DeepInfra: Models Intelligence, Performance & Price

Name: Intelligence
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

DeepInfra

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

Updated

GLM-5.2 (max) (FP4)

DeepSeek V4 Pro (max) (FP4)

Kimi K2.6 (FP4)

DeepSeek V4 Pro (high) (FP4)

MiMo-V2.5-Pro

Intelligence index

Total 91 models

Fastest

gpt-oss-120b (high) (Turbo)

310 t/s

Step 3.7 Flash

179 t/s

Qwen3.5 35B A3B (FP8)

173 t/s

Qwen3.5 35B A3B FP8

150 t/s

Qwen3 Next 80B A3B

117 t/s

Output speed

Total 91 models

Lowest Price

Llama 3.1 8B (Turbo, FP8)

$0.02

Llama 3.1 8B

$0.02

Gemma 4 E4B

$0.03

Gemma 4 E4B

$0.03

gpt-oss-20b (high)

$0.04

Blended price (per 1M tokens)

Total 91 models

Indicates a reasoning model

DeepInfra offers 91 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-5.2 (max) (FP4) (51), DeepSeek V4 Pro (max) (FP4) (44), Kimi K2.6 (FP4) (44).
For output speed, the fastest models are gpt-oss-120b (high) (Turbo) (310 t/s), Step 3.7 Flash (179 t/s), Qwen3.5 35B A3B (FP8) (173 t/s). Speed varies significantly across models, with a 165% difference between the fastest and slowest.
For latency, NVIDIA Nemotron 3 Nano (0.38s), Qwen3.5 35B A3B FP8 (0.44s), Qwen3 30B (FP8) (0.52s) offer the lowest time to first answer token.
For pricing, Llama 3.1 8B (Turbo, FP8) ($0.02), Llama 3.1 8B ($0.02), Gemma 4 E4B ($0.03) offer the lowest blended prices per 1M tokens.
For context window size, GLM-5.2 (max) (FP4) (1M), DeepSeek V4 Pro (max) (FP4) (1M), DeepSeek V4 Flash (max) (FP4) (1M) support the largest context windows on DeepInfra.

Highlights

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M tokens (blended) · Lower is better

Intelligence Evaluations

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR

Estimate (independent evaluation forthcoming)

Reasoning models are indicated by a lightbulb icon

Artificial Analysis Intelligence Index v4.1 includes: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

𝜏³-Banking

Agentic tool use

Terminal-Bench v2.1

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GPQA Diamond

Scientific reasoning

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR

Long context reasoning

AA-BriefcaseNew

Agentic knowledge work, Elo

AutomationBench-AANew

Agentic SaaS workflows

Harvey LAB-AANew

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AANew

Agentic business operations

IFBench

Instruction following

APEX-Agents-AA

Long-horizon agentic tasks

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

Reasoning models are indicated by a lightbulb icon

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

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).

Context Window

Context window: tokens limit · Higher is better

Reasoning models are indicated by a lightbulb icon

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Pricing

Intelligence Index vs. Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon

While higher intelligence models are typically more expensive, they do not all follow the same price-quality curve.

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

The blended cache price shown here uses cache hit price only. Other caching costs differ by provider:

Anthropic: charges a separate cache write fee, with different rates for 5-minute and 1-hour TTLs (1-hour TTL is more expensive).
Google (Vertex/Gemini): charges a per-hour cache storage fee in addition to cache hit pricing. Some providers also use tiered pricing for prompts above 200K tokens.
OpenAI, DeepSeek, others: typically charge only cache hit pricing with no write or storage fee.

See Prompt Caching for the full breakdown.

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 · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon

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, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better

Reasoning models are indicated by a lightbulb icon

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

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

Reasoning models are indicated by a lightbulb icon

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.

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 · USD per 1M tokens (blended)

Most attractive quadrant

Reasoning models are indicated by a lightbulb icon

Price per token, shown in USD per million tokens. Price is a blend of cache hit, input, and output token prices using the selected ratio (default 7:2:1 cache-input-output).

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 median (P50) measurement over the past 72 hours to reflect sustained changes in performance.


