LLM API Providers Leaderboard - Comparison of over 500 AI Model endpoints

Comparison of API provider performance across over 500 AI Model endpoints, including from OpenAI, Google, DeepSeek and others, across performance key metrics including price, output speed, latency, context window and more.

For more details including relating to our methodology, see our FAQs.

Reasoning model


										Further Analysis
Anthropic	Claude Fable 5 (with fallback)	1M	Proprietary	60	$2.75	73	129.10	135.94	--	Model Provider
Google	Claude Fable 5 (with fallback)	1M	Proprietary	60	$2.90	73	103.59	110.39	--	Model Provider
Microsoft Azure	Claude Fable 5 (with fallback)	1M	Proprietary	60	$7.96	69	134.72	141.94	--	Model Provider
OpenAI	GPT-5.6 Sol (max)	1M	Proprietary	59	$1.04	63	154.71	162.59	--	Model Provider
OpenAI	GPT-5.6 Sol (xhigh)	1M	Proprietary	58	$0.68	64	60.80	68.56	--	Model Provider
Kimi	Kimi K3	1.05M	Proprietary	57	$0.95	34	6.38	80.08	58.96	Model Provider
OpenAI	GPT-5.6 Sol (high)	1M	Proprietary	56	$0.45	58	12.98	21.56	--	Model Provider
Anthropic	Claude Opus 4.8 (max)	1M	Proprietary	56	$1.80	59	33.71	42.20	--	Model Provider
Amazon Bedrock	Claude Opus 4.8 (max)	1M	Proprietary	56	$1.78	65	18.93	26.64	--	Model Provider
Google	Claude Opus 4.8 (max)	1M	Proprietary	56	$2.39	68	23.56	30.91	--	Model Provider
OpenAI	GPT-5.6 Terra (max)	1M	Proprietary	55	$0.82	137	157.39	161.05	--	Model Provider
SpaceXAI	Grok 4.5 (high)	500k	Proprietary	54	$0.31	70	11.14	18.29	--	Model Provider
OpenAI	GPT-5.6 Sol (medium)	1M	Proprietary	54	$0.31	55	6.72	15.76	--	Model Provider
Google	Claude Sonnet 5 (max)	1M	Proprietary	53	$2.92	73	166.18	173.01	--	Model Provider
Microsoft Azure	Claude Sonnet 5 (max)	1M	Proprietary	53	$2.19	81	195.09	201.29	--	Model Provider
Anthropic	Claude Sonnet 5 (max)	1M	Proprietary	53	$1.53	79	175.45	181.81	--	Model Provider
Amazon Bedrock	Claude Sonnet 5 (max)	1M	Proprietary	53	$2.60	71	170.13	177.15	--	Model Provider
OpenAI	GPT-5.6 Terra (xhigh)	1M	Proprietary	52	$0.48	122	20.40	24.50	--	Model Provider
OpenAI	GPT-5.6 Luna (max)	1M	Proprietary	51	$0.21	181	134.26	137.02	--	Model Provider
Wafer	GLM-5.2 (max)	205k	Open	51	$0.32	168	3.94	18.85	11.93	Model Provider
FriendliAI	GLM-5.2 (max)	1M	Open	51	$0.37	231	1.46	12.30	8.67	Model Provider
Makora	GLM-5.2 (max) (NVFP4)	1M	Open	51	$0.44	167	0.82	15.83	12.00	Model Provider
Novita	GLM-5.2 (max) (FP8)	1.05M	Open	51	--	39	2.16	65.46	50.64	Model Provider
GMI	GLM-5.2 (max) (FP8)	1.05M	Open	51	--	--	--	--	--	Model Provider
Parasail	GLM-5.2 (max) (NVFP4)	1M	Open	51	--	198	1.23	13.85	10.09	Model Provider
CoreWeave	GLM-5.2 (max)	262k	Open	51	--	121	1.38	21.99	16.48	Model Provider
Baseten	GLM-5.2 (max)	261k	Open	51	--	380	0.93	7.51	5.26	Model Provider
Together AI	GLM-5.2 (max)	262k	Open	51	--	399	1.04	7.31	5.02	Model Provider
DeepInfra	GLM-5.2 (max) (FP4)	1.05M	Open	51	--	48	1.10	52.85	41.40	Model Provider
Nebius	GLM-5.2 (max) (FP4)	432k	Open	51	--	206	0.66	12.80	9.71	Model Provider
Blackbox AI	GLM-5.2 (max)	1.05M	Open	51	--	410	1.86	7.95	4.87	Model Provider
Databricks	GLM-5.2 (max)	1M	Open	51	--	314	0.98	8.94	6.37	Model Provider
Scaleway	GLM-5.2 (max)	262k	Open	51	--	77	1.74	34.33	26.07	Model Provider
Crusoe	GLM-5.2 (max) (NVFP4)	262k	Open	51	$0.32	435	0.87	6.62	4.59	Model Provider
Fireworks	GLM-5.2 (max)	1M	Open	51	--	299	1.11	9.47	6.69	Model Provider
SiliconFlow	GLM-5.2 (max) (FP8)	1.05M	Open	51	$0.57	56	1.93	46.56	35.70	Model Provider
Meta	Muse Spark 1.1 (xhigh)	1.05M	Proprietary	51	$0.26	120	1.40	22.30	16.72	Model Provider
Google	Gemini 3.5 Flash AI Studio	1M	Proprietary	50	$0.59	183	17.98	20.71	--	Model Provider
Google	Gemini 3.6 Flash AI Studio	1M	Proprietary	50	$0.50	248	14.00	16.02	--	Model Provider
OpenAI	GPT-5.6 Sol (low)	1M	Proprietary	49	$0.20	55	3.41	12.52	--	Model Provider
OpenAI	GPT-5.6 Luna (xhigh)	1M	Proprietary	49	$0.14	169	46.69	49.64	--	Model Provider
OpenAI	GPT-5.6 Terra (high)	1M	Proprietary	49	$0.34	124	2.45	6.48	--	Model Provider
Google	Gemini 3.1 Pro Preview (AI Studio)	1M	Proprietary	46	$0.29	116	30.08	34.40	--	Model Provider
Google	Gemini 3.1 Pro Preview (Vertex)	1M	Proprietary	46	$0.36	123	32.16	36.23	--	Model Provider
OpenAI	GPT-5.6 Luna (high)	1M	Proprietary	46	$0.09	161	8.70	11.81	--	Model Provider
Alibaba Cloud	Qwen3.7 Max	991k	Proprietary	46	$1.03	196	2.47	17.27	12.26	Model Provider
GMI	Qwen3.7 Max (FP8)	262k	Proprietary	46	--	--	--	--	--	Model Provider
Novita	Qwen3.7 Max	1M	Proprietary	46	$0.52	52	2.06	58.00	46.32	Model Provider
OpenAI	GPT-5.6 Terra (medium)	1M	Proprietary	46	$0.18	123	1.63	5.70	--	Model Provider
Google	Gemini 3.5 Flash (medium)	1M	Proprietary	45*	--	193	20.64	23.23	--	Model Provider
Parasail	MiniMax-M3 (MXFP8)	1M	Open	44	$0.17	77	1.38	33.87	26.00	Model Provider
CoreWeave	MiniMax-M3	262k	Open	44	$0.12	365	0.98	7.84	5.49	Model Provider
Together AI	MiniMax-M3	1M	Open	44	$0.18	119	0.72	21.79	16.85	Model Provider
Novita	MiniMax-M3	1M	Open	44	$0.13	103	1.23	25.44	19.37	Model Provider
Nebius	MiniMax-M3 (FP8)	1.05M	Open	44	--	206	1.90	14.04	9.72	Model Provider
SiliconFlow	MiniMax-M3	1M	Open	44	$0.22	103	1.55	25.81	19.40	Model Provider
MiniMax	MiniMax-M3	512k	Open	44	$0.12	96	1.28	27.24	20.77	Model Provider
GMI	MiniMax-M3	1.05M	Open	44	--	--	--	--	--	Model Provider
DeepInfra	DeepSeek V4 Pro (max) (FP4)	1.05M	Open	44	--	56	1.31	88.70	78.42	Model Provider
