Stay connected with us on X, Discord, and LinkedIn to stay up to date with future analysis
Loading...
logo

DeepInfra: Models Intelligence, 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.

DeepInfra

Most Intelligent

#1
GLM-5 FP8GLM-5 FP8
50
#2
Kimi K2.5 TurboKimi K2.5 Turbo
47
#3
Kimi K2.5Kimi K2.5
47
#4
GLM-4.7 (FP4)GLM-4.7 (FP4)
42
#5
MiniMax-M2.5 (FP8)MiniMax-M2.5 (FP8)
42

Intelligence index

Total 77 models

Fastest

#1
NVIDIA Nemotron 3 SuperNVIDIA Nemotron 3 Super
505 t/s
#2
Kimi K2.5 TurboKimi K2.5 Turbo
324 t/s
#3
gpt-oss-120B (high) (Turbo)gpt-oss-120B (high) (Turbo)
223 t/s
#4
Qwen3 Next 80B A3BQwen3 Next 80B A3B
192 t/s
#5
Devstral SmallDevstral Small
188 t/s

Output speed

Total 77 models

Lowest Price

#1
Llama 3.2 3BLlama 3.2 3B
$0.02
#2
Llama 3.1 8B (Turbo, FP8)Llama 3.1 8B (Turbo, FP8)
$0.02
#3
Llama 3.1 8BLlama 3.1 8B
$0.03
#4
Llama 3.2 11B (Vision)Llama 3.2 11B (Vision)
$0.05
#5
Gemma 3 4BGemma 3 4B
$0.05

Blended price (per 1M tokens)

Total 77 models

DeepInfra offers 77 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.

  • For intelligence, the top models on DeepInfra are GLM-5 FP8 (50), Kimi K2.5 Turbo (47), Kimi K2.5 (47).
  • For output speed, the fastest models are NVIDIA Nemotron 3 Super (505 t/s), Kimi K2.5 Turbo (324 t/s), gpt-oss-120B (high) (Turbo) (223 t/s). Speed varies significantly across models, with a 168% difference between the fastest and slowest.
  • For latency, gpt-oss-120B (high) (Turbo) (0.42s), NVIDIA Nemotron 3 Nano (0.45s), gpt-oss-120B (high) (0.46s) offer the lowest time to first token.
  • For pricing, Llama 3.2 3B ($0.02), Llama 3.1 8B (Turbo, FP8) ($0.02), Llama 3.1 8B ($0.03) offer the lowest blended prices per 1M tokens. Prices vary up to 2.5x across models.
  • For context window size, Llama 4 Maverick (FP8) (1m), Llama 4 Scout (328k), Kimi K2.5 Turbo (262k) support the largest context windows on DeepInfra.
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better

Navigation

Intelligence EvaluationsContext WindowJSON Mode & Function CallingPricingPerformance SummarySpeedLatencyEnd-to-End Response Time

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index; Higher is better

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

Intelligence evaluations measured independently by Artificial Analysis; Higher is better
Results claimed by AI Lab (not yet independently verified)
GDPval-AA (Agentic Real-World Work Tasks, (ELO-500)/2000)
Terminal-Bench Hard (Agentic Coding & Terminal Use)
𝜏²-Bench Telecom (Agentic Tool Use)
AA-LCR (Long Context Reasoning)
AA-Omniscience Accuracy (Knowledge)
AA-Omniscience Non-Hallucination Rate (1 - Hallucination Rate)
Humanity's Last Exam (Reasoning & Knowledge)
GPQA Diamond (Scientific Reasoning)
SciCode (Coding)
IFBench (Instruction Following)
CritPt (Physics Reasoning)
MMMU Pro (Visual Reasoning)

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; Price: USD per 1M Tokens
Most attractive quadrant
DeepInfra
DeepInfra (FP4)
DeepInfra (FP8)
DeepInfra (Turbo)
DeepInfra FP8
DeepInfra Turbo

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

Context Window: Tokens Limit; Higher is better

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

ModelsFunction callingJSON Mode
GLM-5 FP8, DeepInfra logoGLM-5 FP8, DeepInfra
Kimi K2.5 Turbo, DeepInfra logoKimi K2.5 Turbo, DeepInfra
Kimi K2.5, DeepInfra logoKimi K2.5, DeepInfra
GLM-4.7 (FP4), DeepInfra logoGLM-4.7 (FP4), DeepInfra
MiniMax-M2.5 (FP8), DeepInfra logoMiniMax-M2.5 (FP8), DeepInfra
Kimi K2 Thinking, DeepInfra logoKimi K2 Thinking, DeepInfra
GLM-5 (FP8), DeepInfra logoGLM-5 (FP8), DeepInfra
MiniMax-M2.1 (FP8), DeepInfra logoMiniMax-M2.1 (FP8), DeepInfra
NVIDIA Nemotron 3 Super, DeepInfra logoNVIDIA Nemotron 3 Super, DeepInfra
GLM-4.7 (FP4), DeepInfra logoGLM-4.7 (FP4), DeepInfra
gpt-oss-120B (high) (Turbo), DeepInfra logogpt-oss-120B (high) (Turbo), DeepInfra
gpt-oss-120B (high), DeepInfra logogpt-oss-120B (high), DeepInfra

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; Price: USD per 1M Tokens
Most attractive quadrant
DeepInfra
DeepInfra (FP4)
DeepInfra (FP8)
DeepInfra (Turbo)
DeepInfra FP8
DeepInfra Turbo

