Marketplace

Model & provider rankings

Every model we route to, ordered by price per million tokens, with the time-to-first-token and uptime we measure for the provider serving it.

We publish measurements, not estimates. Latency and uptime are probed per provider, so every model from one provider shares them. Where we have not measured something yet it reads “—”, and there is no quality ranking here because we do not yet publish one.

Models ranked by price per million tokens, with measured provider latency and uptime.
#	Model	Provider	Price / M	TTFT p95	Uptime	Status
1	Qwen 2 Instruct (1.5B)	Together AI	$0.02	2,626ms	100.00%	Healthy
2	meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo	DeepInfra	$0.03	8,448ms	99.98%	Healthy
3	mistralai/Mistral-Nemo-Instruct-2407	DeepInfra	$0.04	8,448ms	99.98%	Healthy
4	meta-llama/Meta-Llama-3.1-8B-Instruct	DeepInfra	$0.04	8,448ms	99.98%	Healthy
5	Sao10K/L3-8B-Lunaris-v1-Turbo	DeepInfra	$0.05	8,448ms	99.98%	Healthy
6	Meta Llama 3.2 1B Instruct	Together AI	$0.07	2,626ms	100.00%	Healthy
7	Meta Llama 3.2 3B Instruct	Together AI	$0.07	2,626ms	100.00%	Healthy
8	mistralai/Mistral-Small-24B-Instruct-2501	DeepInfra	$0.08	8,448ms	99.98%	Healthy
9	google/gemma-3-4b-it	DeepInfra	$0.09	8,448ms	99.98%	Healthy
10	LFM2-24B-A2B	Together AI	$0.09	2,626ms	100.00%	Healthy
11	openai/gpt-oss-20b	DeepInfra	$0.10	8,448ms	99.98%	Healthy
12	Gemma 3N E4B Instruct	Together AI	$0.11	2,626ms	100.00%	Healthy
13	Qwen/Qwen3-235B-A22B-Instruct-2507	DeepInfra	$0.11	8,448ms	99.98%	Healthy
14	Trinity Mini	Together AI	$0.12	2,626ms	100.00%	Healthy
15	google/gemma-3-12b-it	DeepInfra	$0.12	8,448ms	99.98%	Healthy
16	Arize AI Qwen 2 1.5B Instruct	Together AI	$0.12	2,626ms	100.00%	Healthy
17	openai/gpt-oss-120b	DeepInfra	$0.13	8,448ms	99.98%	Healthy
18	microsoft/phi-4	DeepInfra	$0.13	8,448ms	99.98%	Healthy
19	google/gemma-3-27b-it	DeepInfra	$0.14	8,448ms	99.98%	Healthy
20	Qwen/Qwen3.5-9B	DeepInfra	$0.15	8,448ms	99.98%	Healthy
21	nvidia/Nemotron-3-Nano-30B-A3B	DeepInfra	$0.15	8,448ms	99.98%	Healthy
22	OpenAI GPT-OSS 20B	Together AI	$0.15	2,626ms	100.00%	Healthy
23	deepseek-ai/DeepSeek-V4-Flash	DeepInfra	$0.16	8,448ms	99.98%	Healthy
24	mistralai/Mistral-Small-3.2-24B-Instruct-2506	DeepInfra	$0.17	8,448ms	99.98%	Healthy
25	Meta Llama 3 8B Instruct Lite	Together AI	$0.17	2,626ms	100.00%	Healthy
26	Nvidia Nemotron Nano 9B V2	Together AI	$0.19	2,626ms	100.00%	Healthy
27	Qwen/Qwen3-14B	DeepInfra	$0.22	8,448ms	99.98%	Healthy
28	Qwen/Qwen3-32B	DeepInfra	$0.22	8,448ms	99.98%	Healthy
29	meta-llama/Llama-Guard-4-12B	DeepInfra	$0.22	8,448ms	99.98%	Healthy
30	DeepSeek R1 Distill Qwen 1.5B	Together AI	$0.22	2,626ms	100.00%	Healthy
31	Meta Llama 3.1 8B Instruct Turbo	Together AI	$0.22	2,626ms	100.00%	Healthy
32	meta-llama/Llama-4-Scout-17B-16E-Instruct	DeepInfra	$0.24	8,448ms	99.98%	Healthy
33	nvidia/Nemotron-Content-Safety-3.5	DeepInfra	$0.24	8,448ms	99.98%	Healthy
34	Meta Llama 3 8B Instruct Reference	Together AI	$0.24	2,626ms	100.00%	Healthy
