What is the cheapest AI model for chat?

The cheapest AI chat models are typically smaller models like GPT-3.5-turbo, Claude Instant, or open-source models on platforms like Together AI and Groq. Prices can be as low as $0.10-0.25 per million tokens. However, cheaper models may have reduced capabilities compared to flagship models like GPT-4 or Claude 3 Opus. Use CloudPrice to compare current prices across all providers.

How much does GPT-4 cost?

GPT-4 pricing varies by version. GPT-4 Turbo costs approximately $10 per million input tokens and $30 per million output tokens. GPT-4o is more affordable at around $5/$15 per million tokens. OpenAI also offers GPT-4o-mini at significantly lower prices. Pricing may change, so check CloudPrice for current rates.

What is the difference between input and output tokens?

Input tokens are the text you send to the AI model (your prompts, context, and conversation history). Output tokens are what the model generates in response. Most AI providers charge differently for input and output tokens, with output tokens typically being 2-4x more expensive because they require more computation to generate.

Which AI model has the largest context window?

Google's Gemini 1.5 Pro currently offers one of the largest context windows at 1 million tokens. Anthropic's Claude 3 models support 200K tokens, while OpenAI's GPT-4 Turbo supports 128K tokens. Larger context windows allow processing more text in a single request but may cost more.

What does 'supports vision' mean for AI models?

AI models with vision support can process and understand images in addition to text. You can send images as part of your prompt and the model can describe, analyze, or answer questions about them. Examples include GPT-4 Vision, Claude 3, and Gemini Pro Vision. Vision capabilities typically cost extra per image processed.

AI Models Pricing & Benchmarks Comparison - 1900+ LLM Models

Compare AI model pricing and benchmarks across providers including OpenAI, Anthropic, Google, Amazon Bedrock, Azure, Mistral, and more. Filter by model capabilities like vision, function calling, and reasoning support. Find the most cost-effective model for your use case. Currently tracking 2,711 models across 99 providers. Last update: June 8, 2026 at 12:00 AM UTC

