Gateway
Perplexity Agent
Perplexity Agent is a Gateway provider with 17 models across 17 offerings.
Access
- API base URL
- https://api.perplexity.ai/v1
- SDK
- @ai-sdk/openai
- Environment variables
- PERPLEXITY_API_KEY
Models
17 of 17 model versions
| Model | Family | Provider model ID | Protocol | Streaming | Organization | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Price | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.5 openai/gpt-5.5 | OPOpenAI | GPT | openai/gpt-5.5 | Openai chat | Yes | 1.1M | 128K | Yes | Yes | Yes | -No | Closed | input $5/M · output $30/M cache read $0.5/M | 2026-04-23 | 2026-08-06 | |||
| Claude Opus 4.7 anthropic/claude-opus-4-7 | ANAnthropic | Claude | anthropic/claude-opus-4-7 | Openai chat | Yes | 1M | 128K | Yes | Yes | -No | -No | Closed | input $5/M · output $25/M cache read $0.5/M | 2026-04-16 | 2026-06-11 | |||
| Nemotron 3 Super 120B A12B nvidia/nemotron-3-super-120b-a12b | NVNVIDIA | Nemotron | nvidia/nemotron-3-super-120b-a12b | Openai chat | Yes | 262K | 262K | Yes | Yes | -No | Yes | Open | input $0.25/M · output $2.5/M | 2026-03-11 | 2026-03-12 | |||
| GPT-5.4 openai/gpt-5.4 | OPOpenAI | GPT | openai/gpt-5.4 | Openai chat | Yes | 1.1M | 128K | Yes | Yes | Yes | -No | Closed | input $2.5/M · output $15/M cache read $0.25/M | 2026-03-05 | 2026-08-06 | |||
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | GOGoogle | Gemini | google/gemini-3.1-pro-preview | Openai chat | Yes | 1M | 66K | Yes | Yes | Yes | Yes | Closed | input $2/M · output $12/M cache read $0.2/M | 2026-02-19 | 2026-06-11 | |||
| Claude Sonnet 4.6 anthropic/claude-sonnet-4-6 | ANAnthropic | Claude | anthropic/claude-sonnet-4-6 | Openai chat | Yes | 1M | 64K | Yes | Yes | -No | Yes | Closed | input $3/M · output $15/M cache read $0.3/M | 2026-02-17 | 2026-06-11 | |||
| Claude Opus 4.6 anthropic/claude-opus-4-6 | ANAnthropic | Claude | anthropic/claude-opus-4-6 | Openai chat | Yes | 1M | 128K | Yes | Yes | -No | Yes | Closed | input $5/M · output $25/M cache read $0.5/M | 2026-02-05 | 2026-07-17 | |||
| Gemini 3 Flash Preview google/gemini-3-flash-preview | GOGoogle | Gemini | google/gemini-3-flash-preview | Openai chat | Yes | 1M | 66K | Yes | Yes | Yes | Yes | Closed | input $0.5/M · output $3/M cache read $0.05/M | 2025-12-17 | 2026-06-11 | |||
| GPT-5.2 openai/gpt-5.2 | OPOpenAI | GPT | openai/gpt-5.2 | Openai chat | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.75/M · output $14/M cache read $0.175/M | 2025-12-11 | 2026-01-01 | |||
| GPT-5.1 openai/gpt-5.1 | OPOpenAI | GPT | openai/gpt-5.1 | Openai chat | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.25/M · output $10/M cache read $0.125/M | 2025-11-13 | 2026-02-01 | |||
| Claude Opus 4.5 anthropic/claude-opus-4-5-20251101 | ANAnthropic | Claude | anthropic/claude-opus-4-5 | Openai chat | Yes | 200K | 64K | Yes | Yes | -No | Yes | Closed | input $5/M · output $25/M cache read $0.5/M | 2025-11-01 | 2026-06-11 | |||
| Claude Haiku 4.5 anthropic/claude-haiku-4-5-20251001 | ANAnthropic | Claude | anthropic/claude-haiku-4-5 | Openai chat | Yes | 200K | 64K | Yes | Yes | -No | Yes | Closed | input $1/M · output $5/M cache read $0.1/M | 2025-10-15 | 2026-01-01 | |||
| Claude Sonnet 4.5 anthropic/claude-sonnet-4-5-20250929 | ANAnthropic | Claude | anthropic/claude-sonnet-4-5 | Openai chat | Yes | 200K | 64K | Yes | Yes | -No | Yes | Closed | input $3/M · output $15/M cache read $0.3/M | 2025-09-29 | 2026-06-11 | |||
| GPT-5 mini openai/gpt-5-mini | OPOpenAI | GPT | openai/gpt-5-mini | Openai chat | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $0.25/M · output $2/M cache read $0.025/M | 2025-08-07 | 2026-08-06 | |||
| Gemini 2.5 Flash google/gemini-2.5-flash | GOGoogle | Gemini | google/gemini-2.5-flash | Openai chat | Yes | 1M | 66K | Yes | Yes | Yes | Yes | Closed | input $0.3/M · output $2.5/M cache read $0.03/M | 2025-06-17 | 2026-01-01 | |||
| Gemini 2.5 Pro google/gemini-2.5-pro | GOGoogle | Gemini | google/gemini-2.5-pro | Openai chat | Yes | 1M | 66K | Yes | Yes | Yes | Yes | Closed | input $1.25/M · output $10/M cache read $0.125/M | 2025-06-17 | 2026-01-01 | |||
| Sonar perplexity/sonar | PEPerplexity | Sonar | perplexity/sonar | Openai chat | Yes | 128K | 4.1K | -No | -No | -No | Yes | Closed | input $0.25/M · output $2.5/M cache read $0.063/M | 2024-01-01 | 2025-09-01 |