PROVIDER PRICING
Together AI API Pricing
Together AI API pricing: rates for 53 models, how they compare to official pricing, and what it costs to run.
MODEL PRICING
API model pricing
53 models · prices per million tokens
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Multilingual e5 large instruct | $0.020 | — |
| gpt-oss-20B | $0.050 | $0.200 |
| Gemma 3n E4B Instruct | $0.060 | $0.120 |
| Llama 3 8B Instruct Lite | $0.140 | $0.140 |
| gpt-oss-120B | $0.150 | $0.600 |
| Rnj-1 Instruct | $0.150 | $0.150 |
| Qwen3.5 9B | $0.170 | $0.250 |
| Qwen3 235B A22B Instruct 2507 FP8 | $0.200 | $0.600 |
| Gemma-4-31B-it-Pearl | $0.280 | $0.860 |
| MiniMax M2.7 | $0.300 | $1.20 |
| MiniMax M3 | $0.300 | $1.20 |
| Qwen2.5 7B Instruct Turbo | $0.300 | $0.300 |
| Qwen3.7-Plus | $0.320 | $1.28 |
| Gemma 4 31B | $0.390 | $0.970 |
| Qwen3.6-Plus | $0.500 | $3.00 |
| NVIDIA Nemotron 3 Ultra | $0.600 | $3.60 |
| Qwen3.5-397B-A17B | $0.600 | $3.60 |
| Kimi K2.7 Code | $0.950 | $4.00 |
| Inkling | $1.00 | $4.05 |
| Llama 3.3 70B | $1.04 | $1.04 |
| Kimi K2.6 | $1.20 | $4.50 |
| Cogito v2.1 671B | $1.25 | $1.25 |
| Qwen3.7-Max | $1.25 | $3.75 |
| GLM-5.1 | $1.40 | $4.40 |
| GLM-5.2 | $1.40 | $4.40 |
| DeepSeek V4 Pro | $1.74 | $3.48 |
| FLUX.1 Kontext [max] | — | — |
| FLUX.1 Kontext [pro] | — | — |
| FLUX.1 [schnell] | — | — |
| FLUX.2 [dev] | — | — |
| FLUX.2 [flex] | — | — |
| FLUX.2 [pro] | — | — |
Prices change frequently; confirm current rates on the provider’s official pricing page.