									Further Analysis
GLM-5.2 (max) (FP4)	1.05M	Open	51	--	48	1.11	53.60	41.99	Model Provider
DeepSeek V4 Pro (max) (FP4)	1.05M	Open	44	--	54	1.33	92.36	81.70	Model Provider
Kimi K2.6 (FP4)	262k	Open	44	$0.28	42	0.88	119.69	106.82	Model Provider
DeepSeek V4 Pro (high) (FP4)	65.5k	Open	43	--	58	1.11	44.18	34.43	Model Provider
MiMo-V2.5-Pro	65.5k	Open	42	$0.28	85	0.75	30.25	23.60	Model Provider
Kimi K2.7 Code	262k	Open	42	--	51	0.89	54.85	44.07	Model Provider
Hy3 (FP8)	262k	Open	41	$0.03	42	0.65	60.48	47.87	Model Provider
DeepSeek V4 Flash (max) (FP4)	1.05M	Open	40	--	30	1.16	202.91	185.25	Model Provider
GLM-5.1 (FP4)	203k	Open	40	$0.18	52	1.01	82.99	72.43	Model Provider
GLM-5 (FP4)	203k	Open	40*	--	39	1.05	93.81	79.90	Model Provider
Nemotron 3 Ultra	262k	Open	38	$0.14	71	4.83	44.01	32.12	Model Provider
Nemotron 3 Ultra BF16	262k	Open	38	--	--	--	--	--	Model Provider
DeepSeek V4 Flash (high) (FP4)	1.05M	Open	37	--	32	1.02	54.87	38.38	Model Provider
MiMo-V2.5	262k	Open	37	--	47	0.80	53.73	42.34	Model Provider
Qwen3.6 27B FP8	262k	Open	37	--	49	1.47	126.57	114.97	Model Provider
Kimi K2.5	262k	Open	35	$0.07	71	0.76	49.83	41.99	Model Provider
GLM-5.1 (FP4)	203k	Open	35*	--	58	0.73	9.29	--	Model Provider
Kimi K2.6 (FP4)	262k	Open	35*	--	39	0.74	13.53	--	Model Provider
Qwen3.5 27B (FP8)	262k	Open	34*	--	68	0.93	37.91	29.59	Model Provider
GLM-4.7 (FP4)	203k	Open	34	$0.09	33	0.90	77.13	60.98	Model Provider
Qwen3.5 397B A17B (FP8)	262k	Open	34	$0.18	48	1.18	77.75	66.18	Model Provider
MiniMax-M2.5 (FP8)	197k	Open	34*	--	35	0.85	71.90	56.84	Model Provider
GLM-5 (FP8)	203k	Open	32*	--	41	0.98	13.21	--	Model Provider
Qwen3.5 122B A10B (FP4)	262k	Open	32	$0.11	55	5.38	51.02	36.51	Model Provider
DeepSeek V3.2 (FP4)	164k	Open	32	$0.06	16	1.03	161.77	128.60	Model Provider
Qwen3.5 397B A17B (FP8)	262k	Open	32*	--	32	1.29	16.97	--	Model Provider
Qwen3.6 35B A3B (FP8)	262k	Open	32	$0.11	58	0.64	102.21	92.95	Model Provider
Qwen3.6 27B FP8	262k	Open	30	--	39	1.53	14.50	--	Model Provider
Step 3.7 Flash	256k	Open	30	--	179	0.52	14.47	11.16	Model Provider
Gemma 4 31B	262k	Open	29	$0.01	13	1.57	167.81	129.07	Model Provider
Qwen3.5 27B FP8	262k	Open	29*	--	51	0.99	10.77	--	Model Provider
Qwen3.5 35B A3B (FP8)	262k	Open	29*	--	173	0.46	14.94	11.58	Model Provider
GLM-4.6 (FP4)	203k	Open	29	--	41	1.18	62.50	49.05	Model Provider
MiMo-V2.5-Pro	65.5k	Open	28*	--	82	0.80	6.90	--	Model Provider
Qwen3.5 122B A10B (FP4)	262k	Open	28	$0.09	71	5.90	12.98	--	Model Provider
GLM-4.7 (FP4)	203k	Open	27*	--	44	0.96	12.29	--	Model Provider
Gemma 4 26B A4B	262k	Open	26	$0.02	31	0.72	80.75	64.02	Model Provider
NVIDIA Nemotron 3 Super	262k	Open	25	--	--	--	--	--	Model Provider
DeepSeek V3.2	164k	Open	25*	--	14	1.19	38.01	--	Model Provider
Qwen3.6 35B A3B (FP8)	262k	Open	24	$0.30	60	0.59	8.90	--	Model Provider
Qwen3.5 35B A3B FP8	262k	Open	24	$0.07	150	0.44	3.77	--	Model Provider
gpt-oss-120b (high)	131k	Open	24	$0.02	47	0.60	53.78	42.54	Model Provider
gpt-oss-120b (high) (Turbo)	131k	Open	24	--	310	0.62	8.70	6.46	Model Provider
GLM-4.7-Flash	203k	Open	23*	--	72	0.58	35.43	27.88	Model Provider
Gemma 4 31B (FP8)	262k	Open	22	$0.03	12	1.02	43.82	--	Model Provider
DeepSeek V3.1 Terminus (FP4)	164k	Open	21*	--	77	0.59	7.12	--	Model Provider
DeepSeek V3.1 (FP4)	164k	Open	21*	--	20	1.15	26.59	--	Model Provider
