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.
#ModelProviderPrice / MTTFT p95UptimeStatus
1Qwen 2 Instruct (1.5B)Together AI$0.022,980ms63.18%Degraded
2meta-llama/Meta-Llama-3.1-8B-Instruct-TurboDeepInfra$0.039,121ms99.99%Healthy
3mistralai/Mistral-Nemo-Instruct-2407DeepInfra$0.049,121ms99.99%Healthy
4meta-llama/Meta-Llama-3.1-8B-InstructDeepInfra$0.049,121ms99.99%Healthy
5Sao10K/L3-8B-Lunaris-v1-TurboDeepInfra$0.059,121ms99.99%Healthy
6Meta Llama 3.2 1B InstructTogether AI$0.072,980ms63.18%Degraded
7Meta Llama 3.2 3B InstructTogether AI$0.072,980ms63.18%Degraded
8mistralai/Mistral-Small-24B-Instruct-2501DeepInfra$0.089,121ms99.99%Healthy
9google/gemma-3-4b-itDeepInfra$0.099,121ms99.99%Healthy
10LFM2-24B-A2BTogether AI$0.092,980ms63.18%Degraded
11openai/gpt-oss-20bDeepInfra$0.109,121ms99.99%Healthy
12Gemma 3N E4B InstructTogether AI$0.112,980ms63.18%Degraded
13Qwen/Qwen3-235B-A22B-Instruct-2507DeepInfra$0.119,121ms99.99%Healthy
14Trinity MiniTogether AI$0.122,980ms63.18%Degraded
15google/gemma-3-12b-itDeepInfra$0.129,121ms99.99%Healthy
16Arize AI Qwen 2 1.5B InstructTogether AI$0.122,980ms63.18%Degraded
17openai/gpt-oss-120bDeepInfra$0.139,121ms99.99%Healthy
18microsoft/phi-4DeepInfra$0.139,121ms99.99%Healthy
19google/gemma-3-27b-itDeepInfra$0.149,121ms99.99%Healthy
20Qwen/Qwen3.5-9BDeepInfra$0.159,121ms99.99%Healthy
21nvidia/Nemotron-3-Nano-30B-A3BDeepInfra$0.159,121ms99.99%Healthy
22OpenAI GPT-OSS 20BTogether AI$0.152,980ms63.18%Degraded
23deepseek-ai/DeepSeek-V4-FlashDeepInfra$0.169,121ms99.99%Healthy
24mistralai/Mistral-Small-3.2-24B-Instruct-2506DeepInfra$0.179,121ms99.99%Healthy
25Meta Llama 3 8B Instruct LiteTogether AI$0.172,980ms63.18%Degraded
26Nvidia Nemotron Nano 9B V2Together AI$0.192,980ms63.18%Degraded
27Qwen/Qwen3-14BDeepInfra$0.229,121ms99.99%Healthy
28Qwen/Qwen3-32BDeepInfra$0.229,121ms99.99%Healthy
29meta-llama/Llama-Guard-4-12BDeepInfra$0.229,121ms99.99%Healthy
30DeepSeek R1 Distill Qwen 1.5BTogether AI$0.222,980ms63.18%Degraded
31Meta Llama 3.1 8B Instruct TurboTogether AI$0.222,980ms63.18%Degraded
32meta-llama/Llama-4-Scout-17B-16E-InstructDeepInfra$0.249,121ms99.99%Healthy
33nvidia/Nemotron-Content-Safety-3.5DeepInfra$0.249,121ms99.99%Healthy
34Meta Llama 3 8B Instruct ReferenceTogether AI$0.242,980ms63.18%Degraded
35Meta Llama 3 8B InstructTogether AI$0.242,980ms63.18%Degraded
36Meta Llama 3.1 8BTogether AI$0.242,980ms63.18%Degraded
37Ministral 3 14B Instruct 2512Together AI$0.242,980ms63.18%Degraded
38Mistral (7B) Instruct v0.1Together AI$0.242,980ms63.18%Degraded
39Mistral (7B) Instruct v0.3Together AI$0.242,980ms63.18%Degraded
