200+ open-source models including Llama, Qwen, DBRX, and more with throughput-optimized inference.
| Model | Input per 1M tokens | Output per 1M tokens |
|---|---|---|
| Qwen/Qwen2.5-7B-Instruct-Turbo | $0.3000 | $0.3000 |
| Qwen/Qwen3-235B-A22B-Instruct-2507-tput | $0.2000 | $0.6000 |
| Qwen/Qwen3.5-397B-A17B | $0.6000 | $3.60 |
| Qwen/Qwen3.5-9B | $0.1700 | $0.2500 |
| Qwen/Qwen3.6-Plus | $0.5000 | $3.00 |
| deepcogito/cogito-v2-1-671b | $1.25 | $1.25 |
| essentialai/rnj-1-instruct | $0.1500 | $0.1500 |
| meta-llama/Meta-Llama-3-8B-Instruct-Lite | $0.1400 | $0.1400 |
| openai/gpt-oss-120b | $0.1500 | $0.6000 |
| together/deepseek-v4-1-flash | $0.3000 | $1.20 |
| together/deepseek-v4-1-flash-1017 | $0.3000 | $1.20 |
| together/deepseek-v4-pro-0813 | $1.32 | $3.96 |
| together/glm-5-3 | $1.40 | $4.40 |
| together/glm-5-3-flash | $0.1500 | $0.5000 |
| together/glm-52 | $1.40 | $4.40 |
| together/inkling | $1.00 | $4.05 |
| together/kimi-k3 | $3.00 | $15.00 |
| together/minimax-m3 | $0.3000 | $1.20 |
| together/minimax-m3-1-flash | $0.1500 | $0.6000 |
| together/muse-glimmer | $0.3500 | $1.50 |
| together/muse-spark-open | $1.25 | $4.25 |
| together/nemotron-3-5-super-vl | $0.1500 | $0.5000 |
| together/prism-ml-ternary-bonsai-27b | $0.0000 | $0.0000 |
| together/qwen3-8-flash | $0.1500 | $0.4700 |
| together/qwen3-8-max | $2.00 | $6.00 |
| together/qwen37-max | $1.50 | $4.50 |
| together/qwen37-plus | $0.3200 | $1.28 |
| together/reflection-beam | $0.4000 | $1.20 |
| together/tev1-4b-experimental | $0.0400 | N/A |