently reproduced

All figures come from Exa's launch post, with competitors run at their maximum effort setting, and none have been independently reproduced. Per Exa: WANDR soft recall 81.4% vs Opus 5.5 at 72.3%, GPT-6 Astra at 26.0%, and Perplexity Agent at 40.1%. DeepSearchQA F1 93.9% vs 77.6%, 85.3%, and 89.7%. WideSearch row-level F1 58.9% vs 51.6%, 54.7%, and 56.0%. Company Find-All averaged 2,451 passing entities per task vs 146, 113, and 98. Exa pairs each with a cost claim: on WANDR, a 12.6% gain over Opus 5.5 at half its cost per task; on DeepSearchQA, 4.7% over Perplexity at 46% lower cost per task than GPT-6 Astra; on WideSearch, 5.2% over Perplexity at the lowest cost per task of the four; on Company Find-All, 1,579% over Opus 5.5 at the lowest cost per entity. These gains are relative, not percentage points. On WANDR the absolute gap to Opus 5.5 is 9.1 points.

### How the numbers were produced

WANDR is Perplexity's benchmark of 500 wide and deep data-collection tasks with an open harness. Exa's grader shares the upstream evaluation logic but swaps in Exa as the contents tool, changes transport logic, and uses gpt-6-luna as the judge. Where a vendor published a result on that harness, Exa reports that figure; otherwise Exa ran the benchmark itself. DeepSearchQA is Google DeepMind's 900-prompt multi-step search benchmark, and WideSearch tests broad information gathering. Exa evaluated up to 200 tasks each for WANDR and DeepSearchQA and 100 each for WideSearch and Company Find-All, with graded task counts varying by provider.

### Who it's for

Exa names three target groups. Model providers assembling training data — every paper and repo implementing a technique, verifying criteria like 'released weights, not just an API'. Financial services building diligence market maps, running KYC research across filings and court records, and monitoring portfolio signals. And go-to-market teams building account lists and enriching rows with judgment fields, each backed by a cited URL. Ultra can also expand an existing list: pass the rows you already have and they are excluded from new results. What Agent Ultra does not address is the gap between Exa's self-run benchmarks and independent reproduction, and the absence of open weights means no outside inspection of the system itself.

## Primary Sources & Citations

- [Exa Launches Agent Ultra: A Subagent Swarm Deep Research API Built for Exhaustive List Building](https://www.marktechpost.com/2026/09/26/exa-launches-agent-ultra-a-subagent-swarm-deep-research-api-built-for-exhaustive-list-building/) — *MarkTechPost* (Reporting)

---

[← Back to Headlines](https://highsignal.sh/) | [Daily Brief](https://highsignal.sh/brief) | [All stories](https://highsignal.sh/latest)