LiteLLMModels

Perplexity model pricing

As of October 10, 2026, 83 Perplexity models are available through LiteLLM. The most recently added are GPT-6.1 Sol, Claude Sonnet 5.5, Claude Opus 5.5. Prices below are Perplexity's list prices.

How to call Perplexity with LiteLLM

Perplexity models

ModelLabPriceContextProvidersAdded
GPT-6.1 SolOpenAI$2 / $10 per 1M tokens922K8Sep 2026
Claude Sonnet 5.5Anthropic$2 / $10 per 1M tokens1M7Sep 2026
Claude Opus 5.5Anthropic$4 / $20 per 1M tokens1M8Sep 2026
GPT-6 LunaOpenAI$0.10 / $0.50 per 1M tokens922K8Sep 2026
GPT-6 SolOpenAI$2 / $10 per 1M tokens922K8Sep 2026
Grok 4.7xAI$2 / $6 per 1M tokens500K5Sep 2026
GPT-6 AstraOpenAI$10 / $50 per 1M tokens922K8Sep 2026
Nemotron 3.5 Lightning 30B A3BNVIDIA$0.0115 / $0.17 per 1M tokens–1Sep 2026
Gemini 3.8 FlashGoogle$0.75 / $3.75 per 1M tokens1M5Sep 2026
Claude Fable 5.1Anthropic$10 / $50 per 1M tokens1M7Sep 2026
GLM 5.3Z.ai$1.40 / $4.40 per 1M tokens1M12Aug 2026
GLM 5.3 FlashZ.ai$0.15 / $0.50 per 1M tokens1M11Aug 2026
Nemotron 3 Ultra 550B A55BNVIDIA$0.25 / $2.50 per 1M tokens1M3Aug 2026
PPLX Embed Context V1 0.6B–$0.008 per 1M tokens32K1Aug 2026
PPLX Embed Context V1 4B–$0.05 per 1M tokens32K1Aug 2026
Kimi K3Moonshot AI$3 / $15 per 1M tokens1M13Aug 2026
Gemini 3.7 FlashGoogle$0.75 / $3.75 per 1M tokens1M7Aug 2026
Grok 4.6xAI$2 / $6 per 1M tokens500K7Aug 2026
Claude Opus 5Anthropic$5 / $25 per 1M tokens1M9Jul 2026
Gemini 3.5 Flash LiteGoogle$0.30 / $2.50 per 1M tokens1M5Jul 2026
Gemini 3.6 FlashGoogle$1.50 / $7.50 per 1M tokens1M4Jul 2026
GPT-5.6 LunaOpenAI$0.20 / $1.20 per 1M tokens922K9Jul 2026
GPT-5.6 SolOpenAI$4 / $20 per 1M tokens922K8Jul 2026
GPT-5.6 TerraOpenAI$2 / $12 per 1M tokens922K9Jul 2026
Grok 4.5xAI$2 / $6 per 1M tokens500K2Jul 2026
Claude Sonnet 5Anthropic$2 / $10 per 1M tokens1M9Jun 2026
Claude Fable 5Anthropic$10 / $50 per 1M tokens1M9Jun 2026
Claude Opus 4.8Anthropic$5 / $25 per 1M tokens1M8Jun 2026
DeepSeek V4 FlashDeepSeek$0.13 / $0.26 per 1M tokens1M22Jun 2026
DeepSeek V4 ProDeepSeek$1.32 / $3.96 per 1M tokens1M17Jun 2026
GLM 5.2Z.ai$1.40 / $4.40 per 1M tokens1M19Jun 2026
Kimi K2.7 CodeMoonshot AI$0.95 / $4 per 1M tokens256K14Jun 2026
Gemini 3.1 Flash LiteGoogle$0.25 / $1.50 per 1M tokens1M5May 2026
Gemini 3.5 FlashGoogle$1.50 / $9 per 1M tokens1M5May 2026
Grok 4.20 Non ReasoningxAI$1.25 / $2.50 per 1M tokens1M5May 2026
Grok 4.20 ReasoningxAI$1.25 / $2.50 per 1M tokens1M5May 2026
Grok 4.3xAI$1.25 / $2.50 per 1M tokens1M5May 2026
Claude Opus 4.7Anthropic$5 / $25 per 1M tokens1M7Apr 2026
