Synthetic is a third-party gateway that routes to many upstream models through one API. Gateway quotes are often among the lowest on the site, but availability, rate limits and routing can vary between models, so a low headline price is worth verifying against your own workload.
It lists 11 models on this page. Coverage spans text and chat (11). The lowest-priced model hosted here is GPT OSS 120B.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| GPT OSS 120Bhf:openai/gpt-oss-120b | $0.10 | $0.10 | $0.10 | 131,072 | 1.7× pricier |
| GLM-4.7-Flashhf:zai-org/GLM-4.7-Flash | $0.10 | $0.50 | $0.10 | 196,608 | 1.4× pricier |
| GLM-5.3-Flashhf:zai-org/GLM-5.3-Flash | $0.15 | $0.50 | $0.04 | 524,288 | 5.0× pricier |
| Nemotron 3 Super 120B A12Bhf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | $0.30 | $1.00 | $0.30 | 262,144 | 4.7× pricier |
| DeepSeek V4.1 Flashhf:deepseek-ai/DeepSeek-V4.1-Flash | $0.60 | $1.20 | $0.03 | 524,288 | 15.0× pricier |
| MiniMax-M3hf:MiniMaxAI/MiniMax-M3 | $0.60 | $1.20 | $0.60 | 524,288 | 2.0× pricier |
| Qwen3.6 27Bhf:Qwen/Qwen3.6-27B | $0.45 | $3.60 | $0.45 | 262,144 | 2.4× pricier |
| Kimi K2.7 Codehf:moonshotai/Kimi-K2.7-Code | $0.95 | $4.00 | $0.95 | 262,144 | 3.6× pricier |
| GLM-5.2hf:zai-org/GLM-5.2 | $1.40 | $4.40 | $1.40 | 524,288 | 4.4× pricier |
| GLM-5.3hf:zai-org/GLM-5.3 | $1.40 | $4.40 | $0.26 | 524,288 | 3.3× pricier |
| Kimi K3hf:moonshotai/Kimi-K3 | $3.00 | $15.00 | $0.45 | 524,288 | 1.7× pricier |