Claude Haiku 5.5 is the best AI for cold emails for most teams. Outbound is a volume game, and Haiku 5.5 writes short, natural emails at $0.10/$0.50 per million tokens — a few cents per thousand drafts. Give it real research on each prospect (a recent post, a hiring signal, a product launch) and it will open with something specific instead of flattery. For senior targets and high-value accounts, Claude Sonnet 5.5 writes noticeably sharper personalisation.
The safest cold emails default, the cheaper option worth trying first, and the specialist pick — before you read the detail below.
Claude Haiku 5.5 is the strongest answer here for cold emails — pick it when quality of output matters more than the $0.10/1M/1M input you pay for it.
Claude Sonnet 5.5 is the cheaper way in for cold emails, at $2.00/1M/1M input against Claude Haiku 5.5's $0.10/1M/1M.
GPT-6 Luna is the fastest of these for cold emails — worth it when latency is what the reader notices, not the last few points of reasoning depth.
Claude Haiku 5.5 is the best model for fast, cheap outbound at scale.
Claude Sonnet 5.5 is worth it for senior targets and high-value accounts.
Personalisation quality depends far more on the research you feed in than on the model.
Use Claude Haiku 5.5 for daily outbound volume and subject-line testing.
Use Claude Sonnet 5.5 for executive outreach and nuanced, high-stakes messaging.
Use GPT-6 Luna as a like-for-like alternative at the same price if your stack runs on OpenAI.
Switch the scoring lens to see whether the cold emails answer changes when cost, speed, or long-document depth leads the decision.
Anthropic / Balanced / Oct 10, 2026
Near-Opus 5.5 quality on scoped work at half the price.
Ranks models by the broadest mix of coding, writing, research, and long-context usefulness.
The work is long, ambiguous and multi-step — Anthropic positions Opus 5.5 for exactly that — or you need the lowest possible price, where Haiku 5.5 costs a twentieth as much.
Where the cold emails recommendation shifts once you weigh price or latency differently.
Anthropic's budget model, now with adjustable reasoning, at $0.10/$0.50.
Near-Opus 5.5 quality on scoped work at half the price.
OpenAI's budget tier at half the old price.
List prices and published scores — the numbers this page's pick is built from.
| Model | Input | Output | Est. month | Context | Speed | Coding | Writing | Research |
|---|---|---|---|---|---|---|---|---|
| Claude Haiku 5.5Anthropic | $0.10/1M | $0.50/1M | $2.00 | 1M tokens | Very fast | 86 | 84 | 82 |
| Claude Sonnet 5.5Anthropic | $2.00/1M | $10.00/1M | $40 | 1M tokens | Fast | 98 | 98 | 95 |
| GPT-6 LunaOpenAI | $0.10/1M | $0.50/1M | $2.00 | 1.1M tokens | Very fast | 84 | 82 | 80 |
Scores out of 100 — how we evaluate models. “Est. month” is 10M in / 2M out at list price: a ceiling, no discounts.
Why each one is on the shortlist for cold emails, what it is genuinely good at, and where we would steer you away from it.
Ranked first here for cold emails: 86/100 on coding, with the widest margin of anything in this line-up.
Anthropic's October 7, 2026 low-cost model and the first Haiku with adjustable reasoning effort — thinking can be switched off for simple requests or raised to max, at $0.10/$0.50 per 1M under 100K input tokens.
Your prompts routinely exceed 100K tokens, where the price quintuples, or the task needs sustained reasoning that Sonnet 5.5 handles far better.
The cheapest way to put an Anthropic model in a high-volume pipeline. Keep requests under 100K tokens to stay on the low rate, and set effort per task — at low effort it is a fast classifier, at max it handles real tool-use work.
Full pricing, benchmark table and release notes on the Claude Haiku 5.5 page.
Where most budgets should land for cold emails — balanced-tier pricing, and still 98/100 on the coding axis.
Anthropic's September 28, 2026 Sonnet — built for well-scoped everyday work like features, bug fixes, documents, slides and spreadsheets, priced at $2/$10 and close to Opus 5.5 on most of Anthropic's launch rows.
The work is long, ambiguous and multi-step — Anthropic positions Opus 5.5 for exactly that — or you need the lowest possible price, where Haiku 5.5 costs a twentieth as much.
The model most people should default to in the Claude lineup. Sonnet 5.5 lands within a few points of Opus 5.5 on most of Anthropic's launch rows, beats it on Terminal-Bench 4.0, and costs half as much. Step up to Opus 5.5 only when the task is open-ended and long.
Full pricing, benchmark table and release notes on the Claude Sonnet 5.5 page.
The fastest model in this shortlist for cold emails. Pick it when turnaround is what your readers or users notice.
OpenAI's budget tier at half the old price. Full GPT-6 Luna review →
UseRightAI recommendations are based on practical decision factors people actually feel in day-to-day use.
Newsletter
We email when the cold emails pick changes, when one of these models moves on price, or when something new displaces the current leader.
No spam. Useful updates only. Affiliate disclosures always clearly labeled.
For cold emails, Claude Haiku 5.5 (Anthropic) is our pick. Anthropic's budget model, now with adjustable reasoning, at $0.10/$0.50. It costs $0.1/1M input and $0.5/1M output tokens, with a 1M-token context window — enough headroom for all but the largest cold emails jobs. Claude Sonnet 5.5 is the closest alternative if it doesn't fit your setup.
Because the work it is built for overlaps closely with cold emails: sub-agents in a larger agent system, where dozens of cheap calls replace one expensive one and classification, extraction and routing at volume with thinking turned off. The cheapest way to put an Anthropic model in a high-volume pipeline. Keep requests under 100K tokens to stay on the low rate, and set effort per task — at low effort it is a fast classifier, at max it handles real tool-use work.
On a moderate month — 10M input and 2M output tokens — Claude Haiku 5.5 runs about $2.00 at list price, with no batch or caching discounts applied, so treat that as a ceiling. It is also the cheapest option among the models compared here, so for cold emails there is no cost argument for dropping to something weaker.
Long prompts cost five times more: above 100K input tokens the rate becomes $0.50/$2.50. Effort matters a great deal: Terminal-Bench 4.0 is 12.8% at low effort against 39.2% at max. Avoid it if your prompts routinely exceed 100K tokens, where the price quintuples, or the task needs sustained reasoning that Sonnet 5.5 handles far better. None of that rules it out for cold emails on its own — but if one of those limits maps onto how you actually work, take the alternative on this page seriously rather than defaulting to the top pick.