GPT-5.5OpenAI$5 / $30 per 1M tokens1M10Apr 2026
Grok 4.20 Multi AgentxAI$1.25 / $2.50 per 1M tokens1M3Apr 2026
GPT-5.4OpenAI$2.50 / $15 per 1M tokens1M9Mar 2026
GPT-5.4 MiniOpenAI$0.75 / $4.50 per 1M tokens272K7Mar 2026
GPT-5.4 NanoOpenAI$0.20 / $1.25 per 1M tokens272K6Mar 2026
PPLX Embed V1 0.6B–$0.004 per 1M tokens32K1Mar 2026
PPLX Embed V1 4B–$0.03 per 1M tokens32K1Mar 2026
Claude Opus 4.6Anthropic$5 / $25 per 1M tokens1M7Feb 2026
Claude Sonnet 4.6Anthropic$3 / $15 per 1M tokens1M8Feb 2026
Gemini 3.1 Pro PreviewGoogle$2 / $12 per 1M tokens1M4Feb 2026
GPT-5.3 CodexOpenAI$3.50 / $28 per 1M tokens272K7Feb 2026
Gemini 3 Flash PreviewGoogle$0.50 / $3 per 1M tokens1M5Dec 2025
GPT-5.2OpenAI$1.75 / $14 per 1M tokens272K6Dec 2025
Claude Opus 4.5Anthropic$5 / $25 per 1M tokens200K8Nov 2025
Gemini 3 Pro PreviewGoogle–1M2Nov 2025
GPT-5.1OpenAI$1.25 / $10 per 1M tokens272K5Nov 2025
Grok 4.1 Fast Non ReasoningxAI–128K3Nov 2025
Claude Haiku 4.5Anthropic$1 / $5 per 1M tokens200K12Oct 2025
Claude Sonnet 4.5Anthropic$3 / $15 per 1M tokens200K9Oct 2025
GPT-5OpenAI$1.25 / $10 per 1M tokens272K8Aug 2025
GPT-5 MiniOpenAI$0.25 / $2 per 1M tokens272K8Aug 2025
GPT-5 NanoOpenAI$0.05 / $0.40 per 1M tokens272K7Aug 2025
Gemini 2.5 FlashGoogle–1M8Jun 2025
Gemini 2.5 ProGoogle–1M7Jun 2025
Sonar Deep ResearchPerplexity$2 / $8 per 1M tokens128K1May 2025
Sonar ReasoningPerplexity$1 / $5 per 1M tokens128K2May 2025
Sonar Reasoning ProPerplexity$2 / $8 per 1M tokens128K2May 2025
SonarPerplexity$0.25 / $2.50 per 1M tokens128K2Feb 2025
Sonar ProPerplexity$3 / $15 per 1M tokens200K2Feb 2025
Llama 3.1 70B InstructMeta$1 / $1 per 1M tokens128K11Jul 2024
Llama 3.1 8B InstructMeta$0.20 / $0.20 per 1M tokens128K13Jul 2024
Sonar Medium ChatPerplexity$0.60 / $1.80 per 1M tokens16K1Mar 2024
Sonar Medium OnlinePerplexity$0 / $1.80 per 1M tokens12K1Mar 2024
Sonar Small ChatPerplexity$0.07 / $0.28 per 1M tokens16K1Mar 2024
Sonar Small OnlinePerplexity$0 / $0.28 per 1M tokens12K1Mar 2024
CodeLlama 70B Instruct–$0.70 / $2.80 per 1M tokens16K1Feb 2024
Mixtral 8x7B InstructMistral AI$0.07 / $0.28 per 1M tokens4K2Feb 2024
PPLX 70B Chat–$0.70 / $2.80 per 1M tokens4K1Dec 2023
PPLX 70B Online–$0 / $2.80 per 1M tokens4K1Dec 2023
PPLX 7B Chat–$0.07 / $0.28 per 1M tokens8K1Dec 2023
PPLX 7B Online–$0 / $0.28 per 1M tokens4K1Dec 2023
Mistral 7B InstructMistral AI$0.07 / $0.28 per 1M tokens4K1Oct 2023
Claude Haiku 5.5Anthropic$0.10 / $0.50 per 1M tokens1M7–
CodeLlama 34B Instruct–$0.35 / $1.40 per 1M tokens16K2–
Llama 2 70B ChatMeta$0.70 / $2.80 per 1M tokens4K4–