# 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.

Updated: 2026-10-29 · Canonical: https://theagenticweekly.com/best/ai-model-for-agents · Evidence: Reported (not run by us)

## Picks, and the fact behind each

| Pick | Model | Why | Source |
|---|---|---|---|
| Highest of these on the official Terminal-Bench 4.0 board | [Claude Opus 5.5](https://theagenticweekly.com/models/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](https://www.tbench.ai/leaderboard/terminal-bench/4.0) |
| Lowest listed price | [Mercury 3](https://theagenticweekly.com/models/mercury-3) | $0.1 in / $0.35 out per 1M tokens (temporary price), the lowest of the generally available agent models listed here. | [source](https://www.inceptionlabs.ai/blog/introducing-mercury-3) |
| Largest context window | [GPT-6.1 Terra](https://theagenticweekly.com/models/gpt-6-1-terra) | 1,050,000 tokens, the largest published among the generally available agent models here (tied; newest shown). | [source](https://developers.openai.com/api/docs/models/gpt-6.1-terra) |
| Open weights | [MiniMax M3.1 Flash](https://theagenticweekly.com/models/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](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash/blob/main/LICENSE) |

## All models in scope

Language models in our data released in the 120 days before Oct 29, 2026 that their vendors position for long-running, tool-using work.

