Perplexity
Inference hostPerplexity runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.
Models28
- Cheapest for
- 0 models
- Serves
- 1 model types
Monthly visits—
Models by type
Models on Perplexity
| Model | Input | Output | vs official | Context |
|---|---|---|---|---|
| $2/1M | $10/1M from $8 at APIMart | ±0% | — | |
| Kimi K3Moonshot AI | $3/1M | $15/1M from $8.28 at Kenari | +8% | — |
| GPT-6 AstraOpenAI | $10/1M | From$50/1M from $25 at CrazyRouter | ±0% | — |
| Claude Opus 5.5Anthropic | $4/1M | $20/1M from $16 at APIMart | ±0% | — |
| GPT-6.1 SolOpenAI | $2/1M | From$10/1M from $8 at APIMart | ±0% | — |
| $1.40/1M | $4.40/1M from $1.10 at NanoGPT | ±0% | — | |
| GPT-6 SolOpenAI | $2/1M | From$10/1M from $8 at APIMart | ±0% | — |
| Grok 4.7xAI | $2/1M | From$6/1M from $4.80 at APIMart | ±0% | — |
| $0.15/1M | $0.50/1M from $0.20 at APIMart | ±0% | — | |
| GPT-6 LunaOpenAI | $0.10/1M | From$0.50/1M from $0.40 at APIMart | ±0% | — |
| $0.25/1M | $2.50/1M from $1 at AI/ML API | Official | — | |
| Claude Sonnet 5.5Anthropic | $2/1M | $10/1M from $8 at APIMart | ±0% | — |
| $0.75/1M | $3.75/1M from $3 at APIMart | ±0% | — | |
| Claude Haiku 5.5Anthropic | $0.10/1M | From$0.50/1M from $0.30 at Kie.ai | ±0% | — |
| Claude Opus 5Anthropic | $5/1M | $25/1M from $20 at APIMart | ±0% | — |
| Claude Fable 5Anthropic | $10/1M | $50/1M from $40 at APIMart | ±0% | — |
| Claude Fable 5.1Anthropic | $10/1M | $50/1M from $40 at APIMart | ±0% | — |
| GPT-5.6 LunaOpenAI | $0.20/1M | From$1.20/1M from $0.96 at APIMart | ±0% | — |
| GPT-5.6OpenAI | $4/1M | From$20/1M from $10 at Boundless | ±0% | — |
| Claude Sonnet 5Anthropic | $2/1M | $10/1M from $6.90 at Kenari | ±0% | — |
| Grok 4.6xAI | $2/1M | From$6/1M from $4.80 at APIMart | ±0% | — |
| Grok 4.5xAI | $2/1M | From$6/1M from $3.20 at APIMart | ±0% | — |
| $0.20/1M | $0.50/1M | — | — | |
| $1.32/1M | $3.96/1M from $1.58 at CometAPI | +100% | — | |
| $1.50/1M | $7.50/1M from $3 at CometAPI | +100% | — | |
| $0.75/1M | $3.75/1M from $1.13 at Kie.ai | +233% | — | |
| GPT-5.6 TerraOpenAI | $2/1M | From$12/1M from $9.60 at APIMart | ±0% | — |
| OpenAI GPT-5.5OpenAI | $5/1M | From$30/1M from $24 at APIMart | ±0% | — |
Perplexity at a glance
28 models in total: 28 text. The cheapest is GLM-5.3-Flash at $0.50 /1M. GPT-6 Astra has the largest context window, 1.05M tokens. The most searched is Gemini 4 Argon, with about 2M Google searches a month. The newest is Gemini 4 Argon, released Oct 13, 2026.
Cheapest
GLM-5.3-Flash$0.50/1M
- GPT-6 Luna$0.50/1M
- Claude Haiku 5.5$0.50/1M
Nemotron 3.5 Super 120B A12B$0.50/1M
- GPT-5.6 Luna$1.20/1M
Largest context
- GPT-6 Astra1.05M
- GPT-6.1 Sol1.05M
- GPT-6 Sol1.05M
- GPT-6 Luna1.05M
- GPT-5.6 Luna1.05M
Most searched
Gemini 4 Argon2M
- Kimi K3658K
- GPT-6 Astra580K
- Claude Opus 5.5405K
- GPT-6.1 Sol384K
Newest
Gemini 4 ArgonOct 13, 2026
- Claude Haiku 5.5Oct 7, 2026
- GPT-6.1 SolSep 29, 2026
- Claude Sonnet 5.5Sep 28, 2026
- Claude Opus 5.5Sep 22, 2026