35	Meta Llama 3 8B Instruct	Together AI	$0.24	2,626ms	100.00%	Healthy
36	Meta Llama 3.1 8B	Together AI	$0.24	2,626ms	100.00%	Healthy
37	Ministral 3 14B Instruct 2512	Together AI	$0.24	2,626ms	100.00%	Healthy
38	Mistral (7B) Instruct v0.1	Together AI	$0.24	2,626ms	100.00%	Healthy
39	Mistral (7B) Instruct v0.3	Together AI	$0.24	2,626ms	100.00%	Healthy
40	Mistral Small (24B) Instruct 25.01	Together AI	$0.24	2,626ms	100.00%	Healthy
41	google/gemma-4-26B-A4B-it	DeepInfra	$0.25	8,448ms	99.98%	Healthy
42	meta-llama/Llama-3.3-70B-Instruct-Turbo	DeepInfra	$0.25	8,448ms	99.98%	Healthy
43	Qwen3.5 9B FP8	Together AI	$0.25	2,626ms	100.00%	Healthy
44	zai-org/GLM-4.7-Flash	DeepInfra	$0.28	8,448ms	99.98%	Healthy
45	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B	DeepInfra	$0.29	8,448ms	99.98%	Healthy
46	google/gemma-4-31B-it-turbo	DeepInfra	$0.29	8,448ms	99.98%	Healthy
47	ByteDance/Seed-2.0-mini	DeepInfra	$0.30	8,448ms	99.98%	Healthy
48	google/gemma-4-31B-it	DeepInfra	$0.31	8,448ms	99.98%	Healthy
49	Qwen2.5 7B Instruct Turbo	Together AI	$0.36	2,626ms	100.00%	Healthy
50	Qwen/Qwen3-30B-A3B	DeepInfra	$0.37	8,448ms	99.98%	Healthy
51	deepseek-ai/DeepSeek-V3.2	DeepInfra	$0.38	8,448ms	99.98%	Healthy
52	meta-llama/Llama-3.2-11B-Vision-Instruct	DeepInfra	$0.41	8,448ms	99.98%	Healthy
53	Qwen/Qwen3-VL-30B-A3B-Instruct	DeepInfra	$0.45	8,448ms	99.98%	Healthy
54	meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8	DeepInfra	$0.45	8,448ms	99.98%	Healthy
55	openai/gpt-oss-120b-Turbo	DeepInfra	$0.45	8,448ms	99.98%	Healthy
56	OpenAI GPT-OSS 120B	Together AI	$0.45	2,626ms	100.00%	Healthy
57	Qwen/Qwen2.5-72B-Instruct	DeepInfra	$0.46	8,448ms	99.98%	Healthy
58	Llama 4 Scout Instruct (17Bx16E)	Together AI	$0.46	2,626ms	100.00%	Healthy
59	Gryphe/MythoMax-L2-13b	DeepInfra	$0.48	8,448ms	99.98%	Healthy
60	meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	DeepInfra	$0.48	8,448ms	99.98%	Healthy
61	nvidia/Llama-3.3-Nemotron-Super-49B-v1.5	DeepInfra	$0.48	8,448ms	99.98%	Healthy
62	Qwen3 235B A22B Instruct 2507 FP8 Throughput	Together AI	$0.48	2,626ms	100.00%	Healthy
63	Qwen3-VL-8B-Instruct	Together AI	$0.52	2,626ms	100.00%	Healthy
64	deepseek-ai/DeepSeek-V3.1	DeepInfra	$0.60	8,448ms	99.98%	Healthy
65	nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning	DeepInfra	$0.60	8,448ms	99.98%	Healthy
66	MiniMaxAI/MiniMax-M2.5	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
67	NousResearch/Hermes-4-405B	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
68	NousResearch/Hermes-4-70B	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
69	Qwen/Qwen2.5-VL-72B-Instruct	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
70	Qwen/Qwen3-235B-A22B-Instruct-2507	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
71	Qwen/Qwen3-30B-A3B-Instruct-2507	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
72	Qwen/Qwen3-32B	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
73	Qwen/Qwen3-Embedding-8B	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
