Free models for AI agents

Current models with function calling for agents such as Hermes Agent, OpenClaw, and OpenHands. Outdated and very small models are filtered out.

104 models14 providersup to 10.5M contextbest: GLM 5.3 FlashUpdated: October 31, 2026 at 01:14 PM UTC

Agents need reliable tool calling, structured output, and long context. Free quotas drain quickly in multi-step runs, so compare the providers column.

#	Model ↕	AA Index ↕	GPQA ↕	Context ↕	Size ↕	Free at ↕
1	GLM 5.3 Flash Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	41.8	91%	1M	Mid-size	OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen
2	Step 5 Preview StepFun Tool use	43.7	—	1M	Frontier	NVIDIA Build, UnoRouter
3	GLM 5.3 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	44.8	92%	1M	Frontier	Together AI
4	DeepSeek V4.1 Flash DeepSeek ReasoningCodingTool useOpen weights	39.5	—	1M	Frontier	OrcaRouter, NVIDIA Build, OpenCode Zen
5	Gemini 3.8 Flash Google VisionReasoningCodingTool use	40.9	95%	1M	Mid-size	Google AI Studio
6	Qwen 3.8 27B Alibaba Cloud · 27B ReasoningCodingTool useOpen weights	33.7	91%	262K	Mid-size	Groq, Cloudflare Workers AI, UnoRouter
7	DeepSeek V4 Flash DeepSeek ReasoningCodingTool useOpen weights	34.3	91%	1M	Frontier	OrcaRouter
8	Gemini 3.6 Flash Google VisionReasoningCodingTool use	34.0	93%	1M	Mid-size	UnoRouter
9	GLM 5.2 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	33.7	90%	1M	Frontier	Together AI
10	Kimi K2.6 Moonshot AI ReasoningCodingTool useOpen weights	27.0	91%	256K	Frontier	NVIDIA Build
11	Nemotron 3 Ultra NVIDIA · 550B · 55B ReasoningCodingTool useOpen weights	22.9	87%	1M	Frontier	OpenRouter, NVIDIA Build, UnoRouter
12	Gemma 4 31B Google DeepMind · 31B VisionTool useOpen weights	19.0	86%	262K	Mid-size	OpenRouter, Together AI, NVIDIA Build, UnoRouter
13	MiniMax M2.5 MiniMax ReasoningCodingTool useOpen weights	22.8	85%	205K	Frontier	UnoRouter
14	Qwen 3.5 397B Alibaba Cloud · 397B · 17B ReasoningCodingTool useOpen weights	21.4	86%	262K	Frontier	UnoRouter
15	Qwen 3.6 27B Alibaba Cloud · 27B ReasoningCodingTool useOpen weights	21.4	84%	262K	Mid-size	UnoRouter
16	Gemma 4 26B A4B Google DeepMind · 26B · 4B VisionTool useOpen weights	16.7	79%	262K	Mid-size	OpenRouter, Together AI, Cloudflare Workers AI, UnoRouter
17	GLM 4.7 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	22.2	86%	203K	Frontier	Together AI
18	Qwen 3.6 35B Alibaba Cloud · 35B · 3B ReasoningCodingTool useOpen weights	18.2	84%	262K	Mid-size	Together AI, UnoRouter
19	Step 3.7 Flash StepFun ReasoningTool useOpen weights	19.5	81%	262K	Frontier	Nous Portal
20	Qwen 3.5 35B Alibaba Cloud · 35B · 3B ReasoningCodingTool useOpen weights	19.3	85%	262K	Mid-size	Together AI
21	Nemotron 3.5 Lightning NVIDIA · 30B · 3B ReasoningTool useOpen weights	12.9	74%	1M	Mid-size	+1OpenRouter, NVIDIA Build, Vercel AI Gateway, UnoRouter, OpenCode Zen
22	Qwen 3.5 122B Alibaba Cloud · 122B · 10B ReasoningCodingTool useOpen weights	17.7	83%	262K	Frontier	Together AI