| Model | Vendor | Price (listed) | Context | Licence | Input | Released | Status |
|---|---|---|---|---|---|---|---|
| [Gemini 4 Carbon](https://theagenticweekly.com/models/gemini-4-carbon) | Google | $2 in / $10 out per 1M tokens (introductory price, end date not stated; list $4 / $20) ([source](https://deepmind.google/blog/gemini-4-carbon-our-next-frontier-model/)) | Not published | Proprietary ([source](https://deepmind.google/blog/gemini-4-carbon-our-next-frontier-model/)) | Not published | Oct 28, 2026 ([source](https://deepmind.google/blog/gemini-4-carbon-our-next-frontier-model/)) | Limited access |
| [GPT-6.1 Terra](https://theagenticweekly.com/models/gpt-6-1-terra) | OpenAI | $1 in / $5 out per 1M tokens ([source](https://developers.openai.com/api/docs/models/gpt-6.1-terra)) | 1.05M tokens ([source](https://developers.openai.com/api/docs/models/gpt-6.1-terra)) | Proprietary (API) ([source](https://developers.openai.com/api/docs/models/gpt-6.1-terra)) | text, image ([source](https://developers.openai.com/api/docs/models/gpt-6.1-terra)) | Oct 26, 2026 ([source](https://developers.openai.com/api/docs/changelog)) | Generally available |
| [Kimi K3.1 Pro](https://theagenticweekly.com/models/kimi-k3-1-pro) | Moonshot AI | $2 in / $10 out per 1M tokens ([source](https://www.kimi.ai/resources/kimi-k3-1-pro-pricing)) | 1.05M tokens ([source](https://www.kimi.ai/resources/kimi-k3-1-pro-pricing)) | Not yet published ([source](https://www.kimi.ai/blog/kimi-k3-1-pro)) | Not published | Oct 23, 2026 ([source](https://vercel.com/changelog/kimi-k3-1-pro-and-kimi-k3-1-pro-highspeed-are-available-now-in-ai-gateway)) | Generally available |
| [Kimi K3.1 Pro Highspeed](https://theagenticweekly.com/models/kimi-k3-1-pro-highspeed) | Moonshot AI | $4 in / $20 out per 1M tokens ([source](https://www.kimi.ai/resources/kimi-k3-1-pro-pricing)) | 1.05M tokens ([source](https://www.kimi.ai/resources/kimi-k3-1-pro-pricing)) | Not published | Not published | Oct 23, 2026 ([source](https://vercel.com/changelog/kimi-k3-1-pro-and-kimi-k3-1-pro-highspeed-are-available-now-in-ai-gateway)) | Generally available |
| [Mercury 3](https://theagenticweekly.com/models/mercury-3) | Inception | $0.1 in / $0.35 out per 1M tokens (launch promo, end date not stated; list $0.2 / $0.7) ([source](https://www.inceptionlabs.ai/blog/introducing-mercury-3)) | 1M tokens ([source](https://www.inceptionlabs.ai/blog/introducing-mercury-3)) | Proprietary (API) ([source](https://www.inceptionlabs.ai/blog/introducing-mercury-3)) | Not published | Oct 19, 2026 ([source](https://www.inceptionlabs.ai/blog/introducing-mercury-3)) | Generally available |
| [MiniMax M3.1 Flash](https://theagenticweekly.com/models/minimax-m3-1-flash) | MiniMax | $0.15 in / $0.6 out per 1M tokens ([source](https://www.minimax.io/blog/minimax-m31f)) | 1M tokens ([source](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash)) | MiniMax Community License ([source](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash/blob/main/LICENSE)) | text, image, video ([source](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash)) | Oct 19, 2026 ([source](https://www.minimax.io/blog/minimax-m31f)) | Generally available |
| [Gemini 4 Argon](https://theagenticweekly.com/models/gemini-4-argon) | Google | $2 in / $10 out per 1M tokens (introductory price until Nov 30, 2026; list $4 / $20) ([source](https://ai.google.dev/gemini-api/docs/pricing)) | 1.05M tokens ([source](https://ai.google.dev/gemini-api/docs/models/gemini-4-argon)) | Proprietary (API) ([source](https://ai.google.dev/gemini-api/docs/pricing)) | text, image, video, audio, pdf ([source](https://ai.google.dev/gemini-api/docs/models/gemini-4-argon)) | Oct 13, 2026 ([source](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-argon/)) | Generally available |
| [Muse Wonder](https://theagenticweekly.com/models/muse-wonder) | Meta | $4 in / $20 out per 1M tokens ([source](https://dev.meta.ai/docs/pricing-rate-limits)) | 1.05M tokens ([source](https://dev.meta.ai/docs/models)) | Proprietary (API) ([source](https://dev.meta.ai/docs/models)) | text, image, video, audio, pdf ([source](https://dev.meta.ai/docs/models)) | Oct 12, 2026 ([source](https://about.fb.com/news/2026/10/introducing-muse-wonder-models/)) | Public preview |
| [Muse Wonder Full](https://theagenticweekly.com/models/muse-wonder-full) | Meta | Not published | Not published | Proprietary (subscription) ([source](https://dev.meta.ai/docs/models)) | Not published | Oct 12, 2026 ([source](https://about.fb.com/news/2026/10/introducing-muse-wonder-models/)) | Limited access |
