- Models
- 22
- listed and live
- Location
- Non-EU
- where requests are served
- Trains on prompts
- Not declared
- nothing published yet
- Keeps prompts
- Not declared
- nothing published yet
Models
What OpenAI serves on llm.buzz, at its own prices.
| Model | Input | Output | Cache read | Context | Latency | Uptime (3d) |
|---|---|---|---|---|---|---|
 openai/gpt-4.1 | $2.00 | $8.00 | $0.50 | 1M | 1.20 s | 100% |
openai/gpt-4.1-mini | $0.40 | $1.60 | $0.10 | 1M | 1.00 s | 100% |
openai/gpt-4o-mini | $0.15 | $0.60 | $0.075 | 128K | 0.83 s | 100% |
openai/gpt-5-mini | $0.25 | $2.00 | $0.025 | 400K | 2.48 s | 100% |
openai/gpt-5-nano | $0.05 | $0.40 | $0.005 | 400K | 2.48 s | 100% |
openai/gpt-5.4 | $2.50 | $15.00 | $0.25 | 1.1M | 1.00 s | 100% |
openai/gpt-5.4-mini | $0.75 | $4.50 | $0.075 | 400K | 1.00 s | 100% |
openai/gpt-5.4-nano | $0.20 | $1.25 | $0.02 | 400K | 0.69 s | 100% |
openai/gpt-5.5 | $5.00 | $30.00 | $0.50 | 1.1M | 2.07 s | 100% |
openai/gpt-5.6-luna | $0.20 | $1.20 | $0.02 | 1.1M | 1.72 s | 100% |
openai/gpt-5.6-sol | $4.00 | $20.00 | $0.40 | 1.1M | 3.57 s | 100% |
openai/gpt-5.6-terra | $2.00 | $12.00 | $0.20 | 1.1M | 1.44 s | 98.6% |
openai/gpt-6-astra | $10.00 | $50.00 | $1.00 | 1.1M | 1.72 s | 100% |
openai/gpt-6-luna | $0.10 | $0.50 | $0.01 | 1.1M | 2.48 s | 100% |
openai/gpt-6-sol | $2.00 | $10.00 | $0.20 | 1.1M | 4.29 s | 100% |
openai/gpt-6.1-sol | $2.00 | $10.00 | $0.10 | 1.1M | 2.07 s | 100% |
openai/gpt-image-2 | $5.00 | $30.00 | n/a | n/a | n/a | n/a |
openai/gpt-image-2.5-flare | $5.00 | $30.00 | n/a | n/a | n/a | n/a |
openai/gpt-image-2.5-sunburst | $5.00 | $30.00 | n/a | n/a | n/a | n/a |
openai/text-embedding-3-large | $0.13 | n/a | n/a | 8K | n/a | n/a |
openai/text-embedding-3-small | $0.02 | n/a | n/a | 8K | n/a | n/a |
openai/text-embedding-ada-002 | $0.10 | n/a | n/a | 8K | n/a | n/a |
OpenAI's own prices, in USD per million tokens. Latency is the median time to first token over 24 hours.
Call OpenAI's models with one keyThe same key reaches every provider here; each request pays the price of the provider that answered it.