Model	Creator	Input Price, $	Output Price, $	Context	Max Output	Inference Providers	Intelligence	Coding
GLM-5.1	Zhipu AI	0.980	3.08	203K	64K	compare (4)	51.4#1	43.4#1
Kimi K2.5	Moonshot AI (Kimi)	0.400	1.90	262K	98K	compare (11)	46.8#2	39.6#2
GLM-4.7	Zhipu AI	0.400	1.75	205K	131K	compare (13)	42.1#3	36.3#3
Kimi K2 Thinking	Moonshot AI (Kimi)	0.574	1.20	262K	33K	compare (14)	40.9#4	34.8#4
MiniMax M2.1	MiniMax	0.290	0.950	1.0M	197K	compare (8)	39.4#5	32.8#6
MiniMax M2	MiniMax	0.255	1.00	205K	197K	compare (9)	36.1#6	29.2#9
GPT OSS 120B	OpenAI	0.039	0.180	131K	131K	compare (20)	33.3#7	28.6#10
DeepSeek V3.2	DeepSeek	0.229	0.343	164K	66K	compare (12)	32.1#8	34.6#5
GLM-4.6	Zhipu AI	0.430	1.74	205K	131K	compare (10)	30.2#9	30.2#8
DeepSeek V3.1 Terminus	DeepSeek	0.270	0.950	164K	66K	compare (6)	28.5#10	31.9#7
DeepSeek V3.1	DeepSeek	0.135	0.500	164K	66K	compare (14)	28.1#11	28.4#11
GLM-4.5	Zhipu AI	0.400	1.60	131K	98K	compare (8)	26.4#12	26.3#12
Qwen3 Coder 480B A35B Instruct	Alibaba	0.220	1.30	262K	66K	compare (8)	24.8#13	24.6#13
GPT OSS 20B	OpenAI	0.029	0.140	131K	131K	compare (15)	24.5#14	18.5#18
MiniMax M1 80k	MiniMax	0.100	0.100	1.0M	40K	compare (3)	24.4#15	14.5#25
GLM-4.5 Air	Zhipu AI	0.125	0.850	131K	131K	compare (6)	23.2#16	23.8#14
Mistral Large 3	Mistral AI	0.500	1.20	262K	8K	compare (5)	22.8#17	22.7#15
DeepSeek V3 324	DeepSeek	0.200	0.400	164K	16K	compare (13)	22.3#18	22.0#16
Qwen3 VL 235B A22B Instruct	Alibaba	0.200	0.880	262K	129K	compare (7)	20.8#19	16.5#19
Qwen3 Next 80B A3B Instruct	Alibaba	0.090	0.900	262K	66K	compare (10)	20.1#20	15.3#23
Qwen3 Coder 30B A3B Instruct	Alibaba	0.070	0.260	262K	66K	compare (5)	20.0#21	19.4#17
QwQ 32B	Alibaba	0.150	0.200	131K	16K	compare (8)	19.7#22	N/A
DeepSeek R1	DeepSeek	0.280	0.400	164K	66K	compare (14)	18.8#23	15.9#21
Llama 3.1 405B Instruct	Meta	0.120	0.300	131K	16K	compare (11)	17.4#24	14.5#24
Qwen3 VL 32B Instruct	Alibaba	0.104	0.416	262K	33K	compare (3)	17.2#25	15.6#22
DeepSeek R1 Distill Qwen 32B	DeepSeek	0.150	0.150	131K	33K	compare (7)	17.2#26	N/A
Qwen3 235B A22B Instruct	Alibaba	0.090	0.580	262K	33K	compare (10)	17.0#27	14.0#28
DeepSeek V3	DeepSeek	0.200	0.200	164K	82K	compare (11)	16.5#28	16.4#20
Qwen3 VL 30B A3B Instruct	Alibaba	0.130	0.520	262K	33K	compare (5)	16.0#29	14.3#26
DeepSeek R1 Distill Llama 70B	DeepSeek	0.200	0.375	131K	16K	compare (11)	16.0#30	11.4#32
DeepSeek R1 Distill Qwen 14B	DeepSeek	0.070	0.070	131K	16K	compare (5)	15.8#31	N/A
Qwen2.5 72B Instruct	Alibaba	0.120	0.300	131K	16K	compare (8)	15.6#32	11.9#31
QwQ 32B Preview	Alibaba	0.287	0.861	33K	16K	compare (2)	15.2#33	N/A
Devstral Small	Mistral AI	0.100	0.300	256K	64K	compare (3)	15.2#34	12.1#30
Qwen3 30B A3B	Alibaba	0.080	0.290	131K	20K	compare (6)	15.0#35	14.2#27
