logo

Deepinfra: Models Quality, Performance & Price

Analysis of Deepinfra's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Deepinfra for your use-case. For more details including relating to our methodology, see our FAQs. Models analyzed: Llama 3.1 405B, Llama 3.2 90B (Vision), Llama 3.1 70B (Turbo, FP8), Llama 3.1 70B, Llama 3.2 11B (Vision), Llama 3.1 8B, Llama 3.2 3B, Llama 3.2 1B, Gemma 2 9B, Mistral NeMo, Mixtral 8x7B, Llama 3.1 Nemotron 70B, Qwen2.5 72B, Qwen2 72B, Llama 3 70B, Llama 3 8B, Mistral 7B, and OpenChat 3.5.
Link:

Deepinfra Model Comparison Summary

Quality:Qwen2.5 72B logo Qwen2.5 72B and Llama 3.1 405B logo Llama 3.1 405B are the highest quality models offered by Deepinfra, followed by Llama 3.1 Nemotron 70B logo Llama 3.1 Nemotron 70B, Qwen2 72B logo Qwen2 72B & Llama 3 70B logo Llama 3 70B.Output Speed (tokens/s):Llama 3.2 1B logo Llama 3.2 1B (157 t/s) and Llama 3 8B logo Llama 3 8B (121 t/s) are the fastest models offered by Deepinfra, followed by Mistral 7B logo Mistral 7B, Llama 3.2 3B logo Llama 3.2 3B & Llama 3.1 8B logo Llama 3.1 8B.Latency (seconds):Llama 3 8B logo Llama 3 8B (0.20s) and  Mistral 7B logo Mistral 7B (0.21s) are the lowest latency models offered by Deepinfra, followed by Llama 3.1 8B logo Llama 3.1 8B, Llama 3.2 11B (Vision) logo Llama 3.2 11B (Vision) & Mistral NeMo logo Mistral NeMo.Blended Price ($/M tokens):Llama 3.2 1B logo Llama 3.2 1B ($0.01) and Llama 3.2 3B logo Llama 3.2 3B ($0.04) are the cheapest models offered by Deepinfra, followed by Llama 3.2 11B (Vision) logo Llama 3.2 11B (Vision), Llama 3.1 8B logo Llama 3.1 8B & Llama 3 8B logo Llama 3 8B.Context Window Size:Qwen2.5 72B logo Qwen2.5 72B (131k) and Llama 3.1 Nemotron 70B logo Llama 3.1 Nemotron 70B (128k) are the largest context window models offered by Deepinfra, followed by Llama 3.1 70B (Turbo, FP8) logo Llama 3.1 70B (Turbo, FP8), Llama 3.1 70B logo Llama 3.1 70B & Llama 3.2 11B (Vision) logo Llama 3.2 11B (Vision).

Highlights

Quality
Artificial Analysis Quality Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:

Quality vs. Output Speed, Price

Artificial Analysis Quality Index; Output Speed: Output Tokens per Second; Price: Price: USD per 1M Tokens
Most attractive quadrant
Size represents Price (USD per M Tokens)
Artificial Analysis Quality Index: Average result across our evaluations covering different dimensions of model intelligence. Currently includes MMLU, GPQA, Math & HumanEval. OpenAI o1 model figures are preliminary and are based on figures stated by OpenAI. See methodology for more details.
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).
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Function Calling Support

ModelsFunction callingJSON Mode
Qwen2.5 72B, Deepinfra logoQwen2.5 72B, Deepinfra
Llama 3.1 405B, Deepinfra logoLlama 3.1 405B, Deepinfra
Llama 3.1 Nemotron 70B, Deepinfra logoLlama 3.1 Nemotron 70B, Deepinfra
Qwen2 72B, Deepinfra logoQwen2 72B, Deepinfra
Llama 3.2 90B (Vision), Deepinfra logoLlama 3.2 90B (Vision), Deepinfra
Llama 3.1 70B (Turbo, FP8), Deepinfra logoLlama 3.1 70B (Turbo, FP8), Deepinfra
Llama 3.1 70B, Deepinfra logoLlama 3.1 70B, Deepinfra
Llama 3.2 11B (Vision), Deepinfra logoLlama 3.2 11B (Vision), Deepinfra
Llama 3.1 8B, Deepinfra logoLlama 3.1 8B, Deepinfra
Mistral NeMo, Deepinfra logoMistral NeMo, Deepinfra
Llama 3.2 3B, Deepinfra logoLlama 3.2 3B, Deepinfra
Gemma 2 9B, Deepinfra logoGemma 2 9B, Deepinfra
Function (Tool) Calling: Indicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.
JSON Mode: Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.