40Mistral Small (24B) Instruct 25.01Together AI$0.242,980ms63.18%Degraded
41google/gemma-4-26B-A4B-itDeepInfra$0.259,121ms99.99%Healthy
42meta-llama/Llama-3.3-70B-Instruct-TurboDeepInfra$0.259,121ms99.99%Healthy
43Qwen3.5 9B FP8Together AI$0.252,980ms63.18%Degraded
44zai-org/GLM-4.7-FlashDeepInfra$0.289,121ms99.99%Healthy
45nvidia/NVIDIA-Nemotron-3-Super-120B-A12BDeepInfra$0.299,121ms99.99%Healthy
46google/gemma-4-31B-it-turboDeepInfra$0.299,121ms99.99%Healthy
47ByteDance/Seed-2.0-miniDeepInfra$0.309,121ms99.99%Healthy
48google/gemma-4-31B-itDeepInfra$0.319,121ms99.99%Healthy
49Qwen2.5 7B Instruct TurboTogether AI$0.362,980ms63.18%Degraded
50Qwen/Qwen3-30B-A3BDeepInfra$0.379,121ms99.99%Healthy
51deepseek-ai/DeepSeek-V3.2DeepInfra$0.389,121ms99.99%Healthy
52meta-llama/Llama-3.2-11B-Vision-InstructDeepInfra$0.419,121ms99.99%Healthy
53Qwen/Qwen3-VL-30B-A3B-InstructDeepInfra$0.459,121ms99.99%Healthy
54meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8DeepInfra$0.459,121ms99.99%Healthy
55openai/gpt-oss-120b-TurboDeepInfra$0.459,121ms99.99%Healthy
56OpenAI GPT-OSS 120BTogether AI$0.452,980ms63.18%Degraded
57Qwen/Qwen2.5-72B-InstructDeepInfra$0.469,121ms99.99%Healthy
58Llama 4 Scout Instruct (17Bx16E)Together AI$0.462,980ms63.18%Degraded
59Gryphe/MythoMax-L2-13bDeepInfra$0.489,121ms99.99%Healthy
60meta-llama/Meta-Llama-3.1-70B-Instruct-TurboDeepInfra$0.489,121ms99.99%Healthy
61nvidia/Llama-3.3-Nemotron-Super-49B-v1.5DeepInfra$0.489,121ms99.99%Healthy
62Qwen3 235B A22B Instruct 2507 FP8 ThroughputTogether AI$0.482,980ms63.18%Degraded
63Qwen3-VL-8B-InstructTogether AI$0.522,980ms63.18%Degraded
64deepseek-ai/DeepSeek-V3.1DeepInfra$0.609,121ms99.99%Healthy
65nvidia/Nemotron-3-Nano-Omni-30B-A3B-ReasoningDeepInfra$0.609,121ms99.99%Healthy
66MiniMaxAI/MiniMax-M2.5Nebius Token Factory$0.606,917ms99.97%Healthy
67NousResearch/Hermes-4-405BNebius Token Factory$0.606,917ms99.97%Healthy
68NousResearch/Hermes-4-70BNebius Token Factory$0.606,917ms99.97%Healthy
69Qwen/Qwen2.5-VL-72B-InstructNebius Token Factory$0.606,917ms99.97%Healthy
70Qwen/Qwen3-235B-A22B-Instruct-2507Nebius Token Factory$0.606,917ms99.97%Healthy
71Qwen/Qwen3-30B-A3B-Instruct-2507Nebius Token Factory$0.606,917ms99.97%Healthy
72Qwen/Qwen3-32BNebius Token Factory$0.606,917ms99.97%Healthy
73Qwen/Qwen3-Embedding-8BNebius Token Factory$0.606,917ms99.97%Healthy
74Qwen/Qwen3-Next-80B-A3B-ThinkingNebius Token Factory$0.606,917ms99.97%Healthy
75Qwen/Qwen3.5-397B-A17BNebius Token Factory$0.606,917ms99.97%Healthy
76deepseek-ai/DeepSeek-V4-ProNebius Token Factory$0.606,917ms99.97%Healthy