Microsoft Azure	DeepSeek V4 Pro (max)	1M	Open	44	--	57	2.12	87.51	76.64	Model Provider
SiliconFlow	DeepSeek V4 Pro (max)	1.05M	Open	44	$0.31	58	1.94	86.28	75.69	Model Provider
Novita	DeepSeek V4 Pro (max)	1.05M	Open	44	--	62	1.79	80.97	71.06	Model Provider
Makora	DeepSeek V4 Pro (max)	1M	Open	44	$0.65	162	0.83	30.86	26.95	Model Provider
GMI	DeepSeek V4 Pro (max)	1.05M	Open	44	--	--	--	--	--	Model Provider
Nebius	DeepSeek V4 Pro (max)	1M	Open	44	$0.77	42	2.18	117.58	103.57	Model Provider
Together AI	DeepSeek V4 Pro (max)	512k	Open	44	$0.29	332	1.03	15.70	13.16	Model Provider
Fireworks	DeepSeek V4 Pro (max)	1.05M	Open	44	$0.76	179	1.72	29.03	24.50	Model Provider
DeepSeek	DeepSeek V4 Pro (max)	1M	Open	44	$0.04	68	1.69	73.82	64.74	Model Provider
OpenAI	GPT-5.3 Codex (xhigh)	400k	Proprietary	44*	--	128	76.66	80.57	--	Model Provider
DeepInfra	DeepSeek V4 Pro (high) (FP4)	65.5k	Open	43	--	60	1.18	42.65	33.15	Model Provider
Fireworks	DeepSeek V4 Pro (high)	1.05M	Open	43	$0.85	177	1.34	15.44	11.26	Model Provider
Microsoft Azure	DeepSeek V4 Pro (high)	1M	Open	43	--	56	1.59	46.12	35.59	Model Provider
DeepSeek	DeepSeek V4 Pro (high)	1M	Open	43	$0.04	68	1.58	38.36	29.40	Model Provider
SiliconFlow	DeepSeek V4 Pro (high) (FP8)	1.05M	Open	43	$0.30	52	1.89	49.72	38.23	Model Provider
Nebius	DeepSeek V4 Pro (high)	1M	Open	43	$0.85	42	1.92	61.18	47.37	Model Provider
Together AI	DeepSeek V4 Pro (high)	512k	Open	43	$0.25	333	0.99	8.48	5.98	Model Provider
Makora	DeepSeek V4 Pro (high)	1M	Open	43	$0.71	146	0.81	17.86	13.62	Model Provider
Novita	DeepSeek V4 Pro (high)	1.05M	Open	43	--	67	1.90	38.96	29.62	Model Provider
Baseten	DeepSeek V4 Pro (high)	131k	Open	43	--	120	0.83	21.53	16.54	Model Provider
Anthropic	Claude Opus 4.7 (Non-reasoning, high)	1M	Proprietary	43*	--	46	1.82	12.59	--	Model Provider
Amazon Bedrock	Claude Opus 4.7 (Non-reasoning, high)	1M	Proprietary	43*	--	64	1.77	9.56	--	Model Provider
Novita	MiMo-V2.5-Pro	1.05M	Open	42	$0.04	69	2.96	39.25	29.03	Model Provider
GMI	MiMo-V2.5-Pro	1.05M	Open	42	--	--	--	--	--	Model Provider
DeepInfra	MiMo-V2.5-Pro	65.5k	Open	42	$0.28	79	0.78	32.23	25.16	Model Provider
Xiaomi	MiMo-V2.5-Pro	1M	Open	42	$0.03	65	2.80	41.50	30.96	Model Provider
Nebius	Kimi K2.7 Code (FP4)	256k	Open	42	--	26	1.91	105.44	84.56	Model Provider
GMI	Kimi K2.7 Code (FP8)	65.5k	Open	42	--	43	6.67	70.08	51.79	Model Provider
CoreWeave	Kimi K2.7 Code	262k	Open	42	--	261	1.15	11.59	8.53	Model Provider
Parasail	Kimi K2.7 Code	262k	Open	42	$0.16	45	1.64	62.32	49.57	Model Provider
Together AI	Kimi K2.7 Code	262k	Open	42	$0.27	190	0.55	14.95	11.76	Model Provider
Novita	Kimi K2.7 Code	262k	Open	42	--	46	3.26	62.65	48.51	Model Provider
Crusoe	Kimi K2.7 Code (NVFP4)	262k	Open	42	$0.19	463	0.64	6.53	4.81	Model Provider
Databricks	Kimi K2.7 Code	262k	Open	42	--	152	1.07	18.98	14.63	Model Provider
DeepInfra	Kimi K2.7 Code	262k	Open	42	--	50	0.77	54.99	44.29	Model Provider
Makora	Kimi K2.7 Code	262k	Open	42	$0.45	286	0.55	10.09	7.79	Model Provider
Kimi	Kimi K2.7 Code	256k	Open	42	--	46	2.92	61.76	48.06	Model Provider
Anthropic	Claude Sonnet 5 (Non-reasoning)	1M	Proprietary	42	$0.37	66	1.31	8.91	--	Model Provider
Databricks	Claude Sonnet 5 (Non-reasoning)	524k	Proprietary	42	$0.42	67	2.76	10.25	--	Model Provider
Novita	Hy3	262k	Open	41	$0.03	59	2.67	45.40	34.19	Model Provider
DeepInfra	Hy3 (FP8)	262k	Open	41	$0.03	48	0.77	52.44	41.34	Model Provider
GMI	Hy3	262k	Open	41	$0.03	71	3.53	38.88	28.28	Model Provider
OpenAI	GPT-5.6 Sol (Non-reasoning)	1M	Proprietary	41	$0.20	50	1.00	11.09	--	Model Provider
SiliconFlow	Nex-N2-Pro (FP8)	262k	Open	41	--	136	1.61	20.06	14.76	Model Provider
Thinking Machines	Inkling	262k	Open	41	--	61	1.87	42.73	32.69	Model Provider
OpenAI	GPT-5.6 Terra (low)	1M	Proprietary	40	$0.15	123	1.46	5.54	--	Model Provider
GMI	DeepSeek V4 Flash (max)	1.05M	Open	40	--	--	--	--	--	Model Provider
Makora	DeepSeek V4 Flash (max)	1M	Open	40	--	166	0.70	37.64	33.91	Model Provider
DeepInfra	DeepSeek V4 Flash (max) (FP4)	1.05M	Open	40	--	34	1.18	182.51	166.50	Model Provider
SiliconFlow	DeepSeek V4 Flash (max) (FP8)	1.05M	Open	40	$0.08	25	1.79	246.07	224.29	Model Provider
Parasail	DeepSeek V4 Flash (max) (FP8)	1.05M	Open	40	--	41	1.73	151.34	137.37	Model Provider
Novita	DeepSeek V4 Flash (max)	1.05M	Open	40	$0.06	108	1.88	58.72	52.18	Model Provider
DeepSeek	DeepSeek V4 Flash (max)	1M	Open	40	$0.02	121	1.21	51.77	46.43	Model Provider
Alibaba Cloud	Qwen3.6 Plus	1M	Proprietary	40	$0.31	53	2.65	117.38	105.25	Model Provider
Alibaba Cloud	Qwen3.7 Plus	1M	Proprietary	39	$0.21	53	2.91	49.90	37.60	Model Provider
OpenAI	GPT-5.6 Luna (medium)	1M	Proprietary	38	$0.05	170	3.02	5.96	--	Model Provider
CoreWeave	Nemotron 3 Ultra	262k	Open	38	$0.15	222	1.18	13.67	10.24	Model Provider
GMI	Nemotron 3 Ultra	262k	Open	38	--	--	--	--	--	Model Provider
Together AI	Nemotron 3 Ultra	512k	Open	38	--	154	0.72	18.72	14.75	Model Provider
DeepInfra	Nemotron 3 Ultra	262k	Open	38	$0.14	69	6.14	46.63	33.19	Model Provider
DeepInfra	Nemotron 3 Ultra BF16	262k	Open	38	--	--	--	--	--	Model Provider
Nebius	Nemotron 3 Ultra	256k	Open	38	$0.54	355	2.26	10.07	6.41	Model Provider
Lightning AI	Nemotron 3 Ultra	262k	Open	38	$0.22	76	1.03	37.45	29.85	Model Provider
Blackbox AI	Nemotron 3 Ultra	262k	Open	38	$0.20	470	1.10	7.00	4.84	Model Provider
