Google's flagship reasoning model.
Per 1M tokens
$0.25
Latency
0.6s
Context
1.05M
Compare capabilities and choose a model for your next request.
Lowest latency
0.5sQwen 3.6
Lowest rate
$0.01/MGemini 3.8 Flash
Catalog
28models · 9 providers
Showing 28 models
Google's flagship reasoning model.
Per 1M tokens
$0.25
Latency
0.6s
Context
1.05M
OpenAI's most capable model for the most demanding work.
Per 1M tokens
$0.15
Latency
3.3s
Context
1.05M
Near-Astra performance at a lower cost.
Per 1M tokens
$0.15
Latency
0.7s
Context
1.05M
Moonshot's 2.8T-parameter open-source flagship.
Per 1M tokens
$0.05
Latency
0.7s
Context
1M
Latest GLM release.
Per 1M tokens
$0.05
Latency
1.7s
Context
Unknown
DeepSeek's flagship reasoning model.
Per 1M tokens
$0.05
Latency
1.5s
Context
1M
Cheapest model in the catalog.
Per 1M tokens
$0.02
Latency
1.6s
Context
1M
Anthropic's flagship for agentic coding.
Per 1M tokens
$0.50
Latency
0.6s
Context
1M
GPT-6 reasoning tier below Astra.
Per 1M tokens
$0.15
Latency
0.7s
Context
1.05M
OpenAI's most efficient model for high-volume tasks.
Per 1M tokens
$0.05
Latency
0.8s
Context
1.05M
Previous-generation reasoning flagship.
Per 1M tokens
$0.15
Latency
1.1s
Context
Unknown
Updated K3 with a larger reasoning budget.
Per 1M tokens
$0.10
Latency
0.8s
Context
1M
Cheap, fast GLM for high volume.
Per 1M tokens
$0.05
Latency
2.1s
Context
Unknown
Previous GLM release, still supported.
Per 1M tokens
$0.05
Latency
2s
Context
Unknown
Anthropic's best balance of speed and intelligence.
Per 1M tokens
$0.05
Latency
0.5s
Context
1M
Anthropic's fastest and cheapest small model.
Per 1M tokens
$0.10
Latency
0.6s
Context
1M
Previous Opus generation, still available.
Per 1M tokens
$0.40
Latency
0.7s
Context
1M
Earlier Opus release from the 4.x line.
Per 1M tokens
$0.30
Latency
0.6s
Context
1M
The previous Sonnet flagship.
Per 1M tokens
$0.20
Latency
0.7s
Context
1M
Newest DeepSeek Flash release.
Per 1M tokens
$0.04
Latency
1.8s
Context
1M
Meta's first frontier model.
Per 1M tokens
$0.50
Latency
0.5s
Context
1M
xAI's frontier model for coding and knowledge work.
Per 1M tokens
$0.05
Latency
0.8s
Context
500K
Google's high-volume Flash tier.
Per 1M tokens
$0.01
Latency
0.7s
Context
1M
Anthropic's current flagship for coding and knowledge work.
Per 1M tokens
$0.40
Latency
0.6s
Context
1M
Mythos-class capability, released with safeguards.
Per 1M tokens
$0.40
Latency
1.3s
Context
1M
Mythos-class model, vetted-partner access only.
Per 1M tokens
$0.60
Latency
0.8s
Context
1M
Alibaba's frontier agentic model.
Per 1M tokens
$0.50
Latency
0.5s
Context
1M
Uncensored Qwen 3.8 model.
Per 1M tokens
$0.01
Latency
2.5s
Context
1M