Quality & Context Window

Quality Evaluations

Evaluation results measured independently by Artificial Analysis; Higher is better
Artificial Analysis Quality Index
Reasoning & Knowledge (MMLU)
Scientific Reasoning & Knowledge (GPQA)
Quantitative Reasoning (MATH)
Coding (HumanEval)
Communication (LMSys Chatbot Arena ELO Score)
Artificial Analysis Quality Index: Average result across our evaluations covering different dimensions of model intelligence. Currently includes MMLU, GPQA, Math & HumanEval. OpenAI o1 model figures are preliminary and are based on figures stated by OpenAI. See methodology for more details.

Quality vs. Context Window, Input Token Price

Artificial Analysis Quality Index; Context Window: Tokens Limit; Input Price: USD per 1M Input Tokens
Most attractive quadrant
Size represents Input Price (USD per M Input Tokens)
Artificial Analysis Quality Index: Average result across our evaluations covering different dimensions of model intelligence. Currently includes MMLU, GPQA, Math & HumanEval. OpenAI o1 model figures are preliminary and are based on figures stated by OpenAI. See methodology for more details.
Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Input price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Context Window

Context Window: Tokens Limit; Higher is better
Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Quality vs. Price

Artificial Analysis Quality Index: Average result across our evaluations covering different dimensions of model intelligence. Currently includes MMLU, GPQA, Math & HumanEval. OpenAI o1 model figures are preliminary and are based on figures stated by OpenAI. See methodology for more details.
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Median across providers: Figures represent median (P50) across all providers which support the model.

Pricing: Input and Output Prices

Price: USD per 1M Tokens
Input price
Output price
Input price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Output price: Price per token generated by the model (received from the API), represented as USD per million Tokens.
Median across providers: Figures represent median (P50) across all providers which support the model.

Performance Summary

Output Speed vs. Price

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).
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Latency vs. Output Speed

Latency: Seconds to First Tokens Chunk Received; Output Speed: Output Tokens per Second
Most attractive quadrant
Size represents Price (USD per M Tokens)
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).
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Median across providers: Figures represent median (P50) across all providers which support the model.

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output Tokens per Second; Higher is better
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).
Median across providers: Figures represent median (P50) across all providers which support the model.

Output Speed by Input Token Count (Context Length)

Output Tokens per Second; Higher is better
100 input tokens
1k input tokens
10k input tokens
100k input tokens
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).
Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.
Median across providers: Figures represent median (P50) across all providers which support the model.

Output Speed Variance

Output Tokens per Second; Results by percentile; Higher is better
Median, Other points represent 5th, 25th, 75th, 95th Percentiles respectively
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).
Boxplot: Shows variance of measurements
Picture of the author

Output Speed, Over Time

Output Tokens per Second; Higher is better
Smaller, emerging providers offer high output speed, though precise speeds delivered vary day-to-day.
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).
Over time measurement: Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Qwen2 72B, Deepinfra: 33k context, Llama 3.2 90B (Vision), Deepinfra: 8k context

Latency

Measured by Time (seconds) to First Token

Latency

Seconds to First Tokens Chunk Received; Lower is better
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Median across providers: Figures represent median (P50) across all providers which support the model.

Latency by Input Token Count (Context Length)

Seconds to First Tokens Chunk Received; Lower is better
100 input tokens
1k input tokens
10k input tokens
100k input tokens
Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Median across providers: Figures represent median (P50) across all providers which support the model.

Latency Variance

Seconds to First Tokens Chunk Received; Results by percentile; Lower is better
Median, Other points represent 5th, 25th, 75th, 95th Percentiles respectively
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Boxplot: Shows variance of measurements
Picture of the author

Latency, Over Time

Seconds to First Tokens Chunk Received; Lower is better
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Over time measurement: Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.