| [Claude Haiku 5.5](https://theagenticweekly.com/models/claude-haiku-5-5) | Anthropic | $0.1 in / $0.5 out per 1M tokens ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | 1M tokens ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Proprietary (API) ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | text, image ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Oct 7, 2026 ([source](https://www.anthropic.com/news)) | Generally available |
| [GPT-6.1 Sol](https://theagenticweekly.com/models/gpt-6-1-sol) | OpenAI | $2 in / $10 out per 1M tokens ([source](https://developers.openai.com/api/docs/models/gpt-6.1-sol)) | 1.05M tokens ([source](https://developers.openai.com/api/docs/models/gpt-6.1-sol)) | Proprietary (API) ([source](https://developers.openai.com/api/docs/models/gpt-6.1-sol)) | text, image ([source](https://developers.openai.com/api/docs/models/gpt-6.1-sol)) | Sep 29, 2026 ([source](https://developers.openai.com/api/docs/changelog)) | Generally available |
| [Claude Sonnet 5.5](https://theagenticweekly.com/models/claude-sonnet-5-5) | Anthropic | $2 in / $10 out per 1M tokens ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | 1M tokens ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Proprietary (API) ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | text, image ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Sep 28, 2026 ([source](https://www.anthropic.com/news)) | Generally available |
| [Claude Opus 5.5](https://theagenticweekly.com/models/claude-opus-5-5) | Anthropic | $4 in / $20 out per 1M tokens ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | 1M tokens ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Proprietary (API) ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | text, image ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Sep 22, 2026 ([source](https://www.anthropic.com/news)) | Generally available |
| [GPT-6 Sol](https://theagenticweekly.com/models/gpt-6-sol) | OpenAI | $2 in / $10 out per 1M tokens ([source](https://developers.openai.com/api/docs/changelog)) | Not published | Proprietary (API) ([source](https://developers.openai.com/api/docs/models/gpt-6-sol)) | text, image ([source](https://developers.openai.com/api/docs/models/gpt-6-sol)) | Sep 22, 2026 ([source](https://developers.openai.com/api/docs/changelog)) | Generally available |
| [Grok 4.7](https://theagenticweekly.com/models/grok-4-7) | xAI | $2 in / $6 out per 1M tokens ([source](https://docs.x.ai/developers/models/grok-4.7)) | 500K tokens ([source](https://docs.x.ai/developers/models/grok-4.7)) | Proprietary (API) ([source](https://docs.x.ai/developers/models/grok-4.7)) | text, image ([source](https://docs.x.ai/developers/models/grok-4.7)) | Sep 21, 2026 ([source](https://docs.x.ai/developers/release-notes)) | Generally available |
| [Claude Fable 5.1](https://theagenticweekly.com/models/claude-fable-5-1) | Anthropic | $10 in / $50 out per 1M tokens ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | 1M tokens ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Proprietary (API) ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | text, image ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Sep 15, 2026 ([source](https://www.anthropic.com/news)) | Generally available |
| [GPT-6 Astra](https://theagenticweekly.com/models/gpt-6-astra) | OpenAI | $10 in / $50 out per 1M tokens ([source](https://developers.openai.com/api/docs/models/gpt-6-astra)) | 1.05M tokens ([source](https://developers.openai.com/api/docs/models/gpt-6-astra)) | Proprietary (API) ([source](https://developers.openai.com/api/docs/models/gpt-6-astra)) | text, image ([source](https://developers.openai.com/api/docs/models/gpt-6-astra)) | Sep 3, 2026 ([source](https://openai.com/index/gpt-6-astra/)) | Generally available |
| [Gemini 3.8 Flash](https://theagenticweekly.com/models/gemini-3-8-flash) | Google | $0.75 in / $3.75 out per 1M tokens (temporary price until Dec 31, 2026; list $1.5 / $7.5) ([source](https://ai.google.dev/gemini-api/docs/pricing)) | 1.05M tokens ([source](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash)) | Proprietary (API) ([source](https://ai.google.dev/gemini-api/docs/pricing)) | text, image, video, audio, pdf ([source](https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash)) | Sep 2, 2026 ([source](https://ai.google.dev/gemini-api/docs/changelog)) | Generally available |
| [Claude Mythos 5.1](https://theagenticweekly.com/models/claude-mythos-5-1) | Anthropic | $10 in / $50 out per 1M tokens ([source](https://platform.claude.com/docs/en/release-notes/overview)) | 1M tokens ([source](https://platform.claude.com/docs/en/release-notes/overview)) | Proprietary (API) ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Not published | Sep 1, 2026 ([source](https://platform.claude.com/docs/en/release-notes/overview)) | Limited access |