74	Qwen/Qwen3-Next-80B-A3B-Thinking	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
75	Qwen/Qwen3.5-397B-A17B	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
76	deepseek-ai/DeepSeek-V4-Pro	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
77	google/gemma-3-27b-it	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
78	meta-llama/Llama-3.3-70B-Instruct	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
79	moonshotai/Kimi-K2.6	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
80	moonshotai/Kimi-K2.7-Code	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
81	nvidia/Cosmos3-Super-Reasoner	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
82	nvidia/Llama-3_1-Nemotron-Ultra-253B-v1	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
83	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
84	nvidia/Nemotron-3-Nano-Omni	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
85	nvidia/Nemotron-3-Ultra-550b-a55b	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
86	nvidia/nemotron-3-super-120b-a12b	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
87	openai/gpt-oss-120b	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
88	openbmb/MiniCPM-V-4_5	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
89	zai-org/GLM-5.1	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
90	zai-org/GLM-5.2	Nebius Token Factory	$0.60	6,231ms	100.00%	Healthy
91	Qwen/Qwen3-VL-235B-A22B-Instruct	DeepInfra	$0.65	8,448ms	99.98%	Healthy
92	Qwen/Qwen3.6-35B-A3B	DeepInfra	$0.66	8,448ms	99.98%	Healthy
93	Qwen/Qwen3.5-35B-A3B	DeepInfra	$0.68	8,448ms	99.98%	Healthy
94	deepseek-ai/DeepSeek-V3-0324	DeepInfra	$0.68	8,448ms	99.98%	Healthy
95	Pearl-ai Gemma-4-31B-it-pearl	Together AI	$0.68	2,626ms	100.00%	Healthy
96	Qwen/Qwen3-Next-80B-A3B-Instruct	DeepInfra	$0.71	8,448ms	99.98%	Healthy
97	Nous Hermes 2 Mixtral 8X7B Dpo	Together AI	$0.72	2,626ms	100.00%	Healthy
98	Mixtral-8x7B Instruct v0.1	Together AI	$0.72	2,626ms	100.00%	Healthy
99	deepseek-ai/DeepSeek-V3	DeepInfra	$0.73	8,448ms	99.98%	Healthy
100	deepseek-ai/DeepSeek-V3.1-Terminus	DeepInfra	$0.73	8,448ms	99.98%	Healthy
101	MiniMaxAI/MiniMax-M2.7	DeepInfra	$0.75	8,448ms	99.98%	Healthy
102	MiniMaxAI/MiniMax-M2.5	DeepInfra	$0.78	8,448ms	99.98%	Healthy
103	Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo	DeepInfra	$0.78	8,448ms	99.98%	Healthy
104	Glm 4.5 Air Fp8	Together AI	$0.78	2,626ms	100.00%	Healthy
105	stepfun-ai/Step-3.7-Flash	DeepInfra	$0.81	8,448ms	99.98%	Healthy
106	Gemma 4 31B-it FP8	Together AI	$0.82	2,626ms	100.00%	Healthy
107	NousResearch/Hermes-3-Llama-3.1-70B	DeepInfra	$0.84	8,448ms	99.98%	Healthy
108	MiniMaxAI/MiniMax-M3	DeepInfra	$0.90	8,448ms	99.98%	Healthy
109	deepseek-v4-flash	DeepSeek	$0.90	2,110ms	100.00%	Healthy
110	deepseek-v4-pro	DeepSeek	$0.90	2,110ms	100.00%	Healthy
111	MiniMax M2.7 FP4	Together AI	$0.90	2,626ms	100.00%	Healthy
112	MiniMax M3	Together AI	$0.90	2,626ms	100.00%	Healthy
113	Qwen 2.5 14B Instruct	Together AI	$0.96	2,626ms	100.00%	Healthy
114	Qwen 2.5 Coder 32B Instruct	Together AI	$0.96	2,626ms	100.00%	Healthy