Llama 3.3 70B Instruct	Meta	0.100	0.200	131K	120K	compare (20)	14.5#36	10.7#36
Qwen3 VL 8B Instruct	Alibaba	0.080	0.200	256K	33K	compare (5)	14.3#37	7.3#39
Llama 3.1 Nemotron 70B Instruct	NVIDIA	0.600	0.600	131K	16K	compare (2)	13.4#38	10.8#34
Qwen2.5 32B Instruct	Alibaba	0.060	0.200	131K	8K	compare (3)	13.2#39	N/A
Nemotron Nano 2 9B	NVIDIA	0.040	0.160	131K	16K	compare (5)	13.2#40	7.5#38
Qwen2.5 Coder 32B Instruct	Alibaba	0.050	0.100	131K	33K	compare (8)	12.9#41	N/A
GLM-4.5V	Zhipu AI	0.600	1.20	131K	32K	compare (6)	12.7#42	10.8#35
Qwen3 4B Instruct	Alibaba	0.010	0.030	262K	33K	compare (2)	12.5#44	9.0#37
Qwen3 30B A3B Instruct	Alibaba	0.048	0.193	262K	33K	compare (3)	12.5#43	13.3#29
Llama 3.1 70B Instruct	Meta	0.100	0.100	131K	16K	compare (13)	12.5#46	10.9#33
DeepSeek V2.5	DeepSeek	1.20	1.20	33K	N/A	compare (1)	12.5#45	N/A
DeepSeek R1 Distill Llama 8B	DeepSeek	0.025	0.025	131K	N/A	compare (3)	12.1#47	N/A
Llama 3.1 8B Instruct	Meta	0.020	0.030	200K	128K	compare (20)	11.8#48	4.9#42
Qwen2 72B Instruct	Alibaba	0.900	0.900	33K	N/A	compare (1)	11.7#49	N/A
Nemotron Nano 2 12B VL	NVIDIA	0.100	0.100	131K	4K	compare (2)	10.1#50	5.9#41
Qwen2.5 Coder 7B Instruct	Alibaba	0.010	0.030	131K	8K	compare (4)	10.0#51	N/A
Mixtral 8x22B Instruct	Mistral AI	0.600	0.600	66K	2K	compare (6)	9.8#52	N/A
Llama 3.2 3B Instruct	Meta	0.015	0.020	131K	80K	compare (9)	9.7#54	N/A
Llama 2 7B Chat	Meta	0.050	0.150	4K	4K	compare (4)	9.7#53	N/A
DeepSeek R1 Distill Qwen 1.5B	DeepSeek	0.090	0.090	131K	N/A	compare (3)	9.1#55	N/A
Llama 3 70B Instruct	Meta	0.120	0.300	131K	8K	compare (9)	8.9#56	6.8#40
Llama 2 70B Chat	Meta	0.500	0.900	4K	4K	compare (6)	8.4#58	N/A
Llama 2 13B Chat	Meta	0.100	0.200	4K	4K	compare (4)	8.4#57	N/A
Mixtral 8x7B Instruct	Mistral AI	0.070	0.150	33K	16K	compare (9)	7.7#59	N/A
Mistral 7B Instruct	Mistral AI	0.010	0.100	127K	16K	compare (9)	7.4#60	N/A
Llama 3 8B Instruct	Meta	0.030	0.040	32K	8K	compare (8)	6.4#61	4.0#43
Llama 3.2 1B Instruct	Meta	0.027	0.080	131K	60K	compare (5)	6.3#62	0.6#44
Chronos Hermes 2 13B	Nous Research	0.200	0.200	4K	4K	compare (1)	N/A	N/A
Code Llama 13B	Meta	0.200	0.200	16K	16K	compare (1)	N/A	N/A
Code Llama 13B Instruct	Meta	0.200	0.200	16K	16K	compare (1)	N/A	N/A
Code Llama 13B Python	Meta	0.200	0.200	16K	16K	compare (1)	N/A	N/A
Code Llama 34B	Meta	0.900	0.900	16K	16K	compare (1)	N/A	N/A
Code Llama 34B Instruct	Meta	0.350	0.900	16K	16K	compare (3)	N/A	N/A
Code Llama 34B Python	Meta	0.900	0.900	16K	16K	compare (1)	N/A	N/A
Code Llama 70B	Meta	0.900	0.900	4K	4K	compare (1)	N/A	N/A
Code Llama 70B Instruct	Meta	0.700	0.900	16K	16K	compare (3)	N/A	N/A
Code Llama 70B Python	Meta	0.900	0.900	4K	4K	compare (1)	N/A	N/A
Code Llama 7B	Meta	0.060	0.120	16K	16K	compare (2)	N/A	N/A
