Best AI model for agents: how to choose

There is no single best AI model for agents; it depends on budget, input size and whether you need to self-host. Highest of these on the official Terminal-Bench 4.0 board: Claude Opus 5.5. Lowest listed price: Mercury 3. Largest context window: GPT-6.1 Terra. Open weights: MiniMax M3.1 Flash. Every pick follows one stated fact, linked to its source. We have not run these models.

Reported Updated · Markdown · All models

Share on X

Pick by what limits you

Highest of these on the official Terminal-Bench 4.0 board

Claude Opus 5.5

64.8% on the official Terminal-Bench 4.0 board (snapshot Oct 26, 2026), the highest of the agent models in our data that appear on it. Independent board, not our test. Source

Lowest listed price

Mercury 3

$0.1 in / $0.35 out per 1M tokens (temporary price), the lowest of the generally available agent models listed here. Source

Largest context window

GPT-6.1 Terra

1,050,000 tokens, the largest published among the generally available agent models here (tied; newest shown). Source

Open weights

MiniMax M3.1 Flash

Newest generally available agent model here with downloadable weights (MiniMax Community License); $0.15 in / $0.6 out per 1M tokens on the vendor API. Source

Each pick follows one stated rule over our sourced data, so it moves when the data does. This is a way to choose, not a quality ranking: we have not run these models.

All models in scope (29)

Language models in our data released in the 120 days before Oct 29, 2026 that their vendors position for long-running, tool-using work. Our data is not every model on the market.

