Inference provider
47 models served. Speed, latency and price below are medians across this provider's catalogue, not per-endpoint measurements.
Models served
47
Median output speed
95 t/s
Median latency
902ms
Median price / 1M
$1.5
Catalogue
Strongest and fastest on this provider
What the catalogue looks like at the top end, on the two axes that usually decide the choice.
Highest Intelligence Index
Among models this provider serves
- Claude Opus 5.5Anthropic57.6
- Claude Sonnet 5.5Anthropic56.0
- Claude Fable 5.1Anthropic53.4
- Gemini 4 ArgonGoogle52.6
- Claude Opus 5Anthropic50.8
- Claude Fable 5Anthropic49.6
- Claude Haiku 5.5Anthropic43.4
- Claude Opus 4.8Anthropic41.8
- Gemini 3.8 FlashGoogle40.9
- Claude Opus 4.7Anthropic40.7
View as table
| Model | Intelligence |
|---|---|
| Claude Opus 5.5 (Anthropic) | 57.6 |
| Claude Sonnet 5.5 (Anthropic) | 56.0 |
| Claude Fable 5.1 (Anthropic) | 53.4 |
| Gemini 4 Argon (Google) | 52.6 |
| Claude Opus 5 (Anthropic) | 50.8 |
| Claude Fable 5 (Anthropic) | 49.6 |
| Claude Haiku 5.5 (Anthropic) | 43.4 |
| Claude Opus 4.8 (Anthropic) | 41.8 |
| Gemini 3.8 Flash (Google) | 40.9 |
| Claude Opus 4.7 (Anthropic) | 40.7 |
Fastest output
Median tokens per second
- gpt-oss-120bOpenAI641 t/s
- gpt-oss-20bOpenAI410 t/s
- Gemini 3.6 FlashGoogle242 t/s
- Gemini 2.5 Flash LiteGoogle218 t/s
- Gemini 3.5 Flash LiteGoogle198 t/s
- Claude Haiku 4.5Anthropic195 t/s
- 190 t/s
- Claude Haiku 5.5Anthropic182 t/s
- Claude Opus 4.8Anthropic181 t/s
- Gemini 3.5 FlashGoogle176 t/s
View as table
| Model | Tokens/s |
|---|---|
| gpt-oss-120b (OpenAI) | 641 |
| gpt-oss-20b (OpenAI) | 410 |
| Gemini 3.6 Flash (Google) | 242 |
| Gemini 2.5 Flash Lite (Google) | 218 |
| Gemini 3.5 Flash Lite (Google) | 198 |
| Claude Haiku 4.5 (Anthropic) | 195 |
| Llama 3.3 70B Instruct (Meta) | 190 |
| Claude Haiku 5.5 (Anthropic) | 182 |
| Claude Opus 4.8 (Anthropic) | 181 |
| Gemini 3.5 Flash (Google) | 176 |
Full catalogue
All 47 models on Google
Filter by creator
47 of 47 models