Supported Models
Plug any model in to any agent.
Providers
28 models
Model | Context | Max Output | Latency | Throughput | Input | Output | Cache | |
|---|---|---|---|---|---|---|---|---|
Claude 3 Haiku | 200K | 4K | — | — | — | — | — | |
Claude 3.5 Haiku | 200K | 8K | — | — | — | — | — | |
Claude Haiku 4.5 | 200K | 64K | — | — | — | — | — | |
Claude Opus 4 | 200K | 32K | — | — | — | — | — | |
Claude Opus 4.1 | 200K | 32K | — | — | — | — | — | |
Claude Opus 4.5 | 200K | 64K | — | — | — | — | — | |
Claude Sonnet 3.7 | 200K | 64K | — | — | — | — | — | |
Claude Sonnet 4 | 200K | 64K | — | — | — | — | — | |
Claude Sonnet 4.5 | 200K | 64K | — | — | — | — | — | |
Command A | 256K | 8K | — | — | — | — | — | |
DeepSeek R1 | 128K | 66K | — | — | — | — | — | |
DeepSeek V3.2 | 128K | 8K | — | — | — | — | — | |
Gemini 2.0 Flash | 1.0M | 8K | — | — | — | — | — | |
Gemini 2.5 Flash | 1.0M | 8K | — | — | — | — | — | |
Gemini 2.5 Pro | 1.0M | 8K | — | — | — | — | — | |
GPT-4o | 128K | 16K | — | — | — | — | — | |
GPT-4o Mini | 128K | 16K | — | — | — | — | — | |
Grok 3 | 131K | 16K | — | — | — | — | — | |
Grok 3 Mini | 131K | 16K | — | — | — | — | — | |
Grok 4 | 256K | 16K | — | — | — | — | — | |
Llama 3.3 70B | 128K | 4K | — | — | — | — | — | |
Llama 4 Maverick | 1.0M | 16K | — | — | — | — | — | |
Llama 4 Scout | 1.0M | 16K | — | — | — | — | — | |
Mistral Large 3 | 131K | 8K | — | — | — | — | — | |
Mistral Medium | 131K | 8K | — | — | — | — | — | |
Mistral Small | 131K | 8K | — | — | — | — | — | |
Sonar | 128K | 8K | — | — | — | — | — | |
Sonar Pro | 200K | 8K | — | — | — | — | — |
Prices shown per 1M tokens.