Best AI model for agents: how to choose: models in scope with sourced facts
ModelPrice (listed)ContextLicenceInputReleasedStatus
Gemini 4 CarbonGoogle$2 in / $10 out per 1M tokens (introductory price, end date not stated; list $4 / $20)sourceNot publishedProprietarysourceNot publishedOct 28, 2026sourceLimited access
GPT-6.1 TerraOpenAI$1 in / $5 out per 1M tokenssource1.05M tokenssourceProprietary (API)sourcetext, imagesourceOct 26, 2026sourceGenerally available
Kimi K3.1 ProMoonshot AI$2 in / $10 out per 1M tokenssource1.05M tokenssourceNot yet publishedsourceNot publishedOct 23, 2026sourceGenerally available
Kimi K3.1 Pro HighspeedMoonshot AI$4 in / $20 out per 1M tokenssource1.05M tokenssourceNot publishedNot publishedOct 23, 2026sourceGenerally available
Mercury 3Inception$0.1 in / $0.35 out per 1M tokens (launch promo, end date not stated; list $0.2 / $0.7)source1M tokenssourceProprietary (API)sourceNot publishedOct 19, 2026sourceGenerally available
MiniMax M3.1 FlashMiniMax$0.15 in / $0.6 out per 1M tokenssource1M tokenssourceMiniMax Community Licensesourcetext, image, videosourceOct 19, 2026sourceGenerally available
Gemini 4 ArgonGoogle$2 in / $10 out per 1M tokens (introductory price until Nov 30, 2026; list $4 / $20)source1.05M tokenssourceProprietary (API)sourcetext, image, video, audio, pdfsourceOct 13, 2026sourceGenerally available
Muse WonderMeta$4 in / $20 out per 1M tokenssource1.05M tokenssourceProprietary (API)sourcetext, image, video, audio, pdfsourceOct 12, 2026sourcePublic preview
Muse Wonder FullMetaNot publishedNot publishedProprietary (subscription)sourceNot publishedOct 12, 2026sourceLimited access
Claude Haiku 5.5Anthropic$0.1 in / $0.5 out per 1M tokenssource1M tokenssourceProprietary (API)sourcetext, imagesourceOct 7, 2026sourceGenerally available
GPT-6.1 SolOpenAI$2 in / $10 out per 1M tokenssource1.05M tokenssourceProprietary (API)sourcetext, imagesourceSep 29, 2026sourceGenerally available
Claude Sonnet 5.5Anthropic$2 in / $10 out per 1M tokenssource1M tokenssourceProprietary (API)sourcetext, imagesourceSep 28, 2026sourceGenerally available
Claude Opus 5.5Anthropic$4 in / $20 out per 1M tokenssource1M tokenssourceProprietary (API)sourcetext, imagesourceSep 22, 2026sourceGenerally available
GPT-6 SolOpenAI$2 in / $10 out per 1M tokenssourceNot publishedProprietary (API)sourcetext, imagesourceSep 22, 2026sourceGenerally available
Grok 4.7xAI$2 in / $6 out per 1M tokenssource500K tokenssourceProprietary (API)sourcetext, imagesourceSep 21, 2026sourceGenerally available
Claude Fable 5.1Anthropic$10 in / $50 out per 1M tokenssource1M tokenssourceProprietary (API)sourcetext, imagesourceSep 15, 2026sourceGenerally available
GPT-6 AstraOpenAI$10 in / $50 out per 1M tokenssource1.05M tokenssourceProprietary (API)sourcetext, imagesourceSep 3, 2026sourceGenerally available
Gemini 3.8 FlashGoogle$0.75 in / $3.75 out per 1M tokens (temporary price until Dec 31, 2026; list $1.5 / $7.5)source1.05M tokenssourceProprietary (API)sourcetext, image, video, audio, pdfsourceSep 2, 2026sourceGenerally available
Claude Mythos 5.1Anthropic$10 in / $50 out per 1M tokenssource1M tokenssourceProprietary (API)sourceNot publishedSep 1, 2026sourceLimited access
GLM-5.3-FlashZ.aiNot publishedNot publishedNot publishedNot publishedAug 26, 2026sourceGenerally available
GLM-5.3Z.ai$1.4 in / $4.4 out per 1M tokenssource1.05M tokenssourceGLM-5.3 License (MIT-style plus a MaaS condition)sourceNot publishedAug 14, 2026sourceGenerally available
Grok 4.6xAI$2 in / $6 out per 1M tokenssource500K tokenssourceProprietary (API)sourcetext, imagesourceAug 12, 2026sourceGenerally available
Gemini Robotics ER 2GoogleNot publishedNot publishedProprietary (API)sourceNot publishedJul 30, 2026sourcePublic preview
Claude Opus 5Anthropic$5 in / $25 out per 1M tokenssource1M tokenssourceProprietary (API)sourceNot publishedJul 24, 2026sourceGenerally available
Gemini 3.5 Flash-LiteGoogleNot published1.05M tokenssourceProprietary (API)sourcetext, image, video, audio, pdfsourceJul 21, 2026sourceGenerally available
Gemini 3.6 FlashGoogleNot published1.05M tokenssourceProprietary (API)sourcetext, image, video, audio, pdfsourceJul 21, 2026sourceGenerally available
Kimi K3Moonshot AI$3 in / $15 out per 1M tokenssource1M tokenssourceKimi K3 License (custom)sourceNot publishedJul 16, 2026sourceGenerally available
GPT-5.6 SolOpenAI$4 in / $20 out per 1M tokens (promotional price, OpenAI says it is available at least through Nov 21, 2026; list price after the promo not stated)source1.05M tokenssourceProprietary (API)sourcetext, imagesourceJul 9, 2026sourceGenerally available
Grok 4.5xAI$2 in / $6 out per 1M tokenssource500K tokenssourceProprietary (API)sourcetext, imagesourceJul 8, 2026sourceGenerally available

FAQ

What is the best AI model for agents right now?

It depends on what limits you. Highest of these on the official Terminal-Bench 4.0 board: Claude Opus 5.5. Lowest listed price: Mercury 3. Largest context window: GPT-6.1 Terra. Open weights: MiniMax M3.1 Flash. Each pick names the fact behind it and links to the source.

Which agent model is cheapest?

Mercury 3: $0.1 in / $0.35 out per 1M tokens (temporary price). Next: Claude Haiku 5.5 ($0.1 in / $0.5 out per 1M tokens); MiniMax M3.1 Flash ($0.15 in / $0.6 out per 1M tokens).

Is there an open-weight model for agents?

Yes: MiniMax M3.1 Flash (MiniMax Community License), GLM-5.3 (GLM-5.3 License (MIT-style plus a MaaS condition)), Kimi K3 (Kimi K3 License (custom)).

Did you test these models as agents?

No. This page is Reported. Prices, context windows and licences come from the vendor pages linked in the table; the Terminal-Bench 4.0 score comes from the official board, not from us.

Related

The Weekly Verdict · free

5 new-model use cases. Every Monday.

A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.

Free. Double opt-in. One click to unsubscribe.