Skip to content
OpenKey

Best models for agents

Models that support the tools parameter for function calling. 245 of 338 catalog models match as of July 2026.

245
Models
$0.010
Input from /1M
10M
Max context
Jun 30, 2026
Newest release

245 models in the OpenKey catalog fit the agents facet as of now, with Claude Sonnet 5 (Anthropic, released 2026-06-30) the newest entry — a 1M-context model at $2/$10 per M input/output. Pricing spans from free tiers (Nemotron 3 Ultra free, Laguna M.1 free, Laguna XS.2 free) up to $30/$180 per M on GPT-5.5 Pro and Claude Opus 4.7 (Fast). Most of the field clusters in the $0.1-$5 input range with 256K-1M context, which is the range that actually matters for agent loops: you're paying per tool call and per retry, not per single completion. A handful of models — GLM 5.2, Claude Opus 4.8, Claude Fable 5 — carry design_arena benchmark ranks worth checking before you commit a workflow to one backbone.

Top picks

Claude Sonnet 5

Newest model in the set (2026-06-30), 1M context window, and priced at $2/$10 per M in/out — mid-range for a frontier-class model, which matters when an agent loop burns tokens on tool-call retries and long scratchpads.

GLM 5.2

Ranks 1 on design_arena 3d (elo 1376), the highest elo in this list, at $0.93/$3 per M with a 1,048,576-token context window — strong reasoning signal for a fraction of Opus-tier pricing.

Nemotron 3 Ultra (free)

Same 1M context and design_arena 3d rank 40 (elo 1213) as its paid twin, but $0/$0 per M — useful for prototyping an agent's tool-calling logic before you swap in a paid model for production runs.