23	MiniMax M2 MiniMax · 230B · 10B ReasoningCodingTool useOpen weights	18.6	78%	197K	Frontier	Together AI
24	MiniMax M3.1 Flash MiniMax ReasoningCodingTool useOpen weights	—	—	1M	Frontier	NVIDIA Build, UnoRouter
25	Gemma 4 12B Google DeepMind · 12B VisionTool useOpen weights	14.2	75%	262K	Mid-size	Together AI, UnoRouter
26	GLM 4.7 Flash Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	14.9	58%	131K	Mid-size	Cloudflare Workers AI, UnoRouter
27	Llama 4 Maverick Instruct Fp4 Meta · 400B · 17B VisionTool useOpen weights	—	—	1M	Frontier	Together AI
28	Nemotron 3 Nano Omni NVIDIA · 30B · 3B VisionReasoningTool useOpen weights	10.3	47%	262K	Mid-size	+1OpenRouter, Together AI, NVIDIA Build, TokenRouter, UnoRouter
29	Nemotron 3 Super NVIDIA · 120B · 12B ReasoningCodingTool useOpen weights	12.8	80%	262K	Frontier	NVIDIA Build, UnoRouter
30	Nemotron 3 120B NVIDIA · 120B · 12B ReasoningTool useOpen weights	—	—	256K	Frontier	Cloudflare Workers AI
31	GPT 5 Kiara OpenAI · New VisionTool use	—	—	400K	Frontier	UnoRouter
32	Mistral Small 4 119B Mistral AI · 119B · New Tool useOpen weights	—	—	262K	Frontier	UnoRouter
33	gpt-oss-120b OpenAI · 117B · 5.1B ReasoningCodingTool useOpen weights	11.6	78%	131K	Frontier	Groq, Cloudflare Workers AI, UnoRouter
34	gpt-oss-20b OpenAI · 21B · 3.6B ReasoningTool useOpen weights	10.0	61%	131K	Mid-size	Groq, Cloudflare Workers AI, NVIDIA Build, UnoRouter
35	Qwen3 VL 235B Alibaba Cloud · 235B · 22B VisionReasoningTool useOpen weights	13.4	77%	262K	Frontier	Together AI
36	Nemotron 3.5 Super VL NVIDIA VisionReasoningTool useOpen weights	—	—	1M	Mid-size	OpenRouter, UnoRouter, OpenCode Zen
37	Cogito V1 Preview Llama 70B Meta · 70B Tool useOpen weights	—	—	131K	Frontier	Together AI
38	Meta Llama 3.1 70B Meta · 70B Tool useOpen weights	—	—	131K	Frontier	Together AI
39	GLM 4.7 Fp4 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	203K	Frontier	Together AI
40	GLM 5 Fp4 Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	203K	Frontier	Together AI
41	MiniMax M2.5 Fp4 MiniMax ReasoningCodingTool useOpen weights	—	—	8K	Frontier	Together AI
42	GLM Ocr Z.ai (Zhipu AI) Tool useOpen weights	—	—	131K	Frontier	Together AI
43	Llama 3.3 70B Instruct Fp8 Fast Meta · 70B Tool useOpen weights	—	—	24K	Frontier	Cloudflare Workers AI
44	Nemotron 3.5 Super VL 120B NVIDIA · 120B · 12B VisionReasoningTool useOpen weights	—	—	—	Frontier	NVIDIA Build
45	GLM 4 Z.ai (Zhipu AI) · New ReasoningTool useOpen weights	—	—	25K	Frontier	UnoRouter
46	Qwen2.5 VL 72B Alibaba Cloud · 72B · New VisionTool useOpen weights	—	—	32K	Frontier	UnoRouter
47	Nvidia Nemotron 3 Super NVIDIA · 120B · 12B ReasoningCodingTool useOpen weights	12.8	80%	262K	Frontier	Together AI
48	MiniMax M1 80K MiniMax ReasoningTool useOpen weights	11.7	70%	1M	Frontier	Together AI
49	Qwen3 235B Alibaba Cloud · 235B · 22B ReasoningCodingTool useOpen weights	12.7	79%	262K	Frontier	Together AI