CoreWeave	DeepSeek V4 Flash (high)	1M	Open	37	$0.07	38	1.58	47.42	32.67	Model Provider
DeepInfra	DeepSeek V4 Flash (high) (FP4)	1.05M	Open	37	--	33	1.03	54.55	38.14	Model Provider
GMI	DeepSeek V4 Flash (high)	1.05M	Open	37	--	--	--	--	--	Model Provider
Makora	DeepSeek V4 Flash (high)	1M	Open	37	--	163	0.86	11.55	7.62	Model Provider
Parasail	DeepSeek V4 Flash (high) (FP8)	1.05M	Open	37	--	43	1.99	42.84	29.11	Model Provider
SiliconFlow	DeepSeek V4 Flash (high) (FP8)	1.05M	Open	37	$0.05	35	1.99	52.39	35.91	Model Provider
Novita	DeepSeek V4 Flash (high)	1.05M	Open	37	$0.04	108	1.89	17.93	11.43	Model Provider
DeepSeek	DeepSeek V4 Flash (high)	1M	Open	37	$0.01	116	1.14	16.16	10.71	Model Provider
Novita	MiMo-V2.5	1.05M	Open	37	--	67	3.79	41.10	29.85	Model Provider
Parasail	MiMo-V2.5	1M	Open	37	--	58	1.15	44.24	34.47	Model Provider
DeepInfra	MiMo-V2.5	262k	Open	37	--	42	0.98	60.18	47.36	Model Provider
GMI	MiMo-V2.5	1.05M	Open	37	$0.08	--	--	--	--	Model Provider
Xiaomi	MiMo-V2.5	1M	Open	37	$0.01	66	3.06	40.90	30.27	Model Provider
DeepInfra	Qwen3.6 27B FP8	262k	Open	37	--	51	1.45	122.47	111.23	Model Provider
Groq	Qwen3.6 27B	131k	Open	37	--	449	1.19	14.96	12.65	Model Provider
Novita	Qwen3.6 27B	262k	Open	37	$0.27	55	2.86	115.56	103.57	Model Provider
Alibaba Cloud	Qwen3.6 27B	262k	Open	37	$0.27	56	3.73	114.34	101.65	Model Provider
SiliconFlow	Qwen3.6 27B (FP8)	262k	Open	37	$0.17	41	3.41	155.90	140.14	Model Provider
Makora	Qwen3.6 27B FP4	256k	Open	37	--	42	3.07	151.68	136.58	Model Provider
Google	Gemini 3.5 Flash-Lite AI Studio	1M	Proprietary	36	$0.09	450	9.82	10.93	--	Model Provider
Amazon Bedrock	Grok 4.3 (medium)	524k	Proprietary	36*	--	210	8.33	10.70	--	Model Provider
Microsoft Azure	Grok 4.3 (medium)	200k	Proprietary	36*	--	88	15.70	21.38	--	Model Provider
SpaceXAI	Grok 4.3 (medium)	1M	Proprietary	36*	--	104	14.29	19.11	--	Model Provider
Amazon Bedrock	Grok 4.3 (low)	524k	Proprietary	35*	--	203	3.86	6.33	--	Model Provider
Microsoft Azure	Grok 4.3 (low)	200k	Proprietary	35*	--	82	8.09	14.20	--	Model Provider
SpaceXAI	Grok 4.3 (low)	1M	Proprietary	35*	--	104	6.77	11.58	--	Model Provider
Google	Gemini 3.5 Flash (minimal) AI Studio	1M	Proprietary	35*	--	158	1.00	4.16	--	Model Provider
Clarifai	Kimi K2.6	262k	Open	35*	--	--	--	--	--	Model Provider
Together AI	Kimi K2.6 (FP4)	262k	Open	35*	--	417	0.57	1.77	--	Model Provider
SiliconFlow	Kimi K2.6 (FP8)	262k	Open	35*	--	39	1.87	14.76	--	Model Provider
Fireworks	Kimi K2.6	262k	Open	35*	--	309	0.68	2.31	--	Model Provider
Parasail	Kimi K2.6 (INT4)	262k	Open	35*	--	36	1.94	15.93	--	Model Provider
DeepInfra	Kimi K2.6 (FP4)	262k	Open	35*	--	35	0.71	15.09	--	Model Provider
CoreWeave	Kimi K2.6	262k	Open	35*	--	242	1.16	3.23	--	Model Provider
Microsoft Azure	Kimi K2.6	262k	Open	35*	--	142	1.71	5.23	--	Model Provider
Crusoe	Kimi K2.6 (NVFP4)	262k	Open	35*	--	--	--	--	--	Model Provider
Kimi	Kimi K2.6	256k	Open	35*	--	33	3.07	18.34	--	Model Provider
Nebius	Kimi K2.6	262k	Open	35*	--	160	1.93	5.04	--	Model Provider
Novita	Kimi K2.6	262k	Open	35*	--	32	3.00	18.42	--	Model Provider
Anthropic	Claude Sonnet 4.6 (Non-reasoning, Low Effort)	1M	Proprietary	34*	--	46	1.60	12.53	--	Model Provider
Nebius	GLM-5.2 (FP4)	432k	Open	34	--	165	0.65	3.69	--	Model Provider
Scaleway	GLM-5.2	262k	Open	34	--	83	1.70	7.71	--	Model Provider
Wafer	GLM-5.2	205k	Open	34	--	183	7.74	10.47	--	Model Provider
SiliconFlow	GLM-5.2	1.05M	Open	34	--	54	2.03	11.36	--	Model Provider
OpenAI	GPT-5.6 Terra (Non-reasoning)	1M	Proprietary	34	$0.18	116	0.73	5.05	--	Model Provider
Novita	KAT-Coder-Pro V2	256k	Proprietary	34	--	99	1.61	6.69	--	Model Provider
StreamLake	KAT-Coder-Pro V2	256k	Proprietary	34	--	--	--	--	--	Model Provider
Clarifai	Qwen3.5 397B A17B	256k	Open	34	$0.33	--	--	--	--	Model Provider
Alibaba Cloud	Qwen3.5 397B A17B	262k	Open	34	$0.33	64	2.44	60.14	49.87	Model Provider
Wafer	Qwen3.5 397B A17B	262k	Open	34	$0.24	63	2.30	60.62	50.40	Model Provider
Parasail	Qwen3.5 397B A17B	262k	Open	34	$0.23	78	0.97	48.30	40.91	Model Provider
SiliconFlow	Qwen3.5 397B A17B (FP8)	262k	Open	34	$0.22	88	2.51	44.28	36.11	Model Provider
DeepInfra	Qwen3.5 397B A17B (FP8)	262k	Open	34	$0.18	48	1.26	77.68	66.05	Model Provider
DigitalOcean	Qwen3.5 397B A17B	262k	Open	34	--	13	2.13	287.25	246.44	Model Provider
GMI	Qwen3.5 397B A17B (FP8)	262k	Open	34	$0.33	--	--	--	--	Model Provider
Nebius	Qwen3.5 397B A17B (Base, FP4)	262k	Open	34	$0.33	86	1.97	44.65	36.89	Model Provider
Novita	Qwen3.5 397B A17B	262k	Open	34	$0.33	64	1.50	59.37	50.03	Model Provider
GMI	Hy3-preview	262k	Open	34*	--	--	--	--	--	Model Provider
SiliconFlow	Hy3-preview	256k	Open	34*	--	105	2.98	26.86	19.11	Model Provider
OpenAI	GPT-5.6 Luna (low)	1M	Proprietary	33	$0.04	159	1.79	4.94	--	Model Provider
SiliconFlow	Qwen3.5 122B A10B (FP8)	262k	Open	32	$0.16	47	2.11	55.27	42.52	Model Provider
DeepInfra	Qwen3.5 122B A10B (FP4)	262k	Open	32	$0.11	47	6.07	58.79	42.18	Model Provider
Alibaba Cloud	Qwen3.5 122B A10B	262k	Open	32	$0.24	134	2.35	20.99	14.92	Model Provider
GMI	Qwen3.5 122B A10B (FP8)	262k	Open	32	$0.24	--	--	--	--	Model Provider
Novita	Qwen3.5 122B A10B	262k	Open	32	$0.24	98	1.80	27.29	20.39	Model Provider
Wafer	Qwen3.5 397B A17B	262k	Open	32*	--	61	2.17	10.38	--	Model Provider
DeepInfra	Qwen3.5 397B A17B (FP8)	262k	Open	32*	--	35	1.23	15.68	--	Model Provider