Code Llama 7B Instruct	Meta	0.200	0.200	16K	16K	compare (2)	N/A	N/A
Code Llama 7B Python	Meta	0.200	0.200	16K	16K	compare (1)	N/A	N/A
CodeGemma 2B	Google	0.100	0.100	8K	8K	compare (1)	N/A	N/A
CodeGemma 7B	Google	0.200	0.200	8K	8K	compare (1)	N/A	N/A
CodeQwen 1.5 7B	Alibaba	0.200	0.200	66K	N/A	compare (1)	N/A	N/A
Cogito V1 Preview Llama 3B	DeepCogito	0.100	0.100	131K	N/A	compare (1)	N/A	N/A
Cogito V1 Preview Llama 70B	DeepCogito	0.900	0.900	131K	N/A	compare (1)	N/A	N/A
Cogito V1 Preview Llama 8B	DeepCogito	0.200	0.200	131K	N/A	compare (1)	N/A	N/A
Cogito V1 Preview Qwen 14B	DeepCogito	0.200	0.200	131K	N/A	compare (1)	N/A	N/A
Cogito V1 Preview Qwen 32B	DeepCogito	0.900	0.900	131K	N/A	compare (1)	N/A	N/A
Cogito V2 671B P1	DeepCogito	1.20	1.20	164K	N/A	compare (1)	N/A	N/A
DBRX Instruct	Databricks	1.20	1.20	33K	N/A	compare (1)	N/A	N/A
DeepSeek Coder 1.3B Base	DeepSeek	0.100	0.100	16K	16K	compare (1)	N/A	N/A
DeepSeek Coder 2 Instruct	DeepSeek	1.20	1.20	66K	8K	compare (1)	N/A	N/A
DeepSeek Coder 33B Instruct	DeepSeek	0.900	0.900	16K	16K	compare (1)	N/A	N/A
DeepSeek Coder 7B Base	DeepSeek	0.200	0.200	4K	4K	compare (1)	N/A	N/A
DeepSeek Coder 7B Base v1.5	DeepSeek	0.200	0.200	4K	4K	compare (1)	N/A	N/A
DeepSeek Coder 7B Instruct v1.5	DeepSeek	0.200	0.200	4K	4K	compare (1)	N/A	N/A
DeepSeek Coder V2 Lite Base	DeepSeek	0.500	0.500	164K	8K	compare (1)	N/A	N/A
DeepSeek Coder V2 Lite Instruct	DeepSeek	0.500	0.500	164K	8K	compare (1)	N/A	N/A
DeepSeek Prover V2	DeepSeek	1.20	1.20	164K	N/A	compare (1)	N/A	N/A
DeepSeek R1 528	DeepSeek	0.200	0.250	164K	33K	compare (12)	N/A	N/A
DeepSeek R1 Basic	DeepSeek	0.550	2.19	128K	20K	compare (1)	N/A	N/A
DeepSeek R1 Distill Qwen 7B	DeepSeek	0.072	0.144	131K	16K	compare (4)	N/A	N/A
DeepSeek R1 Distill Qwen3 8B	DeepSeek	0.200	0.200	131K	N/A	compare (1)	N/A	N/A
DeepSeek V2 Lite Chat	DeepSeek	0.500	0.500	164K	N/A	compare (1)	N/A	N/A
Dobby Llama 3.1 Mini 8B Unhinged Plus	Sentientai	0.200	0.200	131K	N/A	compare (1)	N/A	N/A
Dobby Llama 3.3 70B Unhinged	Sentientai	0.900	0.900	131K	N/A	compare (1)	N/A	N/A
Dolphin 2.6 Mixtral 8x7B	Cognitive Computations	0.500	0.500	33K	N/A	compare (1)	N/A	N/A
Dolphin 2.9.2 Qwen2 72B	Cognitive Computations	0.900	0.900	131K	N/A	compare (1)	N/A	N/A
ERNIE 4.5 21B A3B PT	Baidu	0.100	0.100	4K	4K	compare (1)	N/A	N/A
ERNIE 4.5 300B A47B PT	Baidu	0.100	0.100	4K	4K	compare (1)	N/A	N/A
FireFunction V1	Fireworks AI	0.500	0.500	33K	N/A	compare (1)	N/A	N/A
FireFunction V2	Fireworks AI	0.900	0.900	8K	8K	compare (1)	N/A	N/A
FireLLaVA 13B	Fireworks AI	0.200	0.200	4K	4K	compare (1)	N/A	N/A
Firesearch OCR V6	Fireworks AI	0.200	0.200	8K	8K	compare (1)	N/A	N/A
FLUX.1 Dev	Black Forest Labs	0.100	0.100	4K	4K	compare (1)	N/A	N/A
FLUX.1 Dev ControlNet Union	Black Forest Labs	0.0010	0.0010	4K	4K	compare (1)	N/A	N/A