50	Mistral Nemo Mistral AI · 12B Tool useOpen weights	—	—	131K	Mid-size	Mistral AI, Together AI, NVIDIA Build, UnoRouter
51	Llama 4 Scout Meta · 109B · 17B VisionTool useOpen weights	8.1	59%	10.5M	Frontier	Together AI, Cloudflare Workers AI, UnoRouter
52	Qwen3 30B Alibaba Cloud · 30B · 3B ReasoningTool useOpen weights	9.8	71%	262K	Mid-size	Together AI, Cloudflare Workers AI
53	Qwen3 Next 80B Alibaba Cloud · 80B · 3B ReasoningCodingTool useOpen weights	11.2	76%	262K	Frontier	Together AI
54	MiniMax M1 40K MiniMax ReasoningTool useOpen weights	10.0	68%	1M	Frontier	Together AI
55	QwQ 32B Alibaba Cloud · 32B ReasoningTool useOpen weights	9.5	59%	24K	Mid-size	Cloudflare Workers AI, UnoRouter
56	GLM 5.3 Flash Search Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	1M	Mid-size	UnoRouter
57	Nemotron 3 Nano NVIDIA · 30B · 3B Tool useOpen weights	8.9	76%	1M	Mid-size	NVIDIA Build
58	Qwen3 Coder 30B Alibaba Cloud · 30B · 3B ReasoningCodingTool useOpen weights	9.6	52%	262K	Frontier	Together AI
59	DiffusionGemma 26B Google DeepMind · 26B · 4B Tool useOpen weights	9.5	67%	262K	Mid-size	UnoRouter
60	Gemma 4 26B IT Chimerax Google DeepMind · 26B · 4B · New VisionTool useOpen weights	—	—	262K	Mid-size	UnoRouter
61	Gemma 4 26B IT Darksoul Google DeepMind · 26B · 4B · New VisionTool useOpen weights	—	—	262K	Mid-size	UnoRouter
62	Gemma 4 26B IT Luminous Google DeepMind · 26B · 4B · New VisionTool useOpen weights	—	—	262K	Mid-size	UnoRouter
63	Gemma 4 26B IT Meromero Google DeepMind · 26B · 4B · New VisionTool useOpen weights	—	—	262K	Mid-size	UnoRouter
64	Qwen SEA-LION V4.5 27B Alibaba Cloud · 27B Tool useOpen weights	—	—	262K	Mid-size	UnoRouter
65	Qwen 3.5 27B Derestricted Alibaba Cloud · 27B · New ReasoningCodingTool useOpen weights	—	—	262K	Mid-size	UnoRouter
66	Llama 3.2 11B Vision Meta · 11B VisionTool useOpen weights	5.4	22%	131K	Mid-size	Together AI, Cloudflare Workers AI, NVIDIA Build, UnoRouter
67	Nvidia Nemotron 3 Nano NVIDIA · 30B · 3B ReasoningTool useOpen weights	8.9	76%	262K	Mid-size	Together AI
68	DeepSeek R1 Distill Qwen 32B DeepSeek · 32B ReasoningTool useOpen weights	8.4	62%	80K	Mid-size	Cloudflare Workers AI, UnoRouter
69	Llama 3.3 70B Meta · 70B Tool useOpen weights	7.7	50%	131K	Frontier	Together AI, UnoRouter
70	Mixtral 8x7b Instruct V01 Mistral AI · 46.7B · 12.9B Tool useOpen weights	—	—	16K	Mid-size	Together AI
71	Cogito V1 Preview Qwen 32B Alibaba Cloud · 32B Tool useOpen weights	—	—	131K	Mid-size	Together AI
72	Cogito V1 Preview Qwen 14B Alibaba Cloud · 14B Tool useOpen weights	—	—	131K	Mid-size	Together AI
73	Qwen2.5 14B Alibaba Cloud · 14B Tool useOpen weights	—	—	131K	Mid-size	Together AI
74	Medgemma 27B Text Google DeepMind · 27B Tool useOpen weights	—	—	131K	Mid-size	Together AI
75	DeepSeek Ocr 2 DeepSeek Tool useOpen weights	—	—	8K	Mid-size	Together AI
76	C4ai Aya Expanse 32B Cohere · 32B Tool use	—	—	128K	Mid-size	Cohere
77	C4ai Aya Vision 32B Cohere · 32B VisionTool use	—	—	16K	Mid-size	Cohere