Alibaba Cloud	Qwen3.5 397B A17B	262k	Open	32*	--	60	2.17	10.43	--	Model Provider
Nebius	Qwen3.5 397B A17B (Base, FP4)	262k	Open	32*	--	93	1.94	7.32	--	Model Provider
DigitalOcean	Qwen3.5 397B A17B	262k	Open	32*	--	20	116.80	141.82	--	Model Provider
Novita	Qwen3.5 397B A17B	262k	Open	32*	--	61	1.59	9.79	--	Model Provider
Alibaba Cloud	Qwen3.6 35B A3B	229k	Open	32	$0.18	154	2.28	40.48	34.96	Model Provider
SiliconFlow	Qwen3.6 35B A3B (FP8)	262k	Open	32	$0.16	52	2.18	116.12	104.28	Model Provider
Scaleway	Qwen3.6 35B A3B	262k	Open	32	--	137	0.90	43.88	39.33	Model Provider
DeepInfra	Qwen3.6 35B A3B (FP8)	262k	Open	32	$0.11	33	0.73	178.12	162.34	Model Provider
Makora	Qwen3.6 35B A3B FP4	1M	Open	32	$0.11	40	1.08	147.94	134.40	Model Provider
Clarifai	Qwen3.6 35B A3B (FP8)	262k	Open	32	--	--	--	--	--	Model Provider
GMI	Qwen3.6 35B A3B FP8	262k	Open	32	$0.18	--	--	--	--	Model Provider
Parasail	Qwen3.6 35B A3B	262k	Open	32	$0.19	112	0.96	53.67	48.23	Model Provider
Novita	Qwen3.6 35B A3B	205k	Open	32	$0.18	149	1.62	41.14	36.17	Model Provider
Microsoft Azure	DeepSeek V4 Pro	1M	Open	31*	--	70	1.83	8.99	--	Model Provider
Nebius	DeepSeek V4 Pro	1.05M	Open	31*	--	62	2.17	10.23	--	Model Provider
Makora	DeepSeek V4 Pro	1M	Open	31*	--	154	0.81	4.05	--	Model Provider
DeepSeek	DeepSeek V4 Pro	1M	Open	31*	--	66	1.62	9.17	--	Model Provider
Alibaba Cloud	Qwen3.5 Omni Plus	256k	Proprietary	31*	--	50	2.40	12.31	--	Model Provider
InclusionAI	Ring-2.6-1T	262k	Open	31	$0.35	129	3.19	22.59	15.53	Model Provider
Groq	Qwen3.6 27B	131k	Open	30	--	448	1.14	2.25	--	Model Provider
Makora	Qwen3.6 27B FP4	256k	Open	30	--	42	3.06	14.83	--	Model Provider
DeepInfra	Qwen3.6 27B FP8	262k	Open	30	--	39	1.37	14.34	--	Model Provider
Alibaba Cloud	Qwen3.6 27B	262k	Open	30	$0.36	56	3.82	12.77	--	Model Provider
Novita	Qwen3.6 27B	262k	Open	30	$0.36	58	72.90	81.54	--	Model Provider
Microsoft Azure	o3	200k	Proprietary	30*	--	108	34.25	38.89	--	Model Provider
OpenAI	o3	200k	Proprietary	30*	--	--	--	--	--	Model Provider
OpenAI	o3	200k	Proprietary	30*	--	136	6.54	10.21	--	Model Provider
StepFun	Step 3.7 Flash	256k	Open	30	--	395	0.83	7.15	5.06	Model Provider
DeepInfra	Step 3.7 Flash	256k	Open	30	--	181	0.52	14.37	11.08	Model Provider
Mistral	Mistral Medium 3.5	262k	Open	30	$0.56	57	2.12	45.78	34.92	Model Provider
Amazon Bedrock	Claude 4.5 Haiku	200k	Proprietary	30	$0.25	115	14.10	18.45	--	Model Provider
Google	Claude 4.5 Haiku Vertex	200k	Proprietary	30	$0.23	99	12.82	17.86	--	Model Provider
Anthropic	Claude 4.5 Haiku	200k	Proprietary	30	$0.24	98	13.20	18.32	--	Model Provider
Microsoft Azure	Claude 4.5 Haiku	200k	Proprietary	30	$0.51	109	14.53	19.10	--	Model Provider
CoreWeave	Gemma 4 31B	262k	Open	29	--	35	1.02	64.96	49.64	Model Provider
GMI	Gemma 4 31B (FP8)	262k	Open	29	--	--	--	--	--	Model Provider
Novita	Gemma 4 31B	262k	Open	29	--	--	--	--	--	Model Provider
Cerebras	Gemma 4 31B	131k	Open	29	$0.21	1,476	0.81	2.32	1.18	Model Provider
Google	Gemma 4 31B (AI Studio)	262k	Open	29	--	35	1.12	64.59	49.28	Model Provider
Parasail	Gemma 4 31B	262k	Open	29	$0.02	50	3.34	48.05	34.71	Model Provider
DeepInfra	Gemma 4 31B	262k	Open	29	$0.01	19	1.40	120.85	92.74	Model Provider
SiliconFlow	Gemma 4 31B (FP8)	262k	Open	29	--	58	3.42	42.08	30.02	Model Provider
SambaNova	Gemma 4 31B	131k	Open	29	--	195	2.60	14.06	8.90	Model Provider
FriendliAI	Gemma 4 31B	256k	Open	29	--	156	1.76	16.05	11.10	Model Provider
Lightning AI	Gemma 4 31B	131k	Open	29	--	141	0.66	16.49	12.30	Model Provider
Together AI	Gemma 4 31B	262k	Open	29	--	57	1.44	40.88	30.62	Model Provider
OpenAI	GPT-5.5 Instant (June 2026)	400k	Proprietary	29	$0.54	--	--	--	--	Model Provider
DeepSeek	DeepSeek V4 Flash	1M	Open	29*	--	118	1.27	5.52	--	Model Provider
GMI	DeepSeek V4 Flash	1.05M	Open	29*	--	--	--	--	--	Model Provider
Makora	DeepSeek V4 Flash	1M	Open	29*	--	143	0.80	4.31	--	Model Provider
CoreWeave	DeepSeek V4 Flash	1M	Open	29*	--	35	1.50	15.73	--	Model Provider
GMI	MiMo-V2.5-Pro	1.05M	Open	28*	--	--	--	--	--	Model Provider
DeepInfra	MiMo-V2.5-Pro	65.5k	Open	28*	--	77	0.83	7.28	--	Model Provider
Xiaomi	MiMo-V2.5-Pro	131k	Open	28*	--	66	2.69	10.24	--	Model Provider
Novita	MiMo-V2.5-Pro	1.05M	Open	28*	--	66	2.13	9.74	--	Model Provider
DeepInfra	Qwen3.5 122B A10B (FP4)	262k	Open	28	$0.09	58	5.94	14.51	--	Model Provider
Alibaba Cloud	Qwen3.5 122B A10B	262k	Open	28	$0.18	145	2.35	5.80	--	Model Provider
OpenAI	GPT-5.6 Luna (Non-reasoning)	1M	Proprietary	27	$0.05	163	0.70	3.77	--	Model Provider
GMI	Hy3-preview	262k	Open	26*	--	--	--	--	--	Model Provider
SiliconFlow	Hy3-preview	328k	Open	26*	--	120	3.01	7.17	--	Model Provider
InclusionAI	Ling-2.6-1T	262k	Open	26*	--	--	--	--	--	Model Provider
StepFun	Step 3.5 Flash 2603	256k	Proprietary	26*	--	302	1.03	9.31	6.62	Model Provider
Google	Gemini 2.5 Pro Vertex	1M	Proprietary	26	$0.20	114	33.23	37.63	--	Model Provider
Google	Gemini 2.5 Pro (AI Studio)	1M	Proprietary	26	$0.20	139	21.27	24.87	--	Model Provider
Makora	Gemma 4 26B A4B	1M	Open	26	--	160	1.03	16.69	12.53	Model Provider
Novita	Gemma 4 26B A4B	262k	Open	26	$0.04	28	1.97	90.31	70.67	Model Provider
Google	Gemma 4 26B A4B AI Studio	262k	Open	26	--	47	1.14	54.40	42.61	Model Provider
Cloudflare	Gemma 4 26B A4B	256k	Open	26	--	83	1.21	31.50	24.23	Model Provider
DeepInfra	Gemma 4 26B A4B	262k	Open	26	$0.02	25	0.78	102.69	81.53	Model Provider
