---
id: "togetherai"
gateways: ["vercel"]
models: 23
endpoints: 32
tokens_week: 0
token_share: "0.0%"
rank: 106
cheapest_on: "5 of 32 shared models"
cheaper_than: "50% of offers at the median"
uptime_1d: 96.1000
latency_p50_ms: 329
tokens_per_second: 118
trains_on_some: false
retains_on_some: false
quantization: "fp4 (6), fp8 (3)"
---
# togetherai

`alibaba/qwen3.6-plus`, `alibaba/qwen3.8-2.4t-a95b`, `deepseek/deepseek-v4.1-flash`, `deepseek/deepseek-v4.1-flash-1017`, `deepseek/deepseek-v4-flash-0731`, `deepseek/deepseek-v4-pro`, `google/gemma-4-31b-it`, `meta/muse-glimmer-30b`, `meta/muse-spark-open`, `minimax/minimax-m3.1-flash`, `moonshotai/kimi-k2.6`, `moonshotai/kimi-k3`, `moonshotai/kimi-k3.1-pro`, `nvidia/nemotron-3.5-super-vl`, `nvidia/nemotron-3-ultra-550b-a55b`, `openai/gpt-oss-120b`, `openai/gpt-oss-20b`, `reflection/beam`, `thinkingmachines/inkling`, `thinkingmachines/inkling-small`, `zai/glm-5.2`, `zai/glm-5.3`, `zai/glm-5.3-flash`