The Known Good Updated 4 Sep 2026 Subscribe
Providers· Inference host· 42 tracked models

Together — pricing & performance

Compare models All providers Data sources
Models served
42
of 1,094 tracked models
Mean output speed
72
tokens per second, averaged over
21 measured endpoints
Mean latency
1.0s
time to first token, averaged over
21 measured endpoints
Cheapest blended
$0.075
per 1M tokens at a 3:1
input:output blend
Output speed on Together

Output tokens per second for the 21 of 42 models on Together with published throughput telemetry, the most recent figure OpenRouter publishes for each host. The full table below lists all 42, measured or not. Higher is better. We do not run these measurements ourselves.

⇩
169
129
119
118
105
102
92
77
71
68
68
67
The Known Good
42 models on Together
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Arcee AI: Virtuoso Large arcee-ai $0.75 $1.20 $0.86 — — 131k
Deep Cogito: Cogito v2.1 671B deepcogito $1.25 $1.25 $1.25 — — 128k
DeepSeek: DeepSeek V4 Flash 0731 DeepSeek $0.14 $0.28 $0.17 56 0.7s 1.05M
DeepSeek: DeepSeek V4 Flash 0731 (batch) DeepSeek $0.14 $0.28 $0.17 — — 1.05M
DeepSeek: DeepSeek V4 Pro 0423 DeepSeek $1.74 $3.48 $2.17 39 0.6s 512k
DeepSeek: DeepSeek V4 Pro 0813 DeepSeek $1.32 $3.96 $1.98 92 3.0s 1.05M
DeepSeek: DeepSeek V4 Pro 0813 (batch) DeepSeek $1.32 $3.96 $1.98 — — 1.05M
Google: Gemma 3n 4B Google $0.060 $0.12 $0.075 33 0.3s 33k
Google: Gemma 4 31B Google $0.39 $0.97 $0.54 8 0.7s 262k
Google: Gemma 4 31B (batch) Google $0.39 $0.97 $0.54 — — 262k
Meta: Llama 3.3 70B Instruct Meta $1.04 $1.04 $1.04 28 0.7s 131k
Meta: Llama Guard 4 12B Meta $0.20 $0.20 $0.20 14 0.1s 1.05M
Meta: Muse Glimmer 30B Meta $0.35 $1.50 $0.64 102 5.1s 131k
Meta: Muse Glimmer 30B (batch) Meta $0.35 $1.50 $0.64 — — 131k
MiniMax: MiniMax M2.7 MiniMax $0.30 $1.20 $0.53 68 0.3s 197k
MiniMax: MiniMax M3 MiniMax $0.30 $1.20 $0.53 37 1.2s 524k
MiniMax: MiniMax M3 (batch) MiniMax $0.30 $1.20 $0.53 — — 524k
MoonshotAI: Kimi K2.6 Moonshot AI $1.20 $4.50 $2.02 119 0.4s 262k
MoonshotAI: Kimi K2.7 Code Moonshot AI $0.95 $4.00 $1.71 — — 262k
MoonshotAI: Kimi K2.7 Code (batch) Moonshot AI $0.95 $4.00 $1.71 — — 262k
MoonshotAI: Kimi K3 Moonshot AI $3.00 $15.00 $6.00 46 1.5s 1.05M
MoonshotAI: Kimi K3 (batch) Moonshot AI $3.00 $15.00 $6.00 — — 1.05M
NVIDIA: Nemotron 3 Ultra NVIDIA $0.60 $3.60 $1.35 — — 512k
NVIDIA: Nemotron 3 Ultra (batch) NVIDIA $0.60 $3.60 $1.35 — — 512k
OpenAI: gpt-oss-120b OpenAI $0.15 $0.60 $0.26 60 0.3s 131k
OpenAI: gpt-oss-120b (batch) OpenAI $0.15 $0.60 $0.26 — — 131k
OpenAI: gpt-oss-20b OpenAI $0.050 $0.20 $0.087 118 0.3s 131k
OpenAI: gpt-oss-20b (batch) OpenAI $0.050 $0.20 $0.087 — — 131k
Qwen: Qwen2.5 7B Instruct Alibaba $0.30 $0.30 $0.30 — — 33k
Qwen: Qwen3.5-9B Alibaba $0.17 $0.25 $0.19 67 0.2s 262k
Qwen: Qwen3.5-9B (batch) Alibaba $0.17 $0.25 $0.19 — — 262k
Qwen: Qwen3.8 2.4T A95B Alibaba $2.00 $6.00 $3.00 129 0.6s 1.01M
Qwen: Qwen3.8 2.4T A95B (batch) Alibaba $2.00 $6.00 $3.00 — — 1.01M
Thinking Machines: Inkling Thinking Machines $1.00 $4.05 $1.76 77 0.2s 524k
Thinking Machines: Inkling (batch) Thinking Machines $1.00 $4.05 $1.76 — — 524k
Thinking Machines: Inkling Small Thinking Machines $0.50 $1.20 $0.68 169 4.2s 524k
Thinking Machines: Inkling Small (batch) Thinking Machines $0.50 $1.20 $0.68 — — 524k
Z.ai: GLM 5.2 Z.ai $1.40 $4.40 $2.15 71 0.6s 512k
Z.ai: GLM 5.2 (batch) Z.ai $1.40 $4.40 $2.15 — — 1.05M
Z.ai: GLM 5.3 Z.ai $1.40 $4.40 $2.15 105 0.3s 1.05M
Z.ai: GLM 5.3 Flash Z.ai $0.15 $0.50 $0.24 68 0.5s 1.05M
Z.ai: GLM 5.3 Flash (batch) Z.ai $0.15 $0.50 $0.24 — — 1.05M
The Known Good
Source. Prices, endpoint availability and throughput for Together are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.