Parasail	Gemma 4 26B A4B	256k	Open	26	$0.02	49	1.69	52.46	40.62	Model Provider
Clarifai	Gemma 4 26B A4B	256k	Open	26	--	--	--	--	--	Model Provider
GMI	Gemma 4 26B A4B (FP8)	1.05M	Open	26	$0.04	--	--	--	--	Model Provider
Baseten	NVIDIA Nemotron 3 Super	203k	Open	25	--	351	0.28	7.42	5.71	Model Provider
CoreWeave	NVIDIA Nemotron 3 Super	262k	Open	25	$0.20	140	0.98	18.77	14.24	Model Provider
Nebius	NVIDIA Nemotron 3 Super	256k	Open	25	$0.29	339	1.80	9.17	5.89	Model Provider
DeepInfra	NVIDIA Nemotron 3 Super	262k	Open	25	--	--	--	--	--	Model Provider
Google	Gemini 3.1 Flash-Lite (AI Studio)	1M	Proprietary	25	$0.04	303	6.27	7.92	--	Model Provider
Amazon Bedrock	Grok 4.3 (Non-reasoning)	524k	Proprietary	25	$0.99	192	0.94	3.54	--	Model Provider
SpaceXAI	Grok 4.3 (Non-reasoning)	1M	Proprietary	25	$0.29	102	0.99	5.90	--	Model Provider
Clarifai	Qwen3.6 35B A3B (FP8)	262k	Open	24	--	--	--	--	--	Model Provider
Scaleway	Qwen3.6 35B A3B	262k	Open	24	--	130	0.93	4.76	--	Model Provider
Makora	Qwen3.6 35B A3B FP4	1M	Open	24	$0.24	47	40.57	51.31	--	Model Provider
DeepInfra	Qwen3.6 35B A3B (FP8)	262k	Open	24	$0.30	45	0.77	12.00	--	Model Provider
Novita	Qwen3.6 35B A3B	205k	Open	24	$0.40	175	1.55	4.41	--	Model Provider
GMI	Qwen3.6 35B A3B FP8	262k	Open	24	$0.40	--	--	--	--	Model Provider
Parasail	Qwen3.6 35B A3B (FP8)	262k	Open	24	$0.41	123	1.29	5.35	--	Model Provider
Alibaba Cloud	Qwen3.6 35B A3B	262k	Open	24	$0.60	182	2.27	5.01	--	Model Provider
DeepInfra	Qwen3.5 35B A3B FP8	262k	Open	24	$0.07	150	0.46	3.78	--	Model Provider
Alibaba Cloud	Qwen3.5 35B A3B	262k	Open	24	$0.23	140	2.31	5.88	--	Model Provider
Groq	gpt-oss-120b (high)	131k	Open	24	$0.05	478	0.72	5.95	4.19	Model Provider
Cloudflare	gpt-oss-120b (high)	116k	Open	24	--	124	0.96	21.13	16.14	Model Provider
Scaleway	gpt-oss-120b (high)	128k	Open	24	$0.07	153	1.25	17.62	13.10	Model Provider
DeepInfra	gpt-oss-120b (high)	131k	Open	24	$0.02	48	0.57	52.25	41.34	Model Provider
CoreWeave	gpt-oss-120b (high)	131k	Open	24	--	74	1.40	35.14	26.99	Model Provider
Microsoft Azure	gpt-oss-120b (high)	131k	Open	24	$0.06	341	1.09	8.42	5.87	Model Provider
Novita	gpt-oss-120b (high)	131k	Open	24	$0.02	66	0.98	39.00	30.41	Model Provider
DeepInfra	gpt-oss-120b (high) (Turbo)	131k	Open	24	--	279	0.64	9.58	7.16	Model Provider
Makora	gpt-oss-120b (high)	128k	Open	24	--	131	0.92	20.04	15.29	Model Provider
Cerebras	gpt-oss-120b (high)	131k	Open	24	$0.12	1,970	0.52	1.79	1.02	Model Provider
Google	gpt-oss-120b (high) Vertex	131k	Open	24	--	397	0.49	6.79	5.04	Model Provider
Clarifai	gpt-oss-120b (high)	131k	Open	24	--	--	--	--	--	Model Provider
Baseten	gpt-oss-120b (high)	128k	Open	24	$0.04	227	0.29	11.31	8.81	Model Provider
SambaNova	gpt-oss-120b (high)	131k	Open	24	--	710	0.96	4.49	2.82	Model Provider
Parasail	gpt-oss-120b (high)	131k	Open	24	--	181	0.81	14.60	11.03	Model Provider
CompactifAI	gpt-oss-120b (high)	131k	Open	24	$0.02	--	--	--	--	Model Provider
Fireworks	gpt-oss-120b (high)	131k	Open	24	--	675	2.47	6.17	2.96	Model Provider
Nebius	gpt-oss-120b (high) (Base)	128k	Open	24	--	277	0.98	9.99	7.21	Model Provider
Hyperbolic	gpt-oss-120b (high)	131k	Open	24	--	--	--	--	--	Model Provider
Databricks	gpt-oss-120b (high)	128k	Open	24	$0.06	313	0.66	8.64	6.38	Model Provider
Amazon Bedrock	gpt-oss-120b (high)	131k	Open	24	$0.06	87	1.13	29.91	23.02	Model Provider
Together AI	gpt-oss-120b (high)	131k	Open	24	--	587	0.60	4.86	3.41	Model Provider
Microsoft Azure	Claude 4.5 Haiku	200k	Proprietary	24*	--	94	1.40	6.74	--	Model Provider
Amazon Bedrock	Claude 4.5 Haiku	200k	Proprietary	24*	--	108	1.07	5.69	--	Model Provider
Anthropic	Claude 4.5 Haiku	200k	Proprietary	24*	--	93	0.89	6.29	--	Model Provider
Google	Claude 4.5 Haiku Vertex	200k	Proprietary	24*	--	92	0.59	6.02	--	Model Provider
Cohere	Command A+	200k	Open	23	$0.00	187	0.41	13.79	10.71	Model Provider
SiliconFlow	Gemma 4 12B	262k	Open	22*	--	105	2.43	26.20	19.02	Model Provider
Parasail	Gemma 4 31B	262k	Open	22	$0.03	40	2.82	15.37	--	Model Provider
Cerebras	Gemma 4 31B	131k	Open	22	$0.24	1,482	0.87	1.21	--	Model Provider
FriendliAI	Gemma 4 31B	262k	Open	22	--	145	1.57	5.03	--	Model Provider
Together AI	Gemma 4 31B (FP8)	262k	Open	22	--	65	1.21	8.89	--	Model Provider
SiliconFlow	Gemma 4 31B (FP8)	262k	Open	22	--	52	2.86	12.55	--	Model Provider
DeepInfra	Gemma 4 31B (FP8)	262k	Open	22	$0.03	14	1.03	37.74	--	Model Provider
SambaNova	Gemma 4 31B	131k	Open	22	--	201	2.59	5.08	--	Model Provider
Novita	Gemma 4 31B	262k	Open	22	--	14	1.43	38.07	--	Model Provider
Amazon Bedrock	Nova 2.0 Pro Preview (medium)	256k	Proprietary	22	$0.17	127	14.48	34.19	15.77	Model Provider
SiliconFlow	Qwen3.5 9B (FP8)	262k	Open	21	$0.16	53	2.47	49.31	37.47	Model Provider
Together AI	Qwen3.5 9B (FP8)	262k	Open	21	$0.16	51	0.88	49.47	38.88	Model Provider
Inception	Mercury 2	128k	Proprietary	21	$0.08	982	4.09	4.60	--	Model Provider
Amazon Bedrock	Qwen3 Coder Next	128k	Open	21	$0.46	115	2.01	6.36	--	Model Provider
Parasail	Qwen3 Coder Next (FP8)	262k	Open	21	$0.11	86	1.04	6.89	--	Model Provider
Together AI	Qwen3 Coder Next (FP8)	262k	Open	21	--	--	--	--	--	Model Provider
Novita	Qwen3 Coder Next (FP8)	262k	Open	21	$0.20	172	2.72	5.62	--	Model Provider
Amazon Bedrock	Nova 2.0 Omni (medium)	1M	Proprietary	21*	--	--	--	--	--	Model Provider