Total Response Time

Time to receive 100 tokens output, calculated from latency and output speed metrics

Total Response Time

Seconds to Output 100 Tokens; Lower is better
Total Response Time: Time to receive a 100 token response. Calculated based on Latency (time to receive first token) and Output Speed (output tokens per second).
Median across providers: Figures represent median (P50) across all providers which support the model.

Total Response Time by Input Token Count (Context Length)

Seconds to Output 100 Tokens; Lower is better
100 input tokens
1k input tokens
10k input tokens
100k input tokens
Input Tokens Length: Length of tokens provided in the request. See Prompt Options above to see benchmarks of different input prompt lengths across other charts.
Total Response Time: Time to receive a 100 token response. Calculated based on Latency (time to receive first token) and Output Speed (output tokens per second).
Median across providers: Figures represent median (P50) across all providers which support the model.

Total Response Time Variance

Total: Response Time: Seconds to Output 100 Tokens; Results by percentile; Lower is better
Median, Other points represent 5th, 25th, 75th, 95th Percentiles respectively
Total Response Time: Time to receive a 100 token response. Calculated based on Latency (time to receive first token) and Output Speed (output tokens per second).
Boxplot: Shows variance of measurements
Picture of the author

Total Response Time, Over Time

Seconds to Output 100 Tokens; Lower is better
Total Response Time: Time to receive a 100 token response. Calculated based on Latency (time to receive first token) and Output Speed (output tokens per second).
Over time measurement: Median measurement per day, based on 8 measurements each day at different times. Labels represent start of week's measurements.
Notes: Llama 3.1 405B, Deepinfra: 33k context, Qwen2 72B, Deepinfra: 33k context, Llama 3.2 90B (Vision), Deepinfra: 8k context
Features
Price
Output tokens/s
Latency
Further
Analysis
Deepinfra logo
Meta logo
Llama 3.1 405B
33k
72
$1.79
20.1
0.45
Deepinfra logo
Meta logo
Llama 3.2 90B (Vision)
8k
66
$0.36
29.9
0.32
Deepinfra (Turbo, FP8) logo
Meta logo
Llama 3.1 70B (Turbo, FP8)
128k
65
$0.32
52.1
0.27
Deepinfra logo
Meta logo
Llama 3.1 70B
128k
65
$0.36
30.3
0.31
Deepinfra logo
Meta logo
Llama 3.2 11B (Vision)
128k
54
$0.06
76.8
0.22
Deepinfra logo
Meta logo
Llama 3.1 8B
128k
53
$0.06
77.2
0.21
Deepinfra logo
Meta logo
Llama 3.2 3B
128k
47
$0.04
93.5
0.26
Deepinfra logo
Meta logo
Llama 3.2 1B
128k
27
$0.01
156.8
0.25
Deepinfra logo
Google logo
Gemma 2 9B
8k
48
$0.06
49.5
0.34
Deepinfra logo
Mistral logo
Mistral NeMo
128k
52
$0.13
53.5
0.24
Deepinfra logo
Mistral logo
Mixtral 8x7B
33k
43
$0.24
42.3
0.30
Deepinfra logo
NVIDIA logo
Llama 3.1 Nemotron 70B
128k
70
$0.36
26.3
0.32
Deepinfra logo
Alibaba logo
Qwen2.5 72B
131k
75
$0.36
23.3
0.32
Deepinfra logo
Alibaba logo
Qwen2 72B
33k
69
$0.36
23.0
0.32
Deepinfra logo
Meta logo
Llama 3 70B
8k
62
$0.36
22.0
0.36
Deepinfra logo
Meta logo
Llama 3 8B
8k
46
$0.06
120.8
0.20
Deepinfra logo
Mistral logo
Mistral 7B
33k
24
$0.06
94.5
0.21
Deepinfra logo
OpenChat logo
OpenChat 3.5
8k
43
$0.06
74.9
0.31

Key definitions

Artificial Analysis Quality Index: Average result across our evaluations covering different dimensions of model intelligence. Currently includes MMLU, GPQA, Math & HumanEval. OpenAI o1 model figures are preliminary and are based on figures stated by OpenAI. See methodology for more details.
Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
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).
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Output price: Price per token generated by the model (received from the API), represented as USD per million Tokens.
Input price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Time period: Metrics are 'live' and are based on the past 14 days of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.