Models
10 frontier models from OpenAI, Anthropic, and Google — all through one API.
Smart Routing
AI Gateway automatically routes your requests to the optimal model based on your query complexity, available capacity, and cost efficiency. When you use the auto model, our intelligent router selects the best model for each request.
How Smart Routing Works
- Analyzes request complexity and required capabilities
- Checks model availability and current load across providers
- Selects the most cost-effective model that meets your needs
- Automatically retries on failure with fallback to alternate models
Auto Model Selection
Use "model": "auto" in your API request to enable automatic model selection. The router will choose the best model based on your prompt content and your current plan tier.
{
"model": "auto",
"messages": [
{"role": "user", "content": "Your prompt here"}
]
}Available Models
OpenAI4 models
| Model | Context | Max Output | Input Price | Output Price | Capabilities |
|---|---|---|---|---|---|
GPT-5.5 gpt-5.5 | 128k | 16k | $2.5 | $10 | chatcodereasoningfunction-calling |
GPT-5.4 gpt-5.4 | 128k | 16k | $1.5 | $6 | chatcodereasoning |
GPT-5.4 Mini gpt-5.4-mini | 128k | 8k | $0.4 | $1.6 | chatcode |
GPT-5.3 Codex gpt-5.3-codex | 200k | 33k | $1.5 | $6 | codereasoningfunction-calling |
Anthropic3 models
| Model | Context | Max Output | Input Price | Output Price | Capabilities |
|---|---|---|---|---|---|
Claude Opus 4.8 claude-opus-4.8 | 200k | 32k | $15 | $75 | chatcodereasoninganalysis |
Claude Sonnet 4.5 claude-sonnet-4.5 | 200k | 16k | $3 | $15 | chatcodereasoning |
Claude Haiku 3.5 claude-haiku-3.5 | 200k | 8k | $0.8 | $4 | chatcode |
Google3 models
| Model | Context | Max Output | Input Price | Output Price | Capabilities |
|---|---|---|---|---|---|
Gemini 2.5 Pro gemini-2.5-pro | 1M | 66k | $1.25 | $10 | chatcodereasoninganalysismultimodal |
Gemini 2.5 Flash gemini-2.5-flash | 1M | 66k | $0.15 | $0.6 | chatcodereasoning |
Gemini 2.0 Flash gemini-2.0-flash | 1M | 8k | $0.1 | $0.4 | chatcode |
Model Availability by Tier
| Model | Free | Lite | Pro | Enterprise |
|---|---|---|---|---|
GPT-5.5 gpt-5.5 | — | — | ✓ | ✓ |
GPT-5.4 gpt-5.4 | — | ✓ | ✓ | ✓ |
GPT-5.4 Mini gpt-5.4-mini | ✓ | ✓ | ✓ | ✓ |
GPT-5.3 Codex gpt-5.3-codex | — | — | ✓ | ✓ |
Claude Opus 4.8 claude-opus-4.8 | — | — | ✓ | ✓ |
Claude Sonnet 4.5 claude-sonnet-4.5 | — | — | ✓ | ✓ |
Claude Haiku 3.5 claude-haiku-3.5 | ✓ | ✓ | ✓ | ✓ |
Gemini 2.5 Pro gemini-2.5-pro | — | — | ✓ | ✓ |
Gemini 2.5 Flash gemini-2.5-flash | — | ✓ | ✓ | ✓ |
Gemini 2.0 Flash gemini-2.0-flash | ✓ | ✓ | ✓ | ✓ |
Pricing note: Prices shown are per million tokens. Credits are consumed based on actual token usage. Use the auto model for the best cost efficiency — smart routing automatically selects the most affordable model for your use case.