Amazon Bedrock	Nova 2.0 Omni (medium)	1M	Proprietary	21*	--	--	--	--	--	Model Provider
Together AI	Apriel-v1.6-15B-Thinker	131k	Open	21*	--	--	--	--	--	Model Provider
Makora	Gemma 4 26B A4B	1M	Open	20*	--	156	1.01	4.22	--	Model Provider
Parasail	Gemma 4 26B A4B	262k	Open	20*	--	30	1.78	18.28	--	Model Provider
GMI	Gemma 4 26B A4B (FP8)	1.05M	Open	20*	--	--	--	--	--	Model Provider
SiliconFlow	Gemma 4 26B A4B (FP8)	262k	Open	20*	--	57	2.21	11.01	--	Model Provider
Clarifai	Gemma 4 26B A4B	256k	Open	20*	--	--	--	--	--	Model Provider
Scaleway	Gemma 4 26B A4B	262k	Open	20*	--	135	0.89	4.61	--	Model Provider
DeepInfra	Gemma 4 26B A4B (FP8)	262k	Open	20*	--	23	0.69	22.03	--	Model Provider
Novita	Gemma 4 26B A4B	262k	Open	20*	--	28	3.37	20.97	--	Model Provider
DeepInfra	Qwen3.5 4B (FP8)	262k	Open	20*	--	29	0.82	85.92	68.08	Model Provider
Cohere	North Mini Code	256k	Open	20	$0.00	49	0.37	51.22	40.68	Model Provider
Amazon Bedrock	Nova 2.0 Pro Preview (low)	256k	Proprietary	20	$0.21	124	12.88	33.02	16.11	Model Provider
Mistral	Mistral Small 4	256k	Open	20	$0.10	162	0.79	16.22	12.35	Model Provider
Mistral	Devstral 2	262k	Open	19	$0.00	36	1.28	15.14	--	Model Provider
Amazon Bedrock	Nova 2.0 Lite (medium)	1M	Proprietary	19*	--	150	15.48	32.11	13.30	Model Provider
Alibaba Cloud	Qwen3.5 Omni Flash	256k	Proprietary	19*	--	243	1.82	3.87	--	Model Provider
Amazon Bedrock	Nova 2.0 Lite (high)	1M	Proprietary	18	--	--	--	--	--	Model Provider
Amazon Bedrock	Nova 2.0 Lite (high)	1M	Proprietary	18	$0.25	137	25.34	43.63	14.63	Model Provider
Arcee AI	Trinity Large Thinking	262k	Open	18	--	--	--	--	--	Model Provider
Parasail	Trinity Large Thinking (FP8)	262k	Open	18	$0.07	154	0.96	17.20	12.99	Model Provider
Mistral	Magistral Medium 1.2	131k	Proprietary	18	$0.75	43	1.71	60.44	46.98	Model Provider
Amazon Bedrock	Nova 2.0 Lite (low)	1M	Proprietary	18*	--	140	9.51	27.42	14.33	Model Provider
CompactifAI	HyperNova 60B 2605	131k	Open	18	$0.02	415	0.65	6.67	4.82	Model Provider
Mistral	Devstral Small 2	256k	Open	17	$0.00	39	1.24	13.96	--	Model Provider
GMI	Qwen3 Next 80B A3B	262k	Open	17	$0.04	--	--	--	--	Model Provider
Google	Qwen3 Next 80B A3B Vertex	262k	Open	17	--	130	0.80	19.99	15.35	Model Provider
Alibaba Cloud	Qwen3 Next 80B A3B	262k	Open	17	$0.17	176	2.10	16.28	11.35	Model Provider
Nebius	Qwen3 Next 80B A3B (FP8)	262k	Open	17	$0.04	98	1.07	26.52	20.36	Model Provider
Hyperbolic	Qwen3 Next 80B A3B	262k	Open	17	--	--	--	--	--	Model Provider
Amazon Bedrock	Nova 2.0 Omni (low)	1M	Proprietary	17*	--	--	--	--	--	Model Provider
AI9Stars	G9v3-3B	131k	Open	16	--	--	--	--	--	Model Provider
DeepInfra	Qwen3.5 4B FP8	262k	Open	16*	--	26	0.93	20.04	--	Model Provider
Amazon Bedrock	Mistral Large 3	256k	Open	16	$0.06	204	1.21	3.66	--	Model Provider
Microsoft Azure	Mistral Large 3	256k	Open	16	--	70	1.62	8.81	--	Model Provider
Mistral	Mistral Large 3	262k	Open	16	$0.06	49	1.10	11.24	--	Model Provider
Clarifai	Nemotron 3 Nano Omni 30B A3B Reasoning	262k	Open	15*	--	--	--	--	--	Model Provider
Nebius	Nemotron 3 Nano Omni 30B A3B Reasoning (FP8)	65.5k	Open	15*	--	302	1.01	9.28	6.61	Model Provider
Snowflake	gpt-oss-120b (low)	131k	Open	15	--	--	--	--	--	Model Provider
Hyperbolic	gpt-oss-120b (low)	131k	Open	15	--	--	--	--	--	Model Provider
Nebius	gpt-oss-120b (low) Base	128k	Open	15	--	305	0.97	9.17	6.56	Model Provider
Makora	gpt-oss-120b (low)	128k	Open	15	--	134	0.94	19.65	14.97	Model Provider
SambaNova	gpt-oss-120b (low)	131k	Open	15	--	733	1.07	4.48	2.73	Model Provider
Google	gpt-oss-120b (low) Vertex	131k	Open	15	--	414	0.50	6.54	4.83	Model Provider
Fireworks	gpt-oss-120b (low)	131k	Open	15	--	671	2.33	6.05	2.98	Model Provider
CoreWeave	gpt-oss-120b (low)	131k	Open	15	--	78	1.37	33.59	25.77	Model Provider
Cerebras	gpt-oss-120b (low)	131k	Open	15	$0.04	1,758	0.54	1.96	1.14	Model Provider
Microsoft Azure	gpt-oss-120b (low)	131k	Open	15	$0.02	360	0.88	7.82	5.55	Model Provider
Cloudflare	gpt-oss-120b (low)	128k	Open	15	--	111	0.91	23.34	17.94	Model Provider
CompactifAI	gpt-oss-120b (low)	131k	Open	15	$0.01	--	--	--	--	Model Provider
Baseten	gpt-oss-120b (low)	128k	Open	15	$0.01	243	0.37	10.65	8.22	Model Provider
Amazon Bedrock	gpt-oss-120b (low)	131k	Open	15	$0.02	124	1.21	21.42	16.17	Model Provider
Parasail	gpt-oss-120b (low)	131k	Open	15	--	215	0.83	12.45	9.30	Model Provider
Databricks	gpt-oss-120b (low)	128k	Open	15	$0.02	314	0.67	8.62	6.37	Model Provider
Together AI	gpt-oss-120b (low)	131k	Open	15	--	571	0.59	4.97	3.50	Model Provider
Groq	gpt-oss-120b (low)	131k	Open	15	$0.02	475	0.78	6.05	4.21	Model Provider
Clarifai	gpt-oss-120b (low)	131k	Open	15	--	--	--	--	--	Model Provider
Novita	gpt-oss-120b (low)	131k	Open	15	$0.01	72	0.98	35.89	27.93	Model Provider
CoreWeave	gpt-oss-20b (high)	131k	Open	15	--	196	0.91	13.64	10.18	Model Provider
Amazon Bedrock	gpt-oss-20b (high)	131k	Open	15	--	143	30.49	47.98	13.99	Model Provider
DeepInfra	gpt-oss-20b (high)	131k	Open	15	--	118	0.45	21.66	16.97	Model Provider
Together AI	gpt-oss-20b (high)	131k	Open	15	--	428	0.40	6.25	4.68	Model Provider
Hyperbolic	gpt-oss-20b (high)	131k	Open	15	--	--	--	--	--	Model Provider
Lightning AI	gpt-oss-20b (high)	128k	Open	15	--	274	0.53	9.65	7.30	Model Provider
Cloudflare	gpt-oss-20b (high)	128k	Open	15	--	160	0.77	16.40	12.50	Model Provider
Novita	gpt-oss-20b (high)	131k	Open	15	--	149	1.07	17.87	13.44	Model Provider