115	Qwen3.7 Plus	Together AI	$0.96	2,626ms	100.00%	Healthy
116	Deepseek Coder 33B Instruct	Together AI	$0.96	2,626ms	100.00%	Healthy
117	Gemma-2 Instruct (27B)	Together AI	$0.96	2,626ms	100.00%	Healthy
118	Qwen3 Next 80B A3b Instruct	Together AI	$0.99	2,626ms	100.00%	Healthy
119	Qwen3 Next 80B A3b Thinking	Together AI	$0.99	2,626ms	100.00%	Healthy
120	Sao10K/L3.1-70B-Euryale-v2.2	DeepInfra	$1.02	8,448ms	99.98%	Healthy
121	Qwen3 Coder Next Fp8	Together AI	$1.02	2,626ms	100.00%	Healthy
122	google/gemini-3.1-flash-lite	DeepInfra	$1.05	8,448ms	99.98%	Healthy
123	Meta Llama 3 70B Instruct Turbo	Together AI	$1.06	2,626ms	100.00%	Healthy
124	Meta Llama 3.1 70B Instruct Turbo	Together AI	$1.06	2,626ms	100.00%	Healthy
125	Llama 3.1 Nemotron 70B Instruct HF	Together AI	$1.06	2,626ms	100.00%	Healthy
126	Qwen2 72B Instruct	Together AI	$1.08	2,626ms	100.00%	Healthy
127	NousResearch/Hermes-3-Llama-3.1-405B	DeepInfra	$1.20	8,448ms	99.98%	Healthy
128	Qwen3-VL-32B-Instruct	Together AI	$1.20	2,626ms	100.00%	Healthy
129	Meta Llama 3.3 70B Instruct Turbo	Together AI	$1.25	2,626ms	100.00%	Healthy
130	zai-org/GLM-4.7	DeepInfra	$1.29	8,448ms	99.98%	Healthy
131	zai-org/GLM-4.6	DeepInfra	$1.30	8,448ms	99.98%	Healthy
132	ByteDance/Seed-1.8	DeepInfra	$1.35	8,448ms	99.98%	Healthy
133	Deepseek V3.1 NVFP4	Together AI	$1.38	2,626ms	100.00%	Healthy
134	MiniMaxAI/MiniMax-M2.7-Turbo	DeepInfra	$1.44	8,448ms	99.98%	Healthy
135	XiaomiMiMo/MiMo-V2.5	DeepInfra	$1.44	8,448ms	99.98%	Healthy
136	Qwen QwQ-32B	Together AI	$1.44	2,626ms	100.00%	Healthy
137	Qwen2-VL (72B) Instruct	Together AI	$1.44	2,626ms	100.00%	Healthy
138	Qwen2.5 72B Instruct	Together AI	$1.44	2,626ms	100.00%	Healthy
139	Qwen2.5 72B Instruct Turbo	Together AI	$1.44	2,626ms	100.00%	Healthy
140	GLM 4.7 FP8	Together AI	$1.47	2,626ms	100.00%	Healthy
141	Cogito v2.1 671B	Together AI	$1.50	2,626ms	100.00%	Healthy
142	Qwen/Qwen3-235B-A22B-Thinking-2507	DeepInfra	$1.52	8,448ms	99.98%	Healthy
143	deepseek-ai/DeepSeek-R1-0528	DeepInfra	$1.59	8,448ms	99.98%	Healthy
144	zai-org/GLM-5	DeepInfra	$1.61	8,448ms	99.98%	Healthy
145	Qwen/Qwen3.5-122B-A10B	DeepInfra	$1.61	8,448ms	99.98%	Healthy
146	moonshotai/Kimi-K2.5	DeepInfra	$1.62	8,448ms	99.98%	Healthy
147	nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B	DeepInfra	$1.62	8,448ms	99.98%	Healthy
148	google/gemini-2.5-flash	DeepInfra	$1.68	8,448ms	99.98%	Healthy
149	GLM 4.6 Fp8	Together AI	$1.68	2,626ms	100.00%	Healthy
150	Qwen/Qwen3.5-27B	DeepInfra	$1.72	8,448ms	99.98%	Healthy
151	DeepSeek R1 Distill Qwen 14B	Together AI	$1.92	2,626ms	100.00%	Healthy
152	Kimi K2.5 Fp4	Together AI	$1.98	2,626ms	100.00%	Healthy
153	Qwen/Qwen3.5-397B-A17B	DeepInfra	$2.07	8,448ms	99.98%	Healthy
154	ByteDance/Seed-2.0-code	DeepInfra	$2.10	8,448ms	99.98%	Healthy
155	ByteDance/Seed-2.0-pro	DeepInfra	$2.10	8,448ms	99.98%	Healthy
156	Qwen3.6 Plus	Together AI	$2.10	2,626ms	100.00%	Healthy
157	Qwen/Qwen3.6-27B	DeepInfra	$2.11	8,448ms	99.98%	Healthy