Gemma 4 26B A4B (FP8)	262k	Open	20*	--	28	0.59	18.26	--	Model Provider
Qwen3.5 4B (FP8)	262k	Open	20*	--	19	0.96	130.67	103.76	Model Provider
DeepSeek R1 0528	164k	Open	20*	--	29	0.77	87.24	69.18	Model Provider
Qwen3 235B A22B 2507 (FP8)	262k	Open	20	--	49	1.01	52.31	41.05	Model Provider
Qwen3 235B 2507 (FP8)	262k	Open	18*	--	20	0.52	25.59	--	Model Provider
Qwen3 Coder 480B (Turbo, FP4)	262k	Open	18*	--	52	0.53	10.15	--	Model Provider
Qwen3.5 4B FP8	262k	Open	16*	--	18	0.97	28.03	--	Model Provider
DeepSeek V3 0324 (FP4)	164k	Open	15	$0.03	38	1.62	14.61	--	Model Provider
gpt-oss-20b (high)	131k	Open	15	--	111	0.42	23.01	18.07	Model Provider
Mistral Small 3.1	128k	Open	15	$0.02	57	0.80	9.64	--	Model Provider
Llama 4 Maverick (FP8)	1.05M	Open	14	--	44	0.60	11.90	--	Model Provider
NVIDIA Nemotron 3 Nano	262k	Open	14	$0.02	80	8.08	39.51	25.15	Model Provider
DeepSeek V3 (Dec)	164k	Open	14	$0.02	23	0.70	22.12	--	Model Provider
Qwen3 Next 80B A3B	262k	Open	14*	--	117	0.63	4.91	--	Model Provider
Llama Nemotron Super 49B v1.5	131k	Open	12*	--	70	7.49	43.23	28.59	Model Provider
Gemma 4 E4B	262k	Open	12	--	94	0.83	27.52	21.35	Model Provider
Qwen3 32B (FP8)	41k	Open	12	--	68	0.63	37.52	29.52	Model Provider
Mistral Small 3.2 (FP8)	128k	Open	11	$0.09	46	0.77	11.64	--	Model Provider
Qwen3 14B (FP8)	32.8k	Open	10	--	47	0.81	53.61	42.24	Model Provider
Llama 4 Scout	328k	Open	10	$0.0049	47	0.67	11.30	--	Model Provider
DeepSeek R1 Distill Llama 70B	131k	Open	10*	--	33	0.78	76.68	60.72	Model Provider
Qwen2.5 72B	32.8k	Open	10*	--	32	2.08	17.54	--	Model Provider
Llama 3.3 70B (Turbo, FP8)	131k	Open	9	$0.01	13	2.45	42.30	--	Model Provider
Qwen3 30B (FP8)	41k	Open	9*	--	82	0.54	30.85	24.26	Model Provider
NVIDIA Nemotron Nano 12B v2 VL (FP8)	131k	Open	9*	--	80	8.32	39.73	25.13	Model Provider
Gemma 4 E4B	262k	Open	9*	--	94	0.79	6.13	--	Model Provider
NVIDIA Nemotron Nano 9B V2	131k	Open	9*	--	76	9.66	42.59	26.34	Model Provider
Llama Nemotron Super 49B v1.5	131k	Open	9*	--	70	5.96	13.10	--	Model Provider
Qwen3 32B (FP8)	41k	Open	9*	--	65	0.60	8.25	--	Model Provider
Llama 3.1 Nemotron 70B	131k	Open	8*	--	61	6.11	14.26	--	Model Provider
Llama 3.1 8B (Turbo, FP8)	131k	Open	8	--	17	1.07	30.48	--	Model Provider
Llama 3.1 8B	131k	Open	8	--	20	1.08	25.81	--	Model Provider
Gemma 3 27B	131k	Open	7	$0.07	24	1.17	21.67	--	Model Provider
NVIDIA Nemotron 3 Nano	262k	Open	7*	--	72	0.38	7.31	--	Model Provider
NVIDIA Nemotron Nano 9B V2	131k	Open	7*	--	88	6.74	12.43	--	Model Provider
Qwen3 14B (FP8)	41k	Open	7*	--	47	0.82	11.38	--	Model Provider
Mistral Small 3	32.8k	Open	7*	--	35	0.82	15.04	--	Model Provider
Qwen3 30B (FP8)	41k	Open	7*	--	105	0.52	5.27	--	Model Provider
Llama 3.1 70B (Turbo, FP8)	131k	Open	7*	--	28	1.88	19.51	--	Model Provider
Llama 3.1 70B	131k	Open	7*	--	28	2.01	19.77	--	Model Provider
Gemma 3 12B	131k	Open	6	$0.07	50	0.76	10.66	--	Model Provider
Hermes 3 - Llama-3.1 70B	131k	Open	5*	--	36	1.89	15.65	--	Model Provider
Phi-4	16.4k	Open	5*	--	75	0.75	7.46	--	Model Provider
NVIDIA Nemotron Nano 12B v2 VL (FP8)	131k	Open	5*	--	67	5.07	12.56	--	Model Provider
Llama 3.2 11B (Vision)	131k	Open	3*	--	12	1.46	43.06	--	Model Provider
Llama 3 8B	8.19k	Open	1*	--	--	--	--	--	Model Provider
Gemma 3 4B	131k	Open	1*	--	35	0.98	15.07	--	Model Provider