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

Output Speed: Output Tokens per Second; Price: USD per 1M Tokens; 10,000 Input Tokens
Most attractive quadrant
DeepInfra
DeepInfra (FP4)
DeepInfra (FP8)
DeepInfra (Turbo)
DeepInfra FP8
DeepInfra Turbo

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

Output Tokens per Second; Higher is better; 10,000 Input Tokens

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 Answer Token

Seconds to First Token Received; Lower is better
Input processing time
'Thinking' time (reasoning models, where applicable)

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

Seconds to receive a 500 token response. Key components:

  • Input time: Time to receive the first response token
  • Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
  • Answer time: Time to generate 500 output tokens, based on output speed

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

End-to-End Response Time: End-to-End Seconds to Output 500 Tokens; Price: USD per 1M Tokens
Most attractive quadrant
DeepInfra
DeepInfra (FP4)
DeepInfra (FP8)
DeepInfra (Turbo)
DeepInfra FP8
DeepInfra Turbo

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 DeepInfra

DeepInfra offers 77 models that we track: GLM-5, Kimi K2.5, Kimi K2.5, GLM-4.7, MiniMax-M2.5, Kimi K2 Thinking, GLM-5, MiniMax-M2.1, NVIDIA Nemotron 3 Super, GLM-4.7, gpt-oss-120B (high), gpt-oss-120B (high), GLM-4.6, DeepSeek V3.2, Kimi K2 0905, GLM-4.7-Flash, Qwen3 235B A22B 2507, DeepSeek V3.1 Terminus, DeepSeek V3.2 Exp, DeepSeek V3.1, DeepSeek R1 0528, GLM-4.5, Kimi K2, Qwen3 235B 2507, Qwen3 Coder 480B, Qwen3 Coder 480B, gpt-oss-20B (high), NVIDIA Nemotron 3 Nano, GLM-4.6V, GLM-4.5-Air, DeepSeek V3 0324, Qwen3 VL 235B A22B, Qwen3 Next 80B A3B, DeepSeek R1 (Jan), DeepSeek R1 (Jan), Llama Nemotron Super 49B v1.5, Llama 4 Maverick, Devstral Small (May), Qwen3 235B, Qwen3 32B, DeepSeek V3 (Dec), Qwen3 14B, Qwen3 VL 30B A3B, Qwen3 30B, Devstral Small, Mistral Small 3.2, NVIDIA Nemotron Nano 12B v2 VL, NVIDIA Nemotron Nano 9B V2, Llama Nemotron Super 49B v1.5, Llama 3.3 70B, Llama 4 Scout, Llama 3.1 Nemotron 70B, NVIDIA Nemotron 3 Nano, NVIDIA Nemotron Nano 9B V2, Qwen3 14B, Qwen3 30B, Llama 3.1 70B, Llama 3.1 70B, Olmo 3.1 32B Instruct, Llama 3.1 8B, Llama 3.1 8B, Phi-4, Gemma 3 27B, NVIDIA Nemotron Nano 12B v2 VL, Gemma 3 12B, Llama 3.2 11B (Vision), Gemma 3 4B, Llama 3.2 90B (Vision), DeepSeek R1 Distill Llama 70B, Llama 3.2 3B, Mistral Small 3, Mixtral 8x7B, DeepSeek R1 Distill Qwen 32B, Hermes 3 - Llama-3.1 70B, Qwen2.5 72B, Qwen3 32B, and QwQ 32B-Preview.

The most intelligent model available on DeepInfra is GLM-5 with an Intelligence Index score of 50.

The fastest model on DeepInfra by output speed is NVIDIA Nemotron 3 Super at 504.7 tokens per second.

The model with the lowest time to first token on DeepInfra is gpt-oss-120B (high) at 0.42s. Lower latency means faster initial response time.

The most affordable model on DeepInfra by blended price is Llama 3.2 3B at $0.02 per 1M tokens (3:1 input to output ratio).

Prices on DeepInfra vary up to 75x across models, from $0.02 per 1M tokens for Llama 3.2 3B to $1.50 per 1M tokens for DeepSeek R1 (Jan).

Yes, DeepInfra offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.

49 of 77 models on DeepInfra support JSON mode for structured output.

65 of 77 models on DeepInfra support function calling (tool use).

Yes, DeepInfra offers 30 reasoning models: GLM-5, Kimi K2.5, Kimi K2.5, GLM-4.7, MiniMax-M2.5, Kimi K2 Thinking, MiniMax-M2.1, NVIDIA Nemotron 3 Super, gpt-oss-120B (high), gpt-oss-120B (high), GLM-4.6, GLM-4.7-Flash, Qwen3 235B A22B 2507, DeepSeek R1 0528, GLM-4.5, gpt-oss-20B (high), NVIDIA Nemotron 3 Nano, GLM-4.6V, GLM-4.5-Air, DeepSeek R1 (Jan), DeepSeek R1 (Jan), Llama Nemotron Super 49B v1.5, Qwen3 32B, Qwen3 14B, Qwen3 30B, NVIDIA Nemotron Nano 12B v2 VL, NVIDIA Nemotron Nano 9B V2, DeepSeek R1 Distill Llama 70B, DeepSeek R1 Distill Qwen 32B, and QwQ 32B-Preview. Reasoning models use extended thinking to work through complex problems before providing an answer.

Yes, all 77 models on DeepInfra 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 DeepInfra, 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.