77google/gemma-3-27b-itNebius Token Factory$0.606,917ms99.97%Healthy
78meta-llama/Llama-3.3-70B-InstructNebius Token Factory$0.606,917ms99.97%Healthy
79moonshotai/Kimi-K2.6Nebius Token Factory$0.606,917ms99.97%Healthy
80moonshotai/Kimi-K2.7-CodeNebius Token Factory$0.606,917ms99.97%Healthy
81nvidia/Cosmos3-Super-ReasonerNebius Token Factory$0.606,917ms99.97%Healthy
82nvidia/Llama-3_1-Nemotron-Ultra-253B-v1Nebius Token Factory$0.606,917ms99.97%Healthy
83nvidia/NVIDIA-Nemotron-3-Nano-30B-A3BNebius Token Factory$0.606,917ms99.97%Healthy
84nvidia/Nemotron-3-Nano-OmniNebius Token Factory$0.606,917ms99.97%Healthy
85nvidia/Nemotron-3-Ultra-550b-a55bNebius Token Factory$0.606,917ms99.97%Healthy
86nvidia/nemotron-3-super-120b-a12bNebius Token Factory$0.606,917ms99.97%Healthy
87openai/gpt-oss-120bNebius Token Factory$0.606,917ms99.97%Healthy
88openbmb/MiniCPM-V-4_5Nebius Token Factory$0.606,917ms99.97%Healthy
89zai-org/GLM-5.1Nebius Token Factory$0.606,917ms99.97%Healthy
90zai-org/GLM-5.2Nebius Token Factory$0.606,917ms99.97%Healthy
91Qwen/Qwen3-VL-235B-A22B-InstructDeepInfra$0.659,121ms99.99%Healthy
92Qwen/Qwen3.6-35B-A3BDeepInfra$0.669,121ms99.99%Healthy
93Qwen/Qwen3.5-35B-A3BDeepInfra$0.689,121ms99.99%Healthy
94deepseek-ai/DeepSeek-V3-0324DeepInfra$0.689,121ms99.99%Healthy
95Pearl-ai Gemma-4-31B-it-pearlTogether AI$0.682,980ms63.18%Degraded
96Qwen/Qwen3-Next-80B-A3B-InstructDeepInfra$0.719,121ms99.99%Healthy
97Nous Hermes 2 Mixtral 8X7B DpoTogether AI$0.722,980ms63.18%Degraded
98Mixtral-8x7B Instruct v0.1Together AI$0.722,980ms63.18%Degraded
99deepseek-ai/DeepSeek-V3DeepInfra$0.739,121ms99.99%Healthy
100deepseek-ai/DeepSeek-V3.1-TerminusDeepInfra$0.739,121ms99.99%Healthy
101MiniMaxAI/MiniMax-M2.7DeepInfra$0.759,121ms99.99%Healthy
102MiniMaxAI/MiniMax-M2.5DeepInfra$0.789,121ms99.99%Healthy
103Qwen/Qwen3-Coder-480B-A35B-Instruct-TurboDeepInfra$0.789,121ms99.99%Healthy
104Glm 4.5 Air Fp8Together AI$0.782,980ms63.18%Degraded
105stepfun-ai/Step-3.7-FlashDeepInfra$0.819,121ms99.99%Healthy
106Gemma 4 31B-it FP8Together AI$0.822,980ms63.18%Degraded
107NousResearch/Hermes-3-Llama-3.1-70BDeepInfra$0.849,121ms99.99%Healthy
108MiniMaxAI/MiniMax-M3DeepInfra$0.909,121ms99.99%Healthy
109deepseek-v4-flashDeepSeek$0.902,447ms97.65%Degraded
110deepseek-v4-proDeepSeek$0.902,447ms97.65%Degraded
111MiniMax M2.7 FP4Together AI$0.902,980ms63.18%Degraded
112MiniMax M3Together AI$0.902,980ms63.18%Degraded
113Qwen 2.5 14B InstructTogether AI$0.962,980ms63.18%Degraded
114Qwen 2.5 Coder 32B InstructTogether AI$0.962,980ms63.18%Degraded
115Qwen3.7 PlusTogether AI$0.962,980ms63.18%Degraded
