Obscurify.ai 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 15 models on this page. Coverage spans text and chat (15). The lowest-priced model hosted here is Llama-3.3-70B-Instruct.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| Llama-3.3-70B-Instructmeta-llama/llama-3.3-70b-instruct1.1× pricier | $0.055 | $0.25 | — | 128,000 | 1.1× pricier |
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash1.9× pricier | $0.12 | $0.23 | $0.023 | 1,000,000 | 1.9× pricier |
| GLM-5.3-Flashz-ai/glm-5.3-flash3.3× pricier | $0.11 | $0.33 | — | 1,000,000 | 3.3× pricier |
| Claude Haiku 5.5anthropic/claude-haiku-5.52.2× pricier | $0.11 | $0.55 | $0.011 | 1,000,000 | 2.2× pricier |
| GPT-6 Lunaopenai/gpt-6-luna2.8× pricier | $0.11 | $0.55 | $0.011 | 1,050,000 | 2.8× pricier |
| Qwen3-Coder 480B-A35B Instructqwen/qwen3-coder1.1× pricier | $0.14 | $0.55 | — | 262,000 | 1.1× pricier |
| MiniMax-M3.1-Flashminimax/minimax-m3.1-flash8.3× pricier | $0.17 | $0.66 | $0.017 | 1,000,000 | 8.3× pricier |
| Qwen3.8 27Bqwen/qwen3.8-27b2.8× pricier | $0.17 | $0.77 | $0.044 | 262,144 | 2.8× pricier |
| GLM-5.3z-ai/glm-5.32.3× pricier | $0.66 | $1.22 | $0.22 | 1,000,000 | 2.3× pricier |
| DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-08131.4× pricier | $0.73 | $2.76 | $0.044 | 1,000,000 | 1.4× pricier |
| Kimi K2 Instruct 0905moonshotai/kimi-k2-09051.9× pricier | $0.78 | $3.25 | — | 262,144 | 1.9× pricier |
| Gemini 3.8 Flashgoogle/gemini-3.8-flash2.4× pricier | $0.83 | $4.14 | $0.083 | 1,048,576 | 2.4× pricier |
| Grok 4.7x-ai/grok-4.711.1× pricier | $2.21 | $6.63 | $0.55 | 500,000 | 11.1× pricier |
| Claude Sonnet 5.5anthropic/claude-sonnet-5.53.2× pricier | $2.21 | $11.05 | $0.11 | 1,000,000 | 3.2× pricier |
| GPT-5.5openai/gpt-5.514.2× pricier | $5.53 | $33.15 | $0.55 | 1,050,000 | 14.2× pricier |