Google	gpt-oss-20b (high) Vertex	131k	Open	15	--	289	1.25	9.91	6.92	Model Provider
Databricks	gpt-oss-20b (high)	131k	Open	15	$0.03	305	1.13	9.34	6.56	Model Provider
Groq	gpt-oss-20b (high)	131k	Open	15	--	844	0.79	3.76	2.37	Model Provider
Clarifai	gpt-oss-20b (high)	131k	Open	15	$0.02	--	--	--	--	Model Provider
Amazon Bedrock	Nova 2.0 Pro Preview	256k	Proprietary	14	$0.25	107	1.01	5.66	--	Model Provider
Together AI	gpt-oss-20b (low)	131k	Open	14*	--	402	0.40	6.62	4.98	Model Provider
Clarifai	gpt-oss-20b (low)	131k	Open	14*	--	--	--	--	--	Model Provider
Groq	gpt-oss-20b (low)	131k	Open	14*	--	885	0.81	3.63	2.26	Model Provider
Lightning AI	gpt-oss-20b (low)	128k	Open	14*	--	273	0.54	9.69	7.32	Model Provider
Hyperbolic	gpt-oss-20b (low)	131k	Open	14*	--	--	--	--	--	Model Provider
CoreWeave	gpt-oss-20b (low)	131k	Open	14*	--	199	0.92	13.46	10.03	Model Provider
Cloudflare	gpt-oss-20b (low)	128k	Open	14*	--	164	0.75	16.04	12.23	Model Provider
Amazon Bedrock	gpt-oss-20b (low)	131k	Open	14*	--	230	5.82	16.66	8.68	Model Provider
Novita	gpt-oss-20b (low)	131k	Open	14*	--	146	1.03	18.20	13.74	Model Provider
Databricks	gpt-oss-20b (low)	131k	Open	14*	--	233	0.82	11.55	8.58	Model Provider
Google	gpt-oss-20b (low) Vertex	131k	Open	14*	--	244	1.13	11.39	8.21	Model Provider
Novita	Llama 4 Maverick (FP8)	1.05M	Open	14	$0.03	46	0.88	11.84	--	Model Provider
Microsoft Azure	Llama 4 Maverick (FP8)	128k	Open	14	$0.04	117	1.18	5.45	--	Model Provider
Amazon Bedrock	Llama 4 Maverick	128k	Open	14	--	208	0.85	3.25	--	Model Provider
Snowflake	Llama 4 Maverick	131k	Open	14	--	124	1.11	5.14	--	Model Provider
Together AI	Llama 4 Maverick	1.05M	Open	14	--	--	--	--	--	Model Provider
DeepInfra	Llama 4 Maverick (FP8)	1.05M	Open	14	--	43	0.62	12.19	--	Model Provider
Databricks	Llama 4 Maverick	131k	Open	14	$0.05	85	0.98	6.84	--	Model Provider
Parasail	Llama 4 Maverick (FP8)	1.05M	Open	14	$0.02	119	1.00	5.21	--	Model Provider
Nebius	NVIDIA Nemotron 3 Nano	262k	Open	14	$0.02	144	1.14	18.49	13.88	Model Provider
Novita	NVIDIA Nemotron 3 Nano (FP4)	262k	Open	14	--	223	1.07	12.30	8.98	Model Provider
DeepInfra	NVIDIA Nemotron 3 Nano	262k	Open	14	$0.02	74	10.93	44.61	26.95	Model Provider
Novita	Ling 2.6 Flash	262k	Open	14	--	123	1.16	5.22	--	Model Provider
Hyperbolic	Qwen3 Next 80B A3B	262k	Open	14*	--	--	--	--	--	Model Provider
Google	Qwen3 Next 80B A3B Vertex	262k	Open	14*	--	208	0.71	3.11	--	Model Provider
GMI	Qwen3 Next 80B A3B	262k	Open	14*	--	186	2.20	4.88	--	Model Provider
DeepInfra	Qwen3 Next 80B A3B	262k	Open	14*	--	122	0.64	4.75	--	Model Provider
Parasail	Qwen3 Next 80B A3B	262k	Open	14*	--	115	0.87	5.23	--	Model Provider
Novita	Qwen3 Next 80B A3B	131k	Open	14*	--	193	1.62	4.21	--	Model Provider
Alibaba Cloud	Qwen3 Next 80B A3B	131k	Open	14*	--	183	2.18	4.91	--	Model Provider
SiliconFlow	Gemma 4 12B (Non-reasoning)	262k	Open	13*	--	98	2.47	7.55	--	Model Provider
Amazon Bedrock	Nova Premier	1M	Proprietary	13*	--	32	2.93	18.55	--	Model Provider
DeepInfra	Llama Nemotron Super 49B v1.5	131k	Open	12*	--	59	8.07	50.57	34.01	Model Provider
Mistral	Mistral Small 4	262k	Open	12*	--	145	0.76	4.20	--	Model Provider
DeepInfra	Gemma 4 E4B	262k	Open	12	--	93	0.80	27.79	21.60	Model Provider
Sarvam	Sarvam 105B (high)	128k	Open	12*	--	--	--	--	--	Model Provider
Amazon Bedrock	Nova 2.0 Lite	1M	Proprietary	12*	--	147	1.12	4.52	--	Model Provider
Amazon Bedrock	Magistral Small 1.2	128k	Open	11	--	73	1.61	35.71	27.28	Model Provider
Mistral	Magistral Small 1.2	131k	Open	11	$0.25	83	0.96	30.94	23.99	Model Provider
Mistral	Ministral 3 14B	262k	Open	11	$0.15	71	0.87	7.92	--	Model Provider
Amazon Bedrock	Ministral 3 14B	256k	Open	11	$0.15	232	0.97	3.13	--	Model Provider
Amazon Bedrock	Nova 2.0 Omni	1M	Proprietary	11*	--	--	--	--	--	Model Provider
DeepInfra	Llama 4 Scout	328k	Open	10	$0.0049	54	0.56	9.85	--	Model Provider
Microsoft Azure	Llama 4 Scout	128k	Open	10	--	--	--	--	--	Model Provider
Google	Llama 4 Scout Vertex	1.31M	Open	10	$0.01	143	0.84	4.33	--	Model Provider
Cloudflare	Llama 4 Scout	131k	Open	10	$0.01	53	0.76	10.28	--	Model Provider
Amazon Bedrock	Llama 4 Scout	128k	Open	10	--	165	0.85	3.88	--	Model Provider
Novita	Llama 4 Scout	131k	Open	10	$0.01	55	0.90	10.03	--	Model Provider
Groq	Llama 4 Scout	131k	Open	10	$0.01	445	0.76	1.89	--	Model Provider
Nebius	Hermes 4 70B (FP8)	128k	Open	10*	--	94	1.38	28.02	21.31	Model Provider
Alibaba Cloud	Qwen3 Omni 30B A3B	65.5k	Open	10*	--	99	1.93	27.19	20.21	Model Provider
Fireworks	Llama 3.3 70B	131k	Open	9	--	--	--	--	--	Model Provider
Google	Llama 3.3 70B Vertex	128k	Open	9	$0.10	148	0.66	4.03	--	Model Provider
Groq	Llama 3.3 70B	131k	Open	9	$0.08	294	0.99	2.69	--	Model Provider
Novita	Llama 3.3 70B	131k	Open	9	$0.02	--	--	--	--	Model Provider
Parasail	Llama 3.3 70B (FP8)	131k	Open	9	$0.02	63	2.45	10.38	--	Model Provider
SambaNova	Llama 3.3 70B	128k	Open	9	$0.08	280	1.91	3.70	--	Model Provider
Snowflake	Llama 3.3 70B	8k	Open	9	--	--	--	--	--	Model Provider
Nebius	Llama 3.3 70B Base	128k	Open	9	--	20	2.67	27.36	--	Model Provider
Makora	Llama 3.3 70B FP8	128k	Open	9	--	--	--	--	--	Model Provider
CoreWeave	Llama 3.3 70B	128k	Open	9	--	76	0.95	7.51	--	Model Provider
Together AI	Llama 3.3 70B Turbo	131k	Open	9	$0.12	63	1.54	9.50	--	Model Provider