78	Gemma SEA-LION V4 27B Google DeepMind · 27B Tool useOpen weights	—	—	128K	Mid-size	Cloudflare Workers AI
79	Mistral Small 3.1 24B Mistral AI · 24B Tool useOpen weights	—	—	128K	Mid-size	Cloudflare Workers AI
80	Nemotron 3.5 Bolt E4b NVIDIA ReasoningTool useOpen weights	—	—	—	Mid-size	NVIDIA Build
81	GLM 4.5 Flash Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	131K	Mid-size	UnoRouter
82	GLM 4 6v Flash Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	—	—	128K	Mid-size	UnoRouter
83	Qwen SEA-LION V4 32B Alibaba Cloud · 32B Tool useOpen weights	—	—	33K	Mid-size	UnoRouter
84	Qwen3 Alibaba Cloud ReasoningTool useOpen weights	—	—	25K	Mid-size	UnoRouter
85	Llama 3.3 Nemotron Super 49B NVIDIA · 49B Tool useOpen weights	8.9	64%	16K	Mid-size	Together AI
86	Devstral Small Mistral AI CodingTool useOpen weights	8.7	43%	131K	Mid-size	Together AI
87	Magistral Small Mistral AI ReasoningTool useOpen weights	8.6	66%	41K	Mid-size	Together AI
88	Qwen3 32B Alibaba Cloud · 32B ReasoningTool useOpen weights	8.6	67%	41K	Mid-size	Together AI
89	GPT-4o OpenAI VisionTool use	8.4	54%	128K	Frontier	UnoRouter
90	Mistral Small Mistral AI · 24B Tool useOpen weights	5.8	38%	262K	Mid-size	Mistral AI, UnoRouter
91	Qwen3 14B Alibaba Cloud · 14B ReasoningTool useOpen weights	8.2	60%	2K	Mid-size	Together AI
92	Qwen2.5 Coder 32B Alibaba Cloud · 32B CodingTool useOpen weights	6.7	42%	33K	Mid-size	Cloudflare Workers AI, UnoRouter
93	Mistral Small 3.2 Mistral AI · 24B Tool useOpen weights	8.2	51%	128K	Mid-size	UnoRouter
94	Llama 3.2 90B Vision Meta · 90B VisionTool useOpen weights	6.4	43%	16K	Frontier	Together AI, NVIDIA Build
95	DeepSeek R1 Distill Llama 70B DeepSeek · 70B · New ReasoningTool useOpen weights	7.9	40%	131K	Frontier	UnoRouter
96	Qwen2.5 72B Alibaba Cloud · 72B Tool useOpen weights	7.7	49%	131K	Frontier	Together AI
97	GLM 4 5v Z.ai (Zhipu AI) ReasoningCodingTool useOpen weights	7.6	68%	66K	Frontier	Together AI
98	Llama 3.1 Nemotron Ultra 253B NVIDIA · 253B Tool useOpen weights	7.5	73%	128K	Frontier	NVIDIA Build
99	Llama 3.1 405B Meta · 405B Tool useOpen weights	7.3	52%	131K	Frontier	Together AI
100	Qwen2.5 32B Alibaba Cloud · 32B Tool useOpen weights	6.9	47%	131K	Mid-size	Together AI
101	GPT 4o Mini OpenAI VisionTool use	6.7	43%	128K	Mid-size	UnoRouter
102	Llama 3.1 70B Meta · 70B Tool useOpen weights	6.6	41%	16K	Frontier	Together AI
103	Gemma 3 27B Google DeepMind · 27B VisionTool useOpen weights	4.9	43%	66K	Mid-size	Together AI
104	Gemma 3 12B Google DeepMind · 12B VisionTool useOpen weights	3.8	35%	128K	Mid-size	NVIDIA Build

Benchmarks: Artificial Analysis (September 24, 2026). A dash means the model is not on their leaderboard; we never estimate scores ourselves.

FAQ

What is the best free model for ai agents?

GLM 5.3 Flash currently leads — free at OrcaRouter, NVIDIA Build, UnoRouter, OpenCode Zen. Next come Step 5 Preview, GLM 5.3, DeepSeek V4.1 Flash.

FAQ

See also