FLUX.1 Schnell	Black Forest Labs	0.100	0.100	4K	4K	compare (1)	N/A	N/A
Gemma 2 9B Instruct	Google	0.200	0.200	8K	8K	compare (2)	N/A	N/A
Gemma 2B Instruct	Google	0.100	0.100	8K	8K	compare (1)	N/A	N/A
Gemma 3 27B Instruct	Google	0.060	0.160	131K	16K	compare (6)	N/A	N/A
Gemma 7B	Google	0.200	0.200	8K	8K	compare (1)	N/A	N/A
Gemma 7B IT	Google	0.050	0.080	8K	8K	compare (3)	N/A	N/A
GPT OSS 120B Safeguard	OpenAI	0.150	0.600	131K	66K	compare (2)	N/A	N/A
GPT OSS 20B Safeguard	OpenAI	0.070	0.200	131K	66K	compare (5)	N/A	N/A
GTE Base	Alibaba	0.0080	N/A	512	N/A	compare (1)	N/A	N/A
GTE Large	Alibaba	0.016	N/A	512	N/A	compare (1)	N/A	N/A
Hermes 2 Mixtral 8x7B DPO	Nous Research	0.500	0.500	33K	N/A	compare (1)	N/A	N/A
Hermes 2 Yi 34B	Nous Research	0.900	0.900	4K	4K	compare (1)	N/A	N/A
Hermes Llama2 13B	Nous Research	0.200	0.200	4K	4K	compare (1)	N/A	N/A
Hermes Llama2 70B	Nous Research	0.900	0.900	4K	4K	compare (1)	N/A	N/A
Hermes Llama2 7B	Nous Research	0.200	0.200	4K	4K	compare (1)	N/A	N/A
InternVL3 38B	InternLM	0.900	0.900	16K	16K	compare (1)	N/A	N/A
InternVL3 78B	InternLM	0.900	0.900	16K	16K	compare (1)	N/A	N/A
InternVL3 8B	InternLM	0.200	0.200	16K	16K	compare (1)	N/A	N/A
Kimi K2 Instruct	Moonshot AI (Kimi)	0.500	2.00	262K	33K	compare (9)	N/A	N/A
KwaiPilot KAT 32B Dev	KwaiPilot	0.900	0.900	131K	N/A	compare (1)	N/A	N/A
KwaiPilot KAT 72B Dev Exp	KwaiPilot	0.900	0.900	131K	N/A	compare (1)	N/A	N/A
KwaiPilot KAT Coder	KwaiPilot	0.900	0.900	262K	N/A	compare (1)	N/A	N/A
Llama 2 13B	Meta	0.100	0.200	4K	4K	compare (2)	N/A	N/A
Llama 2 70B	Meta	0.100	0.100	4K	4K	compare (2)	N/A	N/A
Llama 2 7B	Meta	0.050	0.200	4K	4K	compare (2)	N/A	N/A
Llama 3 8B	Meta	0.050	0.080	8K	8K	compare (4)	N/A	N/A
Llama 3.1 405B Instruct Long	Meta	0.100	0.100	4K	4K	compare (1)	N/A	N/A
Llama 3.2 11B Vision Instruct	Meta	0.015	0.025	131K	16K	compare (7)	N/A	N/A
Llama 3.2 1B	Meta	0.050	0.050	131K	8K	compare (3)	N/A	N/A
Llama 3.2 3B	Meta	0.040	0.075	131K	8K	compare (4)	N/A	N/A
Llama 3.2 90B Vision Instruct	Meta	0.900	0.900	128K	16K	compare (4)	N/A	N/A
Llama 4 Maverick Instruct	Meta	0.220	0.880	131K	N/A	compare (1)	N/A	N/A
Llama 4 Scout Instruct	Meta	0.150	0.600	131K	N/A	compare (1)	N/A	N/A
Llama Guard 7B	Meta	0.200	0.200	4K	4K	compare (1)	N/A	N/A
LlamaGuard 2 8B	Meta	0.200	0.200	8K	8K	compare (1)	N/A	N/A
LlamaGuard 3 1B	Meta	0.100	0.100	131K	N/A	compare (1)	N/A	N/A
LlamaGuard 3 8B	Meta	0.020	0.030	131K	16K	compare (5)	N/A	N/A
LLaVA Yi 34B	01.AI	0.900	0.900	4K	4K	compare (1)	N/A	N/A
Ministral 3 14B Instruct	Mistral AI	0.200	0.200	256K	8K	compare (2)	N/A	N/A
Ministral 3 3B Instruct	Mistral AI	0.100	0.100	256K	8K	compare (2)	N/A	N/A
Ministral 3 8B Instruct	Mistral AI	0.150	0.150	256K	8K	compare (2)	N/A	N/A