All 245 models

Full catalog →
  • Claude Sonnet 5ctx 1M · inout
  • Fugu Ultractx 1M · inout
  • Nano Banana Pro (Gemini 3 Pro Image)ctx 66K · inout
  • North Mini Code (free)Freectx 256K · inFreeoutFree
  • GLM 5.2ctx 1.0M · inout
  • Kimi K2.7 Codectx 262K · inout
  • Claude Fable 5ctx 1M · inout
  • Nemotron 3 Ultractx 1M · inout
  • Nemotron 3 Ultra (free)Freectx 1M · inFreeoutFree
  • Qwen3.7 Plusctx 1M · inout
  • MiniMax M3ctx 1.0M · inout
  • Step 3.7 Flashctx 256K · inout
  • Claude Opus 4.8ctx 1M · inout
  • Claude Opus 4.8 (Fast)ctx 1M · inout
  • Qwen3.7 Maxctx 1M · inout
  • Grok Build 0.1ctx 256K · inout
  • Gemini 3.5 Flashctx 1.0M · inout
  • Claude Opus 4.7 (Fast)ctx 1M · inout
  • Ring-2.6-1Tctx 262K · inout
  • Gemini 3.1 Flash Litectx 1.0M · inout
  • GPT Chat Latestctx 400K · inout
  • Granite 4.1 8Bctx 131K · inout
  • Mistral Medium 3.5ctx 262K · inout
  • Grok 4.3ctx 1M · inout
  • Nemotron 3 Nano Omni (free)Freectx 256K · inFreeoutFree
  • Laguna M.1ctx 262K · inout
  • Laguna M.1 (free)Freectx 262K · inFreeoutFree
  • Laguna XS.2ctx 262K · inout
  • Laguna XS.2 (free)Freectx 262K · inFreeoutFree
  • Qwen3.5 Plus 2026-04-20ctx 1M · inout
  • Qwen3.6 27Bctx 262K · inout
  • Qwen3.6 35B A3Bctx 262K · inout
  • Qwen3.6 Flashctx 1M · inout
  • Qwen3.6 Max Previewctx 262K · inout
  • DeepSeek V4 Flashctx 1.0M · inout
  • DeepSeek V4 Proctx 1.0M · inout
  • GPT-5.5ctx 1.1M · inout
  • GPT-5.5 Proctx 1.1M · inout
  • Ling-2.6-1Tctx 262K · inout
  • Hy3 previewctx 262K · inout
  • MiMo-V2.5ctx 1.0M · inout
  • MiMo-V2.5-Proctx 1.0M · inout
  • Ling-2.6-flashctx 262K · inout
  • Kimi K2.6ctx 262K · inout
  • Claude Opus 4.7ctx 1M · inout
  • GLM 5.1ctx 203K · inout
  • Gemma 4 26B A4B ctx 262K · inout
  • Gemma 4 26B A4B (free)Freectx 262K · inFreeoutFree
  • Gemma 4 31Bctx 262K · inout
  • Gemma 4 31B (free)Freectx 262K · inFreeoutFree
  • Qwen3.6 Plusctx 1M · inout
  • Trinity Large Thinkingctx 262K · inout
  • GLM 5V Turboctx 203K · inout
  • Grok 4.20ctx 2M · inout
  • KAT-Coder-Pro V2ctx 256K · inout
  • Reka Edgectx 16K · inout
  • MiniMax M2.7ctx 205K · inout
  • GPT-5.4 Minictx 400K · inout
  • GPT-5.4 Nanoctx 400K · inout
  • Mistral Small 4ctx 262K · inout
  • GLM 5 Turboctx 262K · inout
  • Nemotron 3 Superctx 1M · inout
  • Nemotron 3 Super (free)Freectx 1M · inFreeoutFree
  • Seed-2.0-Litectx 262K · inout
  • Qwen3.5-9Bctx 262K · inout
  • GPT-5.4ctx 1.1M · inout
  • GPT-5.4 Proctx 1.1M · inout
  • Mercury 2ctx 128K · inout
  • Gemini 3.1 Flash Lite Previewctx 1.0M · inout
  • GPT-5.3 Chatctx 128K · inout
  • Seed-2.0-Minictx 262K · inout
  • Gemini 3.1 Pro Preview Custom Toolsctx 1.0M · inout
  • Qwen3.5-122B-A10Bctx 262K · inout
  • Qwen3.5-27Bctx 262K · inout
  • Qwen3.5-35B-A3Bctx 262K · inout
  • Qwen3.5-Flashctx 1M · inout
  • GPT-5.3-Codexctx 400K · inout
  • Gemini 3.1 Pro Previewctx 1.0M · inout
  • Claude Sonnet 4.6ctx 1M · inout
  • Qwen3.5 397B A17Bctx 256K · inout
  • Qwen3.5 Plus 2026-02-15ctx 1M · inout
  • MiniMax M2.5ctx 205K · inout
  • GLM 5ctx 203K · inout
  • Qwen3 Max Thinkingctx 262K · inout
  • Claude Opus 4.6ctx 1M · inout
  • Qwen3 Coder Nextctx 262K · inout
  • Free Models RouterFreectx 200K · inFreeoutFree
  • Step 3.5 Flashctx 262K · inout
  • Kimi K2.5ctx 262K · inout
  • Solar Pro 3ctx 128K · inout
  • LFM2.5-1.2B-Thinking (free)Freectx 33K · inFreeoutFree
  • GPT Audioctx 128K · inout
  • GPT Audio Minictx 128K · inout
  • GLM 4.7 Flashctx 203K · inout
  • GPT-5.2-Codexctx 400K · inout
  • Seed 1.6ctx 262K · inout
  • Seed 1.6 Flashctx 262K · inout
  • MiniMax M2.1ctx 205K · inout
  • GLM 4.7ctx 203K · inout
  • Gemini 3 Flash Previewctx 1.0M · inout
  • Nemotron 3 Nano 30B A3Bctx 262K · inout
  • Nemotron 3 Nano 30B A3B (free)Freectx 256K · inFreeoutFree
  • GPT-5.2ctx 400K · inout
  • GPT-5.2 Chatctx 128K · inout
  • GPT-5.2 Proctx 400K · inout
  • Devstral 2 2512ctx 262K · inout
  • Relace Searchctx 256K · inout
  • GLM 4.6Vctx 131K · inout
  • GPT-5.1-Codex-Maxctx 400K · inout
  • Nova 2 Litectx 1M · inout
  • Ministral 3 14B 2512ctx 262K · inout
  • Ministral 3 3B 2512ctx 131K · inout
  • Ministral 3 8B 2512ctx 262K · inout
  • Trinity Minictx 131K · inout
  • DeepSeek V3.2ctx 131K · inout
  • Mistral Large 3 2512ctx 262K · inout
  • Claude Opus 4.5ctx 200K · inout
  • GPT-5.1ctx 400K · inout
  • GPT-5.1 Chatctx 128K · inout
  • GPT-5.1-Codexctx 400K · inout
  • GPT-5.1-Codex-Minictx 400K · inout
  • Kimi K2 Thinkingctx 262K · inout
  • Nova Premier 1.0ctx 1M · inout
  • Voxtral Small 24B 2507ctx 32K · inout
