Perplexity: Sonar Reasoning Pro
perplexity/sonar-reasoning-pro
- Context
- 128000 tokens
- Input → Output
- Text · Image → Text
- Input / 1M
- $2
- Output / 1M
- $8
Reasoning
Details & providers ↗Listed 2025-03-073qk7 / MODELS
Updated 2026-10-19 23:48 UTCModels
Find an API model by context, inputs and price. Start with your constraints, then test on your own tasks.
392 results / 392 modelsSource: OpenRouter ↗
Perplexity: Sonar Pro
perplexity/sonar-pro
- Context
- 200000 tokens
- Input → Output
- Text · Image → Text
- Input / 1M
- $3
- Output / 1M
- $15
Perplexity: Sonar Deep Research
perplexity/sonar-deep-research
- Context
- 128000 tokens
- Input → Output
- Text → Text
- Input / 1M
- $2
- Output / 1M
- $8
Reasoning
Details & providers ↗Listed 2025-03-07Mistral: Saba
mistralai/mistral-saba
- Context
- 32768 tokens
- Input → Output
- Text · File → Text
- Input / 1M
- $0.19999999999999998
- Output / 1M
- $0.6
Tool callingStructured output
Details & providers ↗Listed 2025-02-17OpenAI: o3 Mini High
openai/o3-mini-high
- Context
- 200000 tokens
- Input → Output
- Text · File → Text
- Input / 1M
- $1.1
- Output / 1M
- $4.4
ReasoningTool callingStructured output
Details & providers ↗Listed 2025-02-12AionLabs: Aion-RP 1.0 (8B)
aion-labs/aion-rp-llama-3.1-8b
- Context
- 32768 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.7999999999999999
- Output / 1M
- $1.5999999999999999
Qwen: Qwen2.5 VL 72B Instruct
qwen/qwen2.5-vl-72b-instruct
- Context
- 128000 tokens
- Input → Output
- Text · Image → Text
- Input / 1M
- $0.7999999999999999
- Output / 1M
- $1
Structured output
Details & providers ↗Listed 2025-02-01Qwen: Qwen-Plus
qwen/qwen-plus
- Context
- 1000000 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.26
- Output / 1M
- $0.78
Tool callingStructured output
Details & providers ↗Listed 2025-02-01OpenAI: o3 Mini
openai/o3-mini
- Context
- 200000 tokens
- Input → Output
- Text · File → Text
- Input / 1M
- $1.1
- Output / 1M
- $4.4
ReasoningTool callingStructured output
Details & providers ↗Listed 2025-01-31Mistral: Mistral Small 3
mistralai/mistral-small-24b-instruct-2501
- Context
- 32768 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.049999999999999996
- Output / 1M
- $0.08
Structured output
Details & providers ↗Listed 2025-01-30Perplexity: Sonar
perplexity/sonar
- Context
- 127072 tokens
- Input → Output
- Text · Image → Text
- Input / 1M
- $1
- Output / 1M
- $1
MiniMax: MiniMax-01
minimax/minimax-01
- Context
- 1000192 tokens
- Input → Output
- Text · Image → Text
- Input / 1M
- $0.19999999999999998
- Output / 1M
- $1.1
Microsoft: Phi 4
microsoft/phi-4
- Context
- 16384 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.07
- Output / 1M
- $0.14
Structured output
Details & providers ↗Listed 2025-01-10DeepSeek: DeepSeek V3
deepseek/deepseek-chat
- Context
- 163840 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.32
- Output / 1M
- $0.8899999999999999
Tool callingStructured output
Details & providers ↗Listed 2024-12-26OpenAI: o1
openai/o1
- Context
- 200000 tokens
- Input → Output
- Text · Image · File → Text
- Input / 1M
- $15
- Output / 1M
- $60
ReasoningTool callingStructured output
Details & providers ↗Listed 2024-12-17Cohere: Command R7B (12-2024)
cohere/command-r7b-12-2024
- Context
- 128000 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.0375
- Output / 1M
- $0.15
Structured output
Details & providers ↗Listed 2024-12-14Meta: Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instruct
- Context
- 131072 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.09999999999999999
- Output / 1M
- $0.32
Tool callingStructured output
Details & providers ↗Listed 2024-12-06Amazon: Nova Lite 1.0
amazon/nova-lite-v1
- Context
- 300000 tokens
- Input → Output
- Text · Image → Text
- Input / 1M
- $0.06
- Output / 1M
- $0.24
Tool calling
Details & providers ↗Listed 2024-12-05Amazon: Nova Micro 1.0
amazon/nova-micro-v1
- Context
- 128000 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.035
- Output / 1M
- $0.14
Tool calling
Details & providers ↗Listed 2024-12-05Amazon: Nova Pro 1.0
amazon/nova-pro-v1
- Context
- 300000 tokens
- Input → Output
- Text · Image → Text
- Input / 1M
- $0.7999999999999999
- Output / 1M
- $3.1999999999999997
Tool calling
Details & providers ↗Listed 2024-12-05OpenAI: GPT-4o (2024-11-20)
openai/gpt-4o-2024-11-20
- Context
- 128000 tokens
- Input → Output
- Text · Image · File → Text
- Input / 1M
- $2.5
- Output / 1M
- $10
Tool callingStructured output
Details & providers ↗Listed 2024-11-20Mistral Large 2407
mistralai/mistral-large-2407
- Context
- 131072 tokens
- Input → Output
- Text · File → Text
- Input / 1M
- $2
- Output / 1M
- $6
Tool callingStructured output
Details & providers ↗Listed 2024-11-19Qwen2.5 Coder 32B Instruct
qwen/qwen-2.5-coder-32b-instruct
- Context
- 32768 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.66
- Output / 1M
- $1
TheDrummer: UnslopNemo 12B
thedrummer/unslopnemo-12b
- Context
- 1024000 tokens
- Input → Output
- Text → Text
- Input / 1M
- $0.39999999999999997
- Output / 1M
- $0.39999999999999997
Structured output
Details & providers ↗Listed 2024-11-08Prices are OpenRouter catalog rates in USD per 1M tokens. Provider, cache, image, audio, tools and time-based rates can differ; check the linked model page before use. Listed dates are catalog dates, not necessarily launch dates.
This is an API catalog, not a benchmark leaderboard. Parameter support does not establish quality. A missing rate is unknown, not free. Batch transport variants are omitted.