Mistral 3 7B Instruct	Mistral AI	0.200	0.200	33K	N/A	compare (1)	N/A	N/A
Mistral 7B	Mistral AI	0.050	0.100	33K	8K	compare (5)	N/A	N/A
Mistral 7B OpenOrca	Openorca	0.200	0.200	33K	N/A	compare (1)	N/A	N/A
Mistral Small 24B Instruct	Mistral AI	0.050	0.080	33K	16K	compare (3)	N/A	N/A
Mixtral 8x22B	Mistral AI	1.20	1.20	66K	8K	compare (2)	N/A	N/A
Mixtral 8x7B	Mistral AI	0.500	0.500	33K	8K	compare (3)	N/A	N/A
MythoMax L2 13B	Gryphe	0.060	0.060	4K	4K	compare (4)	N/A	N/A
Nemo Base (24.07)	Mistral AI	0.200	0.200	128K	N/A	compare (1)	N/A	N/A
Nemo Instruct (24.07)	Mistral AI	0.020	0.040	131K	512	compare (5)	N/A	N/A
Nemotron Nano 2 12B	NVIDIA	0.200	0.200	131K	8K	compare (2)	N/A	N/A
Nomic Embed Text 1	Nomic AI	0.0080	N/A	8K	N/A	compare (1)	N/A	N/A
Nomic Embed Text 1.5	Nomic AI	0.0080	N/A	8K	N/A	compare (1)	N/A	N/A
Nous Capybara 7B V1.9	Nous Research	0.200	0.200	33K	N/A	compare (1)	N/A	N/A
OpenChat 3.5 7B	OpenChat	0.200	0.200	8K	8K	compare (1)	N/A	N/A
Phi-2 3B	Microsoft	0.100	0.100	2K	2K	compare (1)	N/A	N/A
Phi-3 Mini Instruct	Microsoft	0.100	0.100	131K	4K	compare (2)	N/A	N/A
Phi-3 Vision Instruct	Microsoft	0.200	0.200	32K	N/A	compare (1)	N/A	N/A
Phind CodeLlama 34B Python V1	Phind	0.900	0.900	16K	16K	compare (1)	N/A	N/A
Phind CodeLlama 34B V1	Phind	0.900	0.900	16K	16K	compare (1)	N/A	N/A
Phind CodeLlama 34B V2	Phind	0.900	0.900	16K	16K	compare (1)	N/A	N/A
Pythia 12B	EleutherAI	0.200	0.200	2K	2K	compare (1)	N/A	N/A
Qwen1.5 72B Chat	Alibaba	0.900	0.900	33K	N/A	compare (1)	N/A	N/A
Qwen2 7B Instruct	Alibaba	0.200	0.200	33K	N/A	compare (1)	N/A	N/A
Qwen2 VL 2B Instruct	Alibaba	0.100	0.100	33K	N/A	compare (1)	N/A	N/A
Qwen2 VL 72B Instruct	Alibaba	0.130	0.400	131K	2K	compare (3)	N/A	N/A
Qwen2 VL 7B Instruct	Alibaba	0.020	0.060	131K	N/A	compare (2)	N/A	N/A
Qwen2.5 0.5B Instruct	Alibaba	0.100	0.100	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 1.5B Instruct	Alibaba	0.100	0.100	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 14B	Alibaba	0.200	0.200	131K	N/A	compare (1)	N/A	N/A
Qwen2.5 14B Instruct	Alibaba	0.200	0.200	131K	8K	compare (2)	N/A	N/A
Qwen2.5 32B	Alibaba	0.900	0.900	131K	N/A	compare (1)	N/A	N/A
Qwen2.5 72B	Alibaba	0.900	0.900	131K	N/A	compare (1)	N/A	N/A
Qwen2.5 7B	Alibaba	0.200	0.200	131K	N/A	compare (1)	N/A	N/A
Qwen2.5 7B Instruct	Alibaba	0.040	0.070	131K	33K	compare (5)	N/A	N/A
Qwen2.5 Coder 0.5B	Alibaba	0.100	0.100	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 Coder 0.5B Instruct	Alibaba	0.100	0.100	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 Coder 1.5B	Alibaba	0.100	0.100	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 Coder 1.5B Instruct	Alibaba	0.100	0.100	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 Coder 14B	Alibaba	0.200	0.200	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 Coder 14B Instruct	Alibaba	0.200	0.200	131K	8K	compare (2)	N/A	N/A
