Together AI
together, the name to use in providers=
- Models offered
- 32
- Billing currency
- USD
- Runs
- hosted
- Fees
- none
Models
| Model | Model id here | Status | Input per 1M | Output per 1M |
|---|---|---|---|---|
| Beam 1.0 501B A23B | reflection/Beam-1.0-501B-A23B | ga | $0.4 | $1.2 |
| DeepSeek V4 Flash 0731 | deepseek-ai/DeepSeek-V4-Flash-0731 | deprecated | $0.14 | $0.28 |
| DeepSeek V4 Pro | deepseek-ai/DeepSeek-V4-Pro-0813 | ga | $1.32 | $3.96 |
| DeepSeek V4.1 Flash | deepseek-ai/DeepSeek-V4.1-Flash | ga | $0.3 | $1.2 |
| DeepSeek-R1 | deepseek-ai/DeepSeek-R1 | deprecated | $3 | $7 |
| DeepSeek-V3 | deepseek-ai/DeepSeek-V3 | deprecated | $1.25 | $1.25 |
| DeepSeek-V3.1 | deepseek-ai/DeepSeek-V3-1 | deprecated | $0.6 | $1.7 |
| GLM-5 | zai-org/GLM-5 | deprecated | $1 | $3.2 |
| GLM-5.1 | zai-org/GLM-5.1 | deprecated | $1.4 | $4.4 |
| GLM-5.2 | zai-org/GLM-5.2 | ga | $1.4 | $4.4 |
| GLM-5.3 | zai-org/GLM-5.3 | ga | $1.4 | $4.4 |
| GLM-5.3-Flash | zai-org/GLM-5.3-Flash | ga | $0.15 | $0.5 |
| GPT OSS 120B | openai/gpt-oss-120b | ga | $0.15 | $0.6 |
| Inkling | thinkingmachines/Inkling | ga | $1 | $4.05 |
| Kimi K3 | moonshotai/Kimi-K3 | ga | $3 | $15 |
| LFM2-24B-A2B | LiquidAI/LFM2-24B-A2B | deprecated | $0.03 | $0.12 |
| Llama-3.3-70B-Instruct | meta-llama/Llama-3.3-70B-Instruct-Turbo | deprecated | $1.04unverified | $1.04 |
| MiniMax-M2.5 | MiniMaxAI/MiniMax-M2.5 | deprecated | $0.3unverified | $1.2 |
| MiniMax-M2.7 | MiniMaxAI/MiniMax-M2.7 | deprecated | $0.3 | $1.2 |
| MiniMax-M3 | MiniMaxAI/MiniMax-M3 | ga | $0.3 | $1.2 |
| Muse Spark Open | meta-models/Muse-Spark-Open-816B-A42B | ga | $1.25 | $4.25 |
| Nemotron 3 Ultra 550B A55B | nvidia/nemotron-3-ultra-550b-a55b | deprecated | $0.6 | $3.6 |
| Nemotron 3.5 Super VL (free) | nvidia/NVIDIA-Nemotron-3.5-Super-VL | ga | $0.15 | $0.5 |
| Qwen 2.5 7B Instruct Turbo | Qwen/Qwen2.5-7B-Instruct-Turbo | deprecated | $0.3 | $0.3 |
| Qwen3 235B A22B Instruct 2507 | Qwen/Qwen3-235B-A22B-Instruct-2507-tput | deprecated | $0.2 | $0.6 |
| Qwen3 Coder 480B A35B | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | deprecated | $2 | $2 |
| Qwen3 Coder Next | Qwen/Qwen3-Coder-Next-FP8 | deprecated | $0.5 | $1.2 |
| Qwen3.5 397B-A17B | Qwen/Qwen3.5-397B-A17B | deprecated | $0.6unverified | $3.6 |
| Qwen3.5 9B | Qwen/Qwen3.5-9B | ga | $0.17unverified | $0.25 |
| Qwen3.6 Plus | Qwen/Qwen3.6-Plus | ga | $0.5 | $3 |
| Qwen3.7 Max | Qwen/Qwen3.7-Max | ga | $2.5unverified | $7.5 |
| Rnj-1 Instruct | essentialai/Rnj-1-Instruct | deprecated | $0.15 | $0.15 |
Built from catalog version 2026-11-04.3 of . Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).