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.
Most Intelligent
Intelligence index
Total 80 models
Fastest
Output speed
Total 80 models
Lowest Price
Blended price (per 1M tokens, 3:1 input-output ratio)
Total 80 models
DeepInfra offers 80 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 Kimi K2.6 (FP4) (54), MiMo-V2.5-Pro (54), DeepSeek V4 Pro (Max) (FP4) (52).
- For output speed, the fastest models are Qwen3.5 2B FP8 (337 t/s), NVIDIA Nemotron Nano 12B v2 VL (FP8) (287 t/s), Llama 3.1 Nemotron 70B (286 t/s). Speed varies significantly across models, with a 66% difference between the fastest and slowest.
- For latency, Qwen3.5 2B FP8 (0.34s), gpt-oss-20B (high) (0.41s), Qwen3.5 0.8B FP8 (0.43s) offer the lowest time to first token.
- For pricing, Qwen3.5 0.8B FP8 ($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, DeepSeek V4 Flash (Max) FP4 (1m), DeepSeek V4 Flash (High) (FP4) (1m), Llama 4 Maverick (FP8) (1m) support the largest context windows on DeepInfra.
Highlights
Intelligence
Speed
Price
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic real-world work tasks, (ELO-500)/2000
Agentic coding & terminal use
Agentic tool use
Long context reasoning
Knowledge
1 - hallucination rate
Reasoning & knowledge
Scientific reasoning
Coding
Instruction following
Physics reasoning
Long-horizon agentic tasks
Visual reasoning
Intelligence vs. Price
Context Window
Context Window
JSON Mode & Function Calling
Function (Tool) Calling & JSON Mode
| Models | Function calling | JSON Mode |
|---|---|---|
 Kimi K2.6 (FP4), DeepInfra | ||
| MiMo-V2.5-Pro, DeepInfra | ||
| DeepSeek V4 Pro (Max) (FP4), DeepInfra | ||
| GLM-5.1 (FP8), DeepInfra | ||
| DeepSeek V4 Pro (High) (FP4), DeepInfra | ||
| GLM-5 FP8, DeepInfra | ||
| Kimi K2.5, DeepInfra | ||
| DeepSeek V4 Flash (Max) FP4, DeepInfra | ||
| DeepSeek V4 Flash (High) (FP4), DeepInfra | ||
| Qwen3.6 27B FP8, DeepInfra | ||
| Qwen3.5 397B A17B (FP8), DeepInfra | ||
| GLM-5.1 (FP8), DeepInfra |
Pricing
Intelligence vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
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
Key definitions
Frequently Asked Questions
Common questions about DeepInfra
DeepInfra offers 80 models that we track: Kimi K2.6, MiMo-V2.5-Pro, DeepSeek V4 Pro (Max), GLM-5.1, DeepSeek V4 Pro (High), GLM-5, Kimi K2.5, DeepSeek V4 Flash (Max), DeepSeek V4 Flash (High), Qwen3.6 27B, Qwen3.5 397B A17B, GLM-5.1, Qwen3.6 35B A3B, GLM-4.7, Qwen3.5 27B, MiniMax-M2.5, Qwen3.5 122B A10B, GLM-5, Qwen3.5 397B A17B, Gemma 4 31B, Qwen3.5 27B, Qwen3.6 27B, Qwen3.5 35B A3B, Qwen3.5 122B A10B, MiMo-V2.5-Pro, GLM-4.7, gpt-oss-120B (high), gpt-oss-120B (high), GLM-4.6, DeepSeek V3.2, Qwen3.6 35B A3B, Gemma 4 26B A4B, Qwen3.5 35B A3B, GLM-4.7-Flash, Qwen3 235B A22B 2507, DeepSeek V3.1 Terminus, DeepSeek V3.1, Qwen3.5 4B, DeepSeek R1 0528, Qwen3 235B 2507, Qwen3 Coder 480B, gpt-oss-20B (high), NVIDIA Nemotron 3 Nano, Qwen3.5 4B, DeepSeek V3 0324, Qwen3 Next 80B A3B, Llama Nemotron Super 49B v1.5, Llama 4 Maverick, Qwen3 32B, DeepSeek V3 (Dec), Qwen3 14B, Qwen3 30B, Mistral Small 3.2, NVIDIA Nemotron Nano 9B V2, Qwen3.5 2B, Llama Nemotron Super 49B v1.5, Llama 3.3 70B, Mistral Small 3.1, 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, Llama 3.1 8B, Llama 3.1 8B, Phi-4, Gemma 3 27B, NVIDIA Nemotron Nano 12B v2 VL, Qwen3.5 0.8B, Gemma 3 12B, Llama 3.2 11B (Vision), Gemma 3 4B, DeepSeek R1 Distill Llama 70B, Mistral Small 3, Hermes 3 - Llama-3.1 70B, Qwen2.5 72B, and Qwen3 32B.
The most intelligent model available on DeepInfra is Kimi K2.6 with an Intelligence Index score of 54.
The fastest model on DeepInfra by output speed is Qwen3.5 2B at 336.6 tokens per second.
The model with the lowest time to first token on DeepInfra is Qwen3.5 2B at 0.34s. Lower latency means faster initial response time.
The most affordable model on DeepInfra by blended price is Qwen3.5 0.8B at $0.02 per 1M tokens (3:1 input to output ratio).
Prices on DeepInfra vary up to 109x across models, from $0.02 per 1M tokens for Qwen3.5 0.8B to $2.17 per 1M tokens for DeepSeek V4 Pro (High).
Yes, DeepInfra offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
58 of 80 models on DeepInfra support JSON mode for structured output.
73 of 80 models on DeepInfra support function calling (tool use).
Yes, DeepInfra offers 34 reasoning models: Kimi K2.6, MiMo-V2.5-Pro, DeepSeek V4 Pro (Max), GLM-5.1, DeepSeek V4 Pro (High), GLM-5, Kimi K2.5, DeepSeek V4 Flash (Max), DeepSeek V4 Flash (High), Qwen3.6 27B, Qwen3.5 397B A17B, Qwen3.6 35B A3B, GLM-4.7, Qwen3.5 27B, MiniMax-M2.5, Qwen3.5 122B A10B, Gemma 4 31B, Qwen3.5 35B A3B, gpt-oss-120B (high), gpt-oss-120B (high), GLM-4.6, Gemma 4 26B A4B, GLM-4.7-Flash, Qwen3 235B A22B 2507, Qwen3.5 4B, DeepSeek R1 0528, gpt-oss-20B (high), NVIDIA Nemotron 3 Nano, Llama Nemotron Super 49B v1.5, Qwen3 32B, Qwen3 14B, Qwen3 30B, NVIDIA Nemotron Nano 9B V2, and DeepSeek R1 Distill Llama 70B. Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, all 80 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.