Qwen2.5 Coder 32B	Alibaba	0.900	0.900	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 Coder 3B	Alibaba	0.100	0.100	33K	N/A	compare (1)	N/A	N/A
Qwen2.5 Coder 3B Instruct	Alibaba	0.010	0.030	33K	N/A	compare (3)	N/A	N/A
Qwen2.5 Coder 7B	Alibaba	0.010	0.030	33K	8K	compare (3)	N/A	N/A
Qwen2.5 Math 72B Instruct	Alibaba	0.574	0.900	4K	4K	compare (2)	N/A	N/A
Qwen2.5 VL 32B Instruct	Alibaba	0.200	0.600	131K	8K	compare (3)	N/A	N/A
Qwen2.5 VL 3B Instruct	Alibaba	0.200	0.200	131K	8K	compare (2)	N/A	N/A
Qwen2.5 VL 72B Instruct	Alibaba	0.130	0.400	131K	8K	compare (7)	N/A	N/A
Qwen2.5 VL 7B Instruct	Alibaba	0.200	0.200	131K	8K	compare (2)	N/A	N/A
Qwen3 0.6B	Alibaba	0.100	0.100	41K	8K	compare (2)	N/A	N/A
Qwen3 1.7B	Alibaba	0.100	0.100	131K	8K	compare (2)	N/A	N/A
Qwen3 1.7B FP8 Draft	Alibaba	0.100	0.100	262K	N/A	compare (1)	N/A	N/A
Qwen3 1.7B FP8 Draft 131072	Alibaba	0.100	0.100	131K	N/A	compare (1)	N/A	N/A
Qwen3 1.7B FP8 Draft 40960	Alibaba	0.100	0.100	41K	N/A	compare (1)	N/A	N/A
Qwen3 14B	Alibaba	0.060	0.200	132K	41K	compare (7)	N/A	N/A
Qwen3 235B A22B	Alibaba	0.090	0.100	262K	131K	compare (9)	N/A	N/A
Qwen3 235B A22B Thinking	Alibaba	0.100	0.100	262K	33K	compare (9)	N/A	N/A
Qwen3 30B A3B Thinking	Alibaba	0.080	0.400	262K	33K	compare (3)	N/A	N/A
Qwen3 32B	Alibaba	0.050	0.100	131K	41K	compare (15)	N/A	N/A
Qwen3 4B	Alibaba	0.030	0.030	131K	20K	compare (4)	N/A	N/A
Qwen3 8B	Alibaba	0.035	0.138	131K	20K	compare (6)	N/A	N/A
Qwen3 Coder 480B Instruct BF16	Alibaba	0.900	0.900	4K	4K	compare (1)	N/A	N/A
Qwen3 Next 80B A3B Thinking	Alibaba	0.098	0.780	262K	66K	compare (10)	N/A	N/A
Qwen3 VL 235B A22B Thinking	Alibaba	0.220	0.880	262K	33K	compare (5)	N/A	N/A
Qwen3 VL 30B A3B Thinking	Alibaba	0.130	0.600	262K	33K	compare (5)	N/A	N/A
Rolm OCR	Rolm	0.200	0.200	128K	N/A	compare (1)	N/A	N/A
Snorkel Mistral PairRM DPO	Snorkel	0.200	0.200	33K	N/A	compare (1)	N/A	N/A
StableCode 3B	Stability AI	0.100	0.100	4K	4K	compare (1)	N/A	N/A
StarCoder 16B	BigCode	0.200	0.200	8K	8K	compare (1)	N/A	N/A
StarCoder 7B	BigCode	0.200	0.200	8K	8K	compare (1)	N/A	N/A
StarCoder2 15B	BigCode	0.200	0.200	16K	16K	compare (1)	N/A	N/A
StarCoder2 3B	BigCode	0.100	0.100	16K	16K	compare (1)	N/A	N/A
StarCoder2 7B	BigCode	0.200	0.200	16K	16K	compare (1)	N/A	N/A
UAE 1 Large	Whereisai	0.016	N/A	512	N/A	compare (1)	N/A	N/A
Yi 34B	01.AI	0.900	0.900	4K	4K	compare (1)	N/A	N/A
Yi 34B 200K Capybara	01.AI	0.900	0.900	200K	N/A	compare (1)	N/A	N/A
Yi 34B Chat	01.AI	0.900	0.900	4K	4K	compare (1)	N/A	N/A
Yi 6B	01.AI	0.200	0.200	4K	4K	compare (1)	N/A	N/A
Yi Large	01.AI	3.00	3.00	33K	N/A	compare (1)	N/A	N/A
Zephyr 7B Beta	Hugging Face	0.150	0.150	33K	16K	compare (2)	N/A	N/A

AI Model Comparison