Cheapest LLM APIs

Chat models ranked by blended price: three input tokens for every output token, the ratio of a typical chat or RAG request. Prices are per million tokens as each provider publishes them.

60 models from the Everstack catalog, updated with every catalog release.

#	Model	Provider	Context	Input /1M	Output /1M
1	inclusionAI: Ling 3.0 Flash VL (OpenRouter)	OpenRouter	262.1K	$0.021	$0.062
2	Ministral 3B (Latest)	Mistral AI	128K	$0.040	$0.040
3	Nex AGI: Nex-N2.5-Mini (OpenRouter)	OpenRouter	262.1K	$0.025	$0.10
4	DeepSeek V4 Flash 0731 (OpenRouter)	OpenRouter	1.3M	$0.040	$0.080
5	Solar Pro 4 (OpenRouter)	OpenRouter	524.3K	$0.030	$0.12
6	Llama 3.1 8B Instant	Groq	131.1K	$0.050	$0.080
7	Inference.net: Schematron V2 Turbo (OpenRouter)	OpenRouter	128K	$0.030	$0.15
8	Command R 7B	Cohere	128K	$0.037	$0.15
9	Command R 7B Arabic	Cohere	128K	$0.037	$0.15
10	Gemini 1.5 Flash 8B	Google	1M	$0.037	$0.15
11	Inception: Mercury 2.5 (OpenRouter)	OpenRouter	260K	$0.040	$0.15
12	Nemotron 3.5 Lightning 30B A3B (Fireworks)	Fireworks AI	262.1K	$0.050	$0.20
13	Upstage: Solar Mini 4 (OpenRouter)	OpenRouter	524.3K	$0.050	$0.20
14	Qwen Turbo	Qwen	1M	$0.050	$0.20
15	Inference.net: Schematron V2 Small (OpenRouter)	OpenRouter	128K	$0.050	$0.23
16	Llama 3.1 8B	Cerebras	32K	$0.10	$0.10
17	Ministral 8B	Mistral AI	128K	$0.10	$0.10
18	Nemotron 3.5 Lightning 30B A3B (OpenRouter)	OpenRouter	262.1K	$0.080	$0.20
19	Nex AGI: Nex-N2.5-Pro (OpenRouter)	OpenRouter	262.1K	$0.075	$0.25
20	GPT OSS 20B (Fireworks)	Fireworks AI	131.1K	$0.070	$0.30
21	Hy-MT2-30B-A3B (OpenRouter)	OpenRouter	8.2K	$0.074	$0.30
22	Gemini 1.5 Flash	Google	1.0M	$0.075	$0.30
23	Gemini 2.0 Flash Lite	Google	1.0M	$0.075	$0.30
24	GPT OSS 20B (Groq)	Groq	131.1K	$0.075	$0.30
25	Gemini 1.5 Flash	Vertex AI	1.0M	$0.075	$0.30
26	GPT-5 Nano (Azure)	Azure OpenAI	400K	$0.050	$0.40
27	GPT-5 Nano	OpenAI	400K	$0.050	$0.40
28	Qwen Flash	Qwen	1M	$0.050	$0.40
29	Mistral Nemo	Mistral AI	128K	$0.15	$0.15
30	Pixtral 12B	Mistral AI	128K	$0.15	$0.15
31	Mistral Small 3.2	Mistral AI	128K	$0.10	$0.30
32	Voxtral Small (latest)	Mistral AI	32K	$0.10	$0.30
33	GLM-4.7-FlashX	Z. Z.AI	200K	$0.070	$0.40
34	Llama 3.3 70B Instruct	OpenRouter	131.1K	$0.10	$0.32
35	Llama 4 Scout 17B 16E (Groq)	Groq	131.1K	$0.11	$0.34
36	DeepSeek Chat (V4)	DeepSeek	1M	$0.14	$0.28
37	DeepSeek Reasoner (V4)	DeepSeek	1M	$0.14	$0.28
38	DeepSeek V4 Flash 0731 (Fireworks)	Fireworks AI	1M	$0.14	$0.28
39	DeepSeek V4 Flash 0731 (Hugging Face)	Hugging Face	1.0M	$0.14	$0.28
40	Xiaomi: MiMo-V2.6-Flash (OpenRouter)	OpenRouter	1.0M	$0.14	$0.28
41	DeepSeek V4 Flash 0731 (Together)	Together AI	1M	$0.14	$0.28
42	Gemini 2.0 Flash	Google	1.0M	$0.10	$0.40
43	Gemini 2.5 Flash Lite	Google	1.0M	$0.10	$0.40
44	Qwen3.5 Flash	Qwen	1M	$0.10	$0.40
45	PrismML: Ternary Bonsai 2 27B (OpenRouter)	OpenRouter	262.1K	$0.075	$0.50
46	GPT-6 Luna	OpenAI	1.1M	$0.10	$0.50
47	OpenAI: GPT-6 Luna Pro (OpenRouter)	OpenRouter	1.1M	$0.10	$0.50
48	OpenAI: GPT-6 Luna (OpenRouter)	OpenRouter	1.1M	$0.10	$0.50
49	Qwen: Qwen3.8 Omni Flash (OpenRouter)	OpenRouter	1M	$0.15	$0.47
50	Mistral 7B	Mistral AI	8K	$0.25	$0.25
51	DeepSeek V4 Flash 0731	Qwen	1M	$0.20	$0.40
52	Command R	Cohere	128K	$0.15	$0.60
53	GPT OSS 120B (Fireworks)	Fireworks AI	131.1K	$0.15	$0.60
54	GPT OSS 120B (Groq)	Groq	131.1K	$0.15	$0.60
55	Mistral Small 4	Mistral AI	256K	$0.15	$0.60
56	Mistral Small (Latest)	Mistral AI	256K	$0.15	$0.60
57	GPT-4o Mini	OpenAI	128K	$0.15	$0.60
58	GPT OSS 120B (Together)	Together AI	131.1K	$0.15	$0.60
59	Grok 4.1 Fast	xAI	2M	$0.20	$0.50
60	Grok 4 Fast	xAI	2M	$0.20	$0.50