Replicate: Models Intelligence, Performance & Price
Replicate Model Comparison Summary
DeepSeek V3 0324 and 
Llama 3.1 405B are the highest intelligence models offered by Replicate, followed by 
Granite 4.0 H Small & Granite 3.3 8B.Output Speed (tokens/s): Granite 3.3 8B (497 t/s) and Granite 4.0 H Small (429 t/s) are the fastest models offered by Replicate, followed by DeepSeek V3 0324 & Llama 3.1 405B.Latency (seconds): Llama 3.1 405B (3.53s) and DeepSeek V3 0324 (3.84s) are the lowest latency models offered by Replicate, followed by Granite 3.3 8B & Granite 4.0 H Small.Blended Price ($/M tokens): Granite 3.3 8B ($0.09) and Granite 4.0 H Small ($0.11) are the cheapest models offered by Replicate, followed by DeepSeek V3 0324 & Llama 3.1 405B.Context Window Size: DeepSeek V3 0324 (128k) and Llama 3.1 405B (128k) are the largest context window models offered by Replicate, followed by Granite 4.0 H Small & Granite 3.3 8B.Intelligence Evaluations
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Intelligence Evaluations
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Intelligence vs. Price
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Context Window
Context Window
Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
JSON Mode & Function Calling
Function (Tool) Calling & JSON Mode
| Models | Function calling | JSON Mode |
|---|---|---|
 DeepSeek V3 0324, Replicate | ||
| Llama 3.1 405B, Replicate | ||
| Granite 4.0 H Small, Replicate | ||
| Granite 3.3 8B, Replicate |
Indicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.
Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.
Pricing
Intelligence vs. Price
Artificial Analysis Intelligence Index v4.0 includes: GDPval-AA, 𝜏²-Bench Telecom, Terminal-Bench Hard, SciCode, AA-LCR, AA-Omniscience, IFBench, Humanity's Last Exam, GPQA Diamond, CritPt. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Performance Summary
Output Speed vs. Price
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Speed
Measured by Output Speed (tokens per second)
Output Speed
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Latency
Measured by Time (seconds) to First Token
Time to First Token
Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
End-to-End Response Time
Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Seconds to receive a 500 token response considering input processing time, 'thinking' time of reasoning models, and output speed.
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Figures represent performance of the model's first-party API (e.g. OpenAI for o1) or the median across providers where a first-party API is not available (e.g. Meta's Llama models).
Key definitions
Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Price per token generated by the model (received from the API), represented as USD per million Tokens.
Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.
Frequently Asked Questions
Common questions about Replicate
Replicate offers 4 models that we track: DeepSeek V3 0324, Llama 3.1 405B, Granite 4.0 H Small, and Granite 3.3 8B.
The most intelligent model available on Replicate is DeepSeek V3 0324 with an Intelligence Index score of 22.
The fastest model on Replicate by output speed is Granite 3.3 8B at 497.0 tokens per second.
The model with the lowest time to first token on Replicate is Llama 3.1 405B at 3.53s. Lower latency means faster initial response time.
The most affordable model on Replicate by blended price is Granite 3.3 8B at $0.09 per 1M tokens (3:1 input to output ratio).
Prices on Replicate vary up to 112x across models, from $0.09 per 1M tokens for Granite 3.3 8B to $9.50 per 1M tokens for Llama 3.1 405B.
Yes, Replicate offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 4 models on Replicate are open weight models.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Replicate, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.