158	deepseek-ai/DeepSeek-V4-Pro	DeepInfra	$2.34	8,448ms	99.98%	Healthy
159	zai-org/GLM-5.2	DeepInfra	$2.36	8,448ms	99.98%	Healthy
160	XiaomiMiMo/MiMo-V2.5-Pro	DeepInfra	$2.40	8,448ms	99.98%	Healthy
161	Qwen3 Coder 480B A35B Instruct Fp8	Together AI	$2.40	2,626ms	100.00%	Healthy
162	DeepSeek R1 Distill Llama 70B	Together AI	$2.40	2,626ms	100.00%	Healthy
163	Qwen3.5 397B A17b	Together AI	$2.52	2,626ms	100.00%	Healthy
164	NVIDIA Nemotron 3 Ultra 550B A55B NVFP4	Together AI	$2.52	2,626ms	100.00%	Healthy
165	GLM 5 Fp4	Together AI	$2.52	2,626ms	100.00%	Healthy
166	moonshotai/Kimi-K2.7-Code	DeepInfra	$2.54	8,448ms	99.98%	Healthy
167	moonshotai/Kimi-K2.6	DeepInfra	$2.55	8,448ms	99.98%	Healthy
168	zai-org/GLM-5.1	DeepInfra	$2.73	8,448ms	99.98%	Healthy
169	kimi-k2.5	Moonshot AI	$2.97	—	0.00%	Degraded
170	kimi-k2.6	Moonshot AI	$2.97	—	0.00%	Degraded
171	kimi-k2.7-code	Moonshot AI	$2.97	—	0.00%	Degraded
172	moonshot-v1-128k	Moonshot AI	$2.97	—	0.00%	Degraded
173	moonshot-v1-128k-vision-preview	Moonshot AI	$2.97	—	0.00%	Degraded
174	moonshot-v1-32k	Moonshot AI	$2.97	—	0.00%	Degraded
175	moonshot-v1-32k-vision-preview	Moonshot AI	$2.97	—	0.00%	Degraded
176	moonshot-v1-8k	Moonshot AI	$2.97	—	0.00%	Degraded
177	moonshot-v1-8k-vision-preview	Moonshot AI	$2.97	—	0.00%	Degraded
178	moonshot-v1-auto	Moonshot AI	$2.97	—	0.00%	Degraded
179	Kimi K2.7 Code	Together AI	$2.97	2,626ms	100.00%	Healthy
180	Qwen3.7 Max	Together AI	$3.00	2,626ms	100.00%	Healthy
181	Deepseek V4 Pro	Together AI	$3.13	2,626ms	100.00%	Healthy
182	Kimi K2.6 Fp4	Together AI	$3.42	2,626ms	100.00%	Healthy
183	GLM 5.1 FP4	Together AI	$3.48	2,626ms	100.00%	Healthy
184	GLM 5.2	Together AI	$3.48	2,626ms	100.00%	Healthy
185	Claude Haiku 4.5	Anthropic	$3.60	—	—	—
186	anthropic/claude-haiku-4-5	DeepInfra	$3.60	8,448ms	99.98%	Healthy
187	Meta Llama 3.1 405B Instruct	Together AI	$4.20	2,626ms	100.00%	Healthy
188	Qwen/Qwen3-Max	DeepInfra	$4.32	8,448ms	99.98%	Healthy
189	Qwen/Qwen3-Max-Thinking	DeepInfra	$4.32	8,448ms	99.98%	Healthy
190	kimi-k2.7-code-highspeed	Moonshot AI	$5.94	—	0.00%	Degraded
191	Qwen2.5-VL (72B) Instruct	Together AI	$5.97	2,626ms	100.00%	Healthy
192	Qwen/Qwen3.7-Max	DeepInfra	$6.00	8,448ms	99.98%	Healthy
193	DeepSeek R1 0528 NVFP4	Together AI	$6.00	2,626ms	100.00%	Healthy
194	google/gemini-3.5-flash	DeepInfra	$6.30	8,448ms	99.98%	Healthy
195	google/gemini-2.5-pro	DeepInfra	$6.75	8,448ms	99.98%	Healthy
196	google/gemini-3.1-pro	DeepInfra	$8.40	8,448ms	99.98%	Healthy
197	Claude Sonnet 4.6	Anthropic	$10.80	—	—	—
198	anthropic/claude-sonnet-4-6	DeepInfra	$10.80	8,448ms	99.98%	Healthy
199	Claude Opus 4.8	Anthropic	$18.00	—	—	—
200	anthropic/claude-opus-4-7	DeepInfra	$18.00	8,448ms	99.98%	Healthy
201	anthropic/claude-opus-4-8	DeepInfra	$18.00	8,448ms	99.98%	Healthy

Provider scorecards

No scorecard cycle published yet.

Provider grades are published as a signed, dated snapshot rather than a number that moves under you. Until a cycle is published there is nothing here to show, and we will not fill the gap with a placeholder.