| [GLM-5.3-Flash](https://theagenticweekly.com/models/glm-5-3-flash) | Z.ai | Not published | Not published | Not published | Not published | Aug 26, 2026 ([source](https://docs.z.ai/release-notes/new-released)) | Generally available |
| [GLM-5.3](https://theagenticweekly.com/models/glm-5-3) | Z.ai | $1.4 in / $4.4 out per 1M tokens ([source](https://docs.z.ai/guides/overview/pricing)) | 1.05M tokens ([source](https://docs.z.ai/guides/llm/glm-5.3)) | GLM-5.3 License (MIT-style plus a MaaS condition) ([source](https://huggingface.co/zai-org/GLM-5.3/blob/main/LICENSE)) | Not published | Aug 14, 2026 ([source](https://z.ai/blog/glm-5.3)) | Generally available |
| [Grok 4.6](https://theagenticweekly.com/models/grok-4-6) | xAI | $2 in / $6 out per 1M tokens ([source](https://docs.x.ai/docs/release-notes)) | 500K tokens ([source](https://docs.x.ai/docs/release-notes)) | Proprietary (API) ([source](https://docs.x.ai/docs/models)) | text, image ([source](https://docs.x.ai/docs/release-notes)) | Aug 12, 2026 ([source](https://docs.x.ai/docs/release-notes)) | Generally available |
| [Gemini Robotics ER 2](https://theagenticweekly.com/models/gemini-robotics-er-2) | Google | Not published | Not published | Proprietary (API) ([source](https://ai.google.dev/gemini-api/docs/models)) | Not published | Jul 30, 2026 ([source](https://ai.google.dev/gemini-api/docs/changelog)) | Public preview |
| [Claude Opus 5](https://theagenticweekly.com/models/claude-opus-5) | Anthropic | $5 in / $25 out per 1M tokens ([source](https://platform.claude.com/docs/en/release-notes/overview)) | 1M tokens ([source](https://platform.claude.com/docs/en/release-notes/overview)) | Proprietary (API) ([source](https://platform.claude.com/docs/en/about-claude/models/overview)) | Not published | Jul 24, 2026 ([source](https://platform.claude.com/docs/en/release-notes/overview)) | Generally available |
| [Gemini 3.5 Flash-Lite](https://theagenticweekly.com/models/gemini-3-5-flash-lite) | Google | Not published | 1.05M tokens ([source](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite)) | Proprietary (API) ([source](https://ai.google.dev/gemini-api/docs/models)) | text, image, video, audio, pdf ([source](https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash-lite)) | Jul 21, 2026 ([source](https://ai.google.dev/gemini-api/docs/changelog)) | Generally available |
| [Gemini 3.6 Flash](https://theagenticweekly.com/models/gemini-3-6-flash) | Google | Not published | 1.05M tokens ([source](https://ai.google.dev/gemini-api/docs/models/gemini-3.6-flash)) | Proprietary (API) ([source](https://ai.google.dev/gemini-api/docs/models)) | text, image, video, audio, pdf ([source](https://ai.google.dev/gemini-api/docs/models/gemini-3.6-flash)) | Jul 21, 2026 ([source](https://ai.google.dev/gemini-api/docs/changelog)) | Generally available |
| [Kimi K3](https://theagenticweekly.com/models/kimi-k3) | Moonshot AI | $3 in / $15 out per 1M tokens ([source](https://platform.kimi.ai/docs/pricing/chat)) | 1M tokens ([source](https://www.kimi.com/blog/kimi-k3)) | Kimi K3 License (custom) ([source](https://huggingface.co/moonshotai/Kimi-K3)) | Not published | Jul 16, 2026 ([source](https://www.kimi.com/blog/kimi-k3)) | Generally available |
| [GPT-5.6 Sol](https://theagenticweekly.com/models/gpt-5-6-sol) | OpenAI | $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) ([source](https://developers.openai.com/api/docs/models/gpt-5.6-sol)) | 1.05M tokens ([source](https://developers.openai.com/api/docs/models/gpt-5.6-sol)) | Proprietary (API) ([source](https://developers.openai.com/api/docs/models/gpt-5.6-sol)) | text, image ([source](https://developers.openai.com/api/docs/models/gpt-5.6-sol)) | Jul 9, 2026 ([source](https://developers.openai.com/api/docs/changelog)) | Generally available |
| [Grok 4.5](https://theagenticweekly.com/models/grok-4-5) | xAI | $2 in / $6 out per 1M tokens ([source](https://docs.x.ai/docs/models)) | 500K tokens ([source](https://docs.x.ai/docs/models)) | Proprietary (API) ([source](https://docs.x.ai/docs/models)) | text, image ([source](https://docs.x.ai/docs/models)) | Jul 8, 2026 ([source](https://docs.x.ai/docs/release-notes)) | Generally 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.

## How to cite

Agentic Weekly, "Best AI model for agents: how to choose", updated 2026-10-29, https://theagenticweekly.com/best/ai-model-for-agents