116Deepseek Coder 33B InstructTogether AI$0.962,980ms63.18%Degraded
117Gemma-2 Instruct (27B)Together AI$0.962,980ms63.18%Degraded
118Qwen3 Next 80B A3b InstructTogether AI$0.992,980ms63.18%Degraded
119Qwen3 Next 80B A3b ThinkingTogether AI$0.992,980ms63.18%Degraded
120Sao10K/L3.1-70B-Euryale-v2.2DeepInfra$1.029,121ms99.99%Healthy
121Qwen3 Coder Next Fp8Together AI$1.022,980ms63.18%Degraded
122google/gemini-3.1-flash-liteDeepInfra$1.059,121ms99.99%Healthy
123Meta Llama 3 70B Instruct TurboTogether AI$1.062,980ms63.18%Degraded
124Meta Llama 3.1 70B Instruct TurboTogether AI$1.062,980ms63.18%Degraded
125Llama 3.1 Nemotron 70B Instruct HFTogether AI$1.062,980ms63.18%Degraded
126Qwen2 72B InstructTogether AI$1.082,980ms63.18%Degraded
127NousResearch/Hermes-3-Llama-3.1-405BDeepInfra$1.209,121ms99.99%Healthy
128Qwen3-VL-32B-InstructTogether AI$1.202,980ms63.18%Degraded
129Meta Llama 3.3 70B Instruct TurboTogether AI$1.252,980ms63.18%Degraded
130zai-org/GLM-4.7DeepInfra$1.299,121ms99.99%Healthy
131zai-org/GLM-4.6DeepInfra$1.309,121ms99.99%Healthy
132ByteDance/Seed-1.8DeepInfra$1.359,121ms99.99%Healthy
133Deepseek V3.1 NVFP4Together AI$1.382,980ms63.18%Degraded
134MiniMaxAI/MiniMax-M2.7-TurboDeepInfra$1.449,121ms99.99%Healthy
135XiaomiMiMo/MiMo-V2.5DeepInfra$1.449,121ms99.99%Healthy
136Qwen QwQ-32BTogether AI$1.442,980ms63.18%Degraded
137Qwen2-VL (72B) InstructTogether AI$1.442,980ms63.18%Degraded
138Qwen2.5 72B InstructTogether AI$1.442,980ms63.18%Degraded
139Qwen2.5 72B Instruct TurboTogether AI$1.442,980ms63.18%Degraded
140GLM 4.7 FP8Together AI$1.472,980ms63.18%Degraded
141Cogito v2.1 671BTogether AI$1.502,980ms63.18%Degraded
142Qwen/Qwen3-235B-A22B-Thinking-2507DeepInfra$1.529,121ms99.99%Healthy
143deepseek-ai/DeepSeek-R1-0528DeepInfra$1.599,121ms99.99%Healthy
144zai-org/GLM-5DeepInfra$1.619,121ms99.99%Healthy
145Qwen/Qwen3.5-122B-A10BDeepInfra$1.619,121ms99.99%Healthy
146moonshotai/Kimi-K2.5DeepInfra$1.629,121ms99.99%Healthy
147nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55BDeepInfra$1.629,121ms99.99%Healthy
148google/gemini-2.5-flashDeepInfra$1.689,121ms99.99%Healthy
149GLM 4.6 Fp8Together AI$1.682,980ms63.18%Degraded
150Qwen/Qwen3.5-27BDeepInfra$1.729,121ms99.99%Healthy
151DeepSeek R1 Distill Qwen 14BTogether AI$1.922,980ms63.18%Degraded
152Kimi K2.5 Fp4Together AI$1.982,980ms63.18%Degraded
153Qwen/Qwen3.5-397B-A17BDeepInfra$2.079,121ms99.99%Healthy
154ByteDance/Seed-2.0-codeDeepInfra$2.109,121ms99.99%Healthy
155ByteDance/Seed-2.0-proDeepInfra$2.109,121ms99.99%Healthy
156Qwen3.6 PlusTogether AI$2.102,980ms63.18%Degraded