  • gpt-oss-safeguard-20bctx 131K · inout
  • Nemotron Nano 12B 2 VL (free)Freectx 128K · inFreeoutFree
  • MiniMax M2ctx 205K · inout
  • Qwen3 VL 32B Instructctx 262K · inout
  • Claude Haiku 4.5ctx 200K · inout
  • Qwen3 VL 8B Instructctx 256K · inout
  • Qwen3 VL 8B Thinkingctx 256K · inout
  • Llama 3.3 Nemotron Super 49B V1.5ctx 131K · inout
  • o3 Deep Researchctx 200K · inout
  • o4 Mini Deep Researchctx 200K · inout
  • GPT-5 Proctx 400K · inout
  • Qwen3 VL 30B A3B Instructctx 262K · inout
  • Qwen3 VL 30B A3B Thinkingctx 131K · inout
  • GLM 4.6ctx 203K · inout
  • Claude Sonnet 4.5ctx 1M · inout
  • DeepSeek V3.2 Expctx 164K · inout
  • Gemini 2.5 Flash Lite Preview 09-2025ctx 1.0M · inout
  • GPT-5 Codexctx 400K · inout
  • Qwen3 Coder Plusctx 1M · inout
  • Qwen3 Maxctx 262K · inout
  • Qwen3 VL 235B A22B Instructctx 262K · inout
  • Qwen3 VL 235B A22B Thinkingctx 131K · inout
  • DeepSeek V3.1 Terminusctx 164K · inout
  • Qwen3 Coder Flashctx 1M · inout
  • Qwen3 Next 80B A3B Instructctx 262K · inout
  • Qwen3 Next 80B A3B Instruct (free)Freectx 262K · inFreeoutFree
  • Qwen3 Next 80B A3B Thinkingctx 262K · inout
  • Qwen Plus 0728ctx 1M · inout
  • Qwen Plus 0728 (thinking)ctx 1M · inout
  • Nemotron Nano 9B V2 (free)Freectx 128K · inFreeoutFree
  • Kimi K2 0905ctx 262K · inout
  • Qwen3 30B A3B Thinking 2507ctx 131K · inout
  • DeepSeek V3.1ctx 164K · inout
  • Mistral Medium 3.1ctx 131K · inout
  • GLM 4.5Vctx 66K · inout
  • Jamba Large 1.7ctx 256K · inout
  • GPT-5ctx 400K · inout
  • GPT-5 Minictx 400K · inout
  • GPT-5 Nanoctx 400K · inout
  • Claude Opus 4.1ctx 200K · inout
  • gpt-oss-120bctx 131K · inout
  • gpt-oss-120b (free)Freectx 131K · inFreeoutFree
  • gpt-oss-20bctx 131K · inout
  • gpt-oss-20b (free)Freectx 131K · inFreeoutFree
  • Codestral 2508ctx 256K · inout
  • Qwen3 Coder 30B A3B Instructctx 160K · inout
  • Qwen3 30B A3B Instruct 2507ctx 131K · inout
  • Qwen3 235B A22B Thinking 2507ctx 262K · inout
  • GLM 4.5ctx 131K · inout
  • GLM 4.5 Airctx 131K · inout
  • Qwen3 Coder 480B A35Bctx 1.0M · inout
  • Qwen3 Coder 480B A35B (free)Freectx 1.0M · inFreeoutFree
  • Gemini 2.5 Flash Litectx 1.0M · inout
  • Qwen3 235B A22B Instruct 2507ctx 262K · inout
  • Kimi K2 0711ctx 131K · inout
  • Mistral Small 3.2 24Bctx 128K · inout
  • Gemini 2.5 Flashctx 1.0M · inout
  • Gemini 2.5 Proctx 1.0M · inout
  • MiniMax M1ctx 1M · inout
  • o3 Proctx 200K · inout
  • Gemini 2.5 Pro Preview 06-05ctx 1.0M · inout
  • R1 0528ctx 164K · inout
  • Claude Opus 4ctx 200K · inout
  • Claude Sonnet 4ctx 1M · inout
  • Gemini 2.5 Pro Preview 05-06ctx 1.0M · inout
  • Mistral Medium 3ctx 131K · inout
  • Virtuoso Largectx 131K · inout
  • Qwen3 14Bctx 132K · inout
  • Qwen3 235B A22Bctx 131K · inout
  • Qwen3 30B A3Bctx 131K · inout
  • Qwen3 32Bctx 131K · inout
  • Qwen3 8Bctx 131K · inout
  • o3ctx 200K · inout
  • o4 Minictx 200K · inout
  • o4 Mini Highctx 200K · inout
  • GPT-4.1ctx 1.0M · inout
  • GPT-4.1 Minictx 1.0M · inout
  • GPT-4.1 Nanoctx 1.0M · inout
  • Llama 4 Maverickctx 1.0M · inout
  • Llama 4 Scoutctx 10M · inout
  • DeepSeek V3 0324ctx 164K · inout
  • Gemma 3 12Bctx 131K · inout
  • Gemma 3 27Bctx 131K · inout
  • Sabactx 33K · inout
  • o3 Mini Highctx 200K · inout
  • Qwen-Plusctx 1M · inout
  • o3 Minictx 200K · inout
  • R1ctx 164K · inout
  • DeepSeek V3ctx 131K · inout
  • o1ctx 200K · inout
  • Llama 3.3 70B Instructctx 131K · inout
  • Llama 3.3 70B Instruct (free)Freectx 131K · inFreeoutFree
  • Nova Lite 1.0ctx 300K · inout
  • Nova Micro 1.0ctx 128K · inout
  • Nova Pro 1.0ctx 300K · inout
  • GPT-4o (2024-11-20)ctx 128K · inout
  • Mistral Large 2407ctx 131K · inout
  • UnslopNemo 12Bctx 33K · inout
  • Qwen2.5 7B Instructctx 131K · inout
  • Qwen2.5 72B Instructctx 131K · inout
  • Command R (08-2024)ctx 128K · inout
  • Command R+ (08-2024)ctx 128K · inout
  • Llama 3.1 Euryale 70B v2.2ctx 131K · inout
  • GPT-4o (2024-08-06)ctx 128K · inout
  • Llama 3.1 70B Instructctx 131K · inout
  • Llama 3.1 8B Instructctx 131K · inout
  • Mistral Nemoctx 131K · inout
  • GPT-4o-minictx 128K · inout
  • GPT-4o-mini (2024-07-18)ctx 128K · inout
  • GPT-4octx 128K · inout
  • GPT-4o (2024-05-13)ctx 128K · inout
  • Mixtral 8x22B Instructctx 66K · inout
  • GPT-4 Turboctx 128K · inout
  • Claude 3 Haikuctx 200K · inout
  • Mistral Largectx 128K · inout
  • GPT-3.5 Turbo (older v0613)ctx 4K · inout
  • GPT-4 Turbo Previewctx 128K · inout
  • Auto Routerctx 2M · inVariableoutVariable
  • GPT-3.5 Turbo 16kctx 16K · inout
  • GPT-3.5 Turboctx 16K · inout
  • GPT-4ctx 8K · inout