Microsoft Azure	Llama 3.3 70B	128k	Open	9	$0.10	101	2.40	7.37	--	Model Provider
DeepInfra	Llama 3.3 70B (Turbo, FP8)	131k	Open	9	$0.01	11	2.28	49.70	--	Model Provider
Cloudflare	Llama 3.3 70B	24k	Open	9	$0.04	38	4.01	17.23	--	Model Provider
Amazon Bedrock	Llama 3.3 70B	128k	Open	9	$0.10	123	1.18	5.25	--	Model Provider
Databricks	Llama 3.3 70B	128k	Open	9	$0.07	65	1.17	8.88	--	Model Provider
Scaleway	Llama 3.3 70B	100k	Open	9	$0.14	82	1.40	7.52	--	Model Provider
Nebius	Llama Nemotron Ultra Base	131k	Open	9*	--	53	2.36	49.92	38.05	Model Provider
SiliconFlow	ERNIE 4.5 300B A47B	131k	Open	9*	--	--	--	--	--	Model Provider
Nebius	Hermes 4 405B (FP8)	128k	Open	9*	--	29	2.40	88.08	68.54	Model Provider
DeepInfra	NVIDIA Nemotron Nano 12B v2 VL (FP8)	131k	Open	9*	--	61	11.23	52.28	32.84	Model Provider
Amazon Bedrock	Ministral 3 8B	256k	Open	9	$0.18	255	1.03	2.99	--	Model Provider
Mistral	Ministral 3 8B	262k	Open	9	$0.18	115	0.76	5.10	--	Model Provider
DeepInfra	Gemma 4 E4B	262k	Open	9*	--	93	0.73	6.09	--	Model Provider
DeepInfra	NVIDIA Nemotron Nano 9B V2	131k	Open	9*	--	82	11.48	41.93	24.36	Model Provider
Nebius	Hermes 4 405B (FP8)	128k	Open	9*	--	34	2.40	17.23	--	Model Provider
DeepInfra	Llama Nemotron Super 49B v1.5	131k	Open	9*	--	66	9.29	16.84	--	Model Provider
Databricks	Llama 3.1 405B	128k	Open	9*	--	--	--	--	--	Model Provider
Liquid AI	LFM2.5-8B-A1B	32.8k	Open	8*	--	332	2.51	10.05	6.03	Model Provider
SiliconFlow	Ring-flash-2.0	131k	Open	8*	--	--	--	--	--	Model Provider
Parasail	Olmo 3.1 32B Think	65.5k	Open	8*	--	--	--	--	--	Model Provider
Cohere	Command A	288k	Open	8*	--	55	1.61	10.74	--	Model Provider
Microsoft Azure	Command A	256k	Open	8*	--	40	3.10	15.47	--	Model Provider
DeepInfra	Llama 3.1 Nemotron 70B	131k	Open	8*	--	59	7.06	15.57	--	Model Provider
Novita	NVIDIA Nemotron 3 Nano (FP4)	262k	Open	7*	--	199	1.11	3.62	--	Model Provider
DeepInfra	NVIDIA Nemotron 3 Nano	262k	Open	7*	--	73	0.42	7.28	--	Model Provider
DeepInfra	NVIDIA Nemotron Nano 9B V2	131k	Open	7*	--	89	10.02	15.65	--	Model Provider
Amazon Bedrock	NVIDIA Nemotron Nano 9B V2	131k	Open	7*	--	160	1.20	4.32	--	Model Provider
Nebius	Hermes 4 70B (FP8)	128k	Open	7*	--	94	1.37	6.68	--	Model Provider
Amazon Bedrock	Ministral 3 3B	256k	Open	7	$0.13	403	1.02	2.26	--	Model Provider
Mistral	Ministral 3 3B	131k	Open	7	$0.13	232	0.60	2.75	--	Model Provider
CoreWeave	Granite 4.1 8B	131k	Open	7*	--	109	0.81	5.38	--	Model Provider
Sarvam	Sarvam 30B (high)	64k	Open	7*	--	--	--	--	--	Model Provider
Microsoft Azure	Llama 3.2 90B (Vision)	8.19k	Open	6*	--	--	--	--	--	Model Provider
Microsoft Azure	Phi-4 Mini	128k	Open	6	$0.00	44	0.82	12.14	--	Model Provider
AI21 Labs	Jamba 1.7 Large	256k	Open	5*	--	57	1.37	10.12	--	Model Provider
Replicate	Granite 4.0 H Small	128k	Open	5*	--	411	10.21	11.43	--	Model Provider
Alibaba Cloud	Qwen3 Omni 30B A3B	65.5k	Open	5*	--	91	1.87	7.39	--	Model Provider
Microsoft Azure	Phi-4	16.4k	Open	5*	--	--	--	--	--	Model Provider
DeepInfra	Phi-4	16.4k	Open	5*	--	75	0.78	7.48	--	Model Provider
Amazon Bedrock	Nova Micro	130k	Proprietary	5*	--	283	0.90	2.66	--	Model Provider
Amazon Bedrock	NVIDIA Nemotron Nano 12B v2 VL	128k	Open	5*	--	206	1.13	3.56	--	Model Provider
DeepInfra	NVIDIA Nemotron Nano 12B v2 VL (FP8)	131k	Open	5*	--	69	6.03	13.28	--	Model Provider
Microsoft Azure	Phi-4 Multimodal	128k	Open	5*	--	18	0.82	28.88	--	Model Provider
Reka AI	Reka Flash 3	54k	Open	4*	--	--	--	--	--	Model Provider
Microsoft Azure	Llama 3.2 11B (Vision)	8.19k	Open	3*	--	--	--	--	--	Model Provider
DeepInfra	Llama 3.2 11B (Vision)	131k	Open	3*	--	14	1.38	36.78	--	Model Provider
Parasail	Olmo 3 7B	65.5k	Open	3*	--	--	--	--	--	Model Provider
Public AI	Apertus 70B Instruct	64k	Open	2*	--	--	--	--	--	Model Provider
Liquid AI	LFM2.5-VL-1.6B	32.8k	Open	1*	--	400	2.13	3.38	--	Model Provider
Cohere	Tiny Aya Global	8.19k	Open	1*	--	--	--	--	--	Model Provider
Public AI	Apertus 8B Instruct	64k	Open	1*	--	--	--	--	--	Model Provider
Anthropic	Claude Sonnet 5 (low)	1M	Proprietary	--	--	64	1.93	9.74	--	Model Provider
Anthropic	Claude Sonnet 5 (xhigh)	1M	Proprietary	--	--	72	32.39	39.36	--	Model Provider
Anthropic	Claude Sonnet 5 (high)	1M	Proprietary	--	--	70	9.63	16.77	--	Model Provider
Together AI	Cogito v2.1	164k	Open	--	--	--	--	--	--	Model Provider
Anthropic	Claude Sonnet 5 (medium)	1M	Proprietary	--	--	67	2.23	9.73	--	Model Provider

Key definitions

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.

Average cost per task in the index. Costs are split by input, cache hit, cache write, reasoning, and answer token pricing where canonical token counts are available.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Price per token to write prompt tokens into the cache so that later requests can hit them, represented as USD per million tokens. Some providers charge a premium over the standard input price to create a cache entry (e.g. Anthropic), while others cache automatically with no separate write fee.

Price per token generated by the model (received from the API), represented as USD per million Tokens.

Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.

LLM API Providers Leaderboard - Comparison of over 500 AI Model endpoints

Key definitions

Context Window

Output Speed

Latency (Time to First Token)

Index Cost per Task

Input Price

Cache Hit

Cache Write

Output Price

Time Period