157Qwen/Qwen3.6-27BDeepInfra$2.119,121ms99.99%Healthy
158deepseek-ai/DeepSeek-V4-ProDeepInfra$2.349,121ms99.99%Healthy
159zai-org/GLM-5.2DeepInfra$2.369,121ms99.99%Healthy
160XiaomiMiMo/MiMo-V2.5-ProDeepInfra$2.409,121ms99.99%Healthy
161Qwen3 Coder 480B A35B Instruct Fp8Together AI$2.402,980ms63.18%Degraded
162DeepSeek R1 Distill Llama 70BTogether AI$2.402,980ms63.18%Degraded
163Qwen3.5 397B A17bTogether AI$2.522,980ms63.18%Degraded
164NVIDIA Nemotron 3 Ultra 550B A55B NVFP4Together AI$2.522,980ms63.18%Degraded
165GLM 5 Fp4Together AI$2.522,980ms63.18%Degraded
166moonshotai/Kimi-K2.7-CodeDeepInfra$2.549,121ms99.99%Healthy
167moonshotai/Kimi-K2.6DeepInfra$2.559,121ms99.99%Healthy
168zai-org/GLM-5.1DeepInfra$2.739,121ms99.99%Healthy
169kimi-k2.5Moonshot AI$2.97—0.00%Degraded
170kimi-k2.6Moonshot AI$2.97—0.00%Degraded
171kimi-k2.7-codeMoonshot AI$2.97—0.00%Degraded
172moonshot-v1-128kMoonshot AI$2.97—0.00%Degraded
173moonshot-v1-128k-vision-previewMoonshot AI$2.97—0.00%Degraded
174moonshot-v1-32kMoonshot AI$2.97—0.00%Degraded
175moonshot-v1-32k-vision-previewMoonshot AI$2.97—0.00%Degraded
176moonshot-v1-8kMoonshot AI$2.97—0.00%Degraded
177moonshot-v1-8k-vision-previewMoonshot AI$2.97—0.00%Degraded
178moonshot-v1-autoMoonshot AI$2.97—0.00%Degraded
179Kimi K2.7 CodeTogether AI$2.972,980ms63.18%Degraded
180Qwen3.7 MaxTogether AI$3.002,980ms63.18%Degraded
181Deepseek V4 ProTogether AI$3.132,980ms63.18%Degraded
182Kimi K2.6 Fp4Together AI$3.422,980ms63.18%Degraded
183GLM 5.1 FP4Together AI$3.482,980ms63.18%Degraded
184GLM 5.2Together AI$3.482,980ms63.18%Degraded
185Claude Haiku 4.5Anthropic$3.60———
186anthropic/claude-haiku-4-5DeepInfra$3.609,121ms99.99%Healthy
187Meta Llama 3.1 405B InstructTogether AI$4.202,980ms63.18%Degraded
188Qwen/Qwen3-MaxDeepInfra$4.329,121ms99.99%Healthy
189Qwen/Qwen3-Max-ThinkingDeepInfra$4.329,121ms99.99%Healthy
190kimi-k2.7-code-highspeedMoonshot AI$5.94—0.00%Degraded
191Qwen2.5-VL (72B) InstructTogether AI$5.972,980ms63.18%Degraded
192Qwen/Qwen3.7-MaxDeepInfra$6.009,121ms99.99%Healthy
193DeepSeek R1 0528 NVFP4Together AI$6.002,980ms63.18%Degraded
194google/gemini-3.5-flashDeepInfra$6.309,121ms99.99%Healthy
195google/gemini-2.5-proDeepInfra$6.759,121ms99.99%Healthy
196google/gemini-3.1-proDeepInfra$8.409,121ms99.99%Healthy
197Claude Sonnet 4.6Anthropic$10.80———
198anthropic/claude-sonnet-4-6DeepInfra$10.809,121ms99.99%Healthy
199Claude Opus 4.8Anthropic$18.00———
200anthropic/claude-opus-4-7DeepInfra$18.009,121ms99.99%Healthy
201anthropic/claude-opus-4-8DeepInfra$18.009,121ms99.99%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.