Prices per 1M tokens, flat 3% fee included. Hover or tap a price for the math.

How to choose

Agent workloads punish you twice for the wrong pick: on cost (multi-step loops multiply token spend) and on context (a 262K window like Kimi K2.7 Code's fills up fast once you add tool schemas and history). GLM 5.2 and DeepSeek V4 Pro give you 1M+ context at under $1 input while ranking on design_arena — good defaults for long-running agents. If you need top-tier reasoning and can absorb the cost, Claude Opus 4.8 ranks 1 on design_arena androidnative (elo 1343) at $5/$25 per M. For throwaway prototyping, the free tier (Nemotron 3 Ultra free, Laguna M.1 free) costs nothing but ships the same benchmark numbers as their paid counterparts.

Questions

What's the cheapest model here that still has agent-relevant benchmarks?
Ring-2.6-1T and Ling-2.6-1T both sit at $0.075/$0.625 per M with 262,144-token context, though neither lists a best_benchmark score. If you want a priced, benchmarked option, DeepSeek V4 Flash is $0.09/$0.18 per M and ranks on design_arena svg (elo 1216).
Is there a free model with a real context window for agent testing?
Yes — Nemotron 3 Ultra (free) and North Mini Code (free) both run at $0/$0. Nemotron 3 Ultra (free) gives you the full 1,000,000-token context plus a design_arena 3d rank 40 (elo 1213), matching its paid version exactly.
How does OpenKey pricing work on these models?
You pay the provider's list price plus a flat 3% fee. For Claude Sonnet 5 at $2 input / $10 output per M tokens, that's $2 × 1.03 = $2.06 input and $10 × 1.03 = $10.30 output on OpenKey — same model, one key, no separate provider accounts.