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.

Average cost per task in the index. Costs are split by input, cache hit, cache write, reasoning, and answer token pricing where canonical token counts are available.

Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

Price per token to write prompt tokens into the cache so that later requests can hit them, represented as USD per million tokens. Some providers charge a premium over the standard input price to create a cache entry (e.g. Anthropic), while others cache automatically with no separate write fee.

Price per token generated by the model (received from 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 91 models that we track: GLM-5.2 (max) (FP4), DeepSeek V4 Pro (max) (FP4), Kimi K2.6 (FP4), DeepSeek V4 Pro (high) (FP4), MiMo-V2.5-Pro, Kimi K2.7 Code, Hy3 (FP8), DeepSeek V4 Flash (max) (FP4), GLM-5.1 (FP4), GLM-5 (FP4), Nemotron 3 Ultra, DeepSeek V4 Flash (high) (FP4), MiMo-V2.5, Qwen3.6 27B FP8, Kimi K2.5, GLM-5.1 (FP4), Kimi K2.6 (FP4), Qwen3.5 27B (FP8), GLM-4.7 (FP4), Qwen3.5 397B A17B (FP8), MiniMax-M2.5 (FP8), GLM-5 (FP8), Qwen3.5 122B A10B (FP4), DeepSeek V3.2 (FP4), Qwen3.5 397B A17B (FP8), Qwen3.6 35B A3B (FP8), Qwen3.6 27B FP8, Step 3.7 Flash, Gemma 4 31B, Qwen3.5 27B FP8, Qwen3.5 35B A3B (FP8), GLM-4.6 (FP4), MiMo-V2.5-Pro, Qwen3.5 122B A10B (FP4), GLM-4.7 (FP4), Gemma 4 26B A4B, DeepSeek V3.2, Qwen3.6 35B A3B (FP8), Qwen3.5 35B A3B FP8, gpt-oss-120b (high), gpt-oss-120b (high) (Turbo), GLM-4.7-Flash, Gemma 4 31B (FP8), DeepSeek V3.1 Terminus (FP4), DeepSeek V3.1 (FP4), Gemma 4 26B A4B (FP8), Qwen3.5 4B (FP8), DeepSeek R1 0528, Qwen3 235B A22B 2507 (FP8), Qwen3 235B 2507 (FP8), Qwen3 Coder 480B (Turbo, FP4), Qwen3.5 4B FP8, DeepSeek V3 0324 (FP4), gpt-oss-20b (high), Mistral Small 3.1, Llama 4 Maverick (FP8), NVIDIA Nemotron 3 Nano, DeepSeek V3 (Dec), Qwen3 Next 80B A3B, Llama Nemotron Super 49B v1.5, Gemma 4 E4B, Qwen3 32B (FP8), Mistral Small 3.2 (FP8), Qwen3 14B (FP8), Llama 4 Scout, DeepSeek R1 Distill Llama 70B, Qwen2.5 72B, Llama 3.3 70B (Turbo, FP8), Qwen3 30B (FP8), NVIDIA Nemotron Nano 12B v2 VL (FP8), Gemma 4 E4B, NVIDIA Nemotron Nano 9B V2, Llama Nemotron Super 49B v1.5, Qwen3 32B (FP8), Llama 3.1 Nemotron 70B, Llama 3.1 8B (Turbo, FP8), Llama 3.1 8B, Gemma 3 27B, NVIDIA Nemotron 3 Nano, NVIDIA Nemotron Nano 9B V2, Qwen3 14B (FP8), Mistral Small 3, Qwen3 30B (FP8), Llama 3.1 70B (Turbo, FP8), Llama 3.1 70B, Gemma 3 12B, Hermes 3 - Llama-3.1 70B, Phi-4, NVIDIA Nemotron Nano 12B v2 VL (FP8), Llama 3.2 11B (Vision), and Gemma 3 4B.

The most intelligent model available on DeepInfra is GLM-5.2 (max) (FP4) with an Intelligence Index score of 51.

The fastest model on DeepInfra by output speed is gpt-oss-120b (high) (Turbo) at 309.5 tokens per second.

The model with the lowest time to first answer token on DeepInfra is NVIDIA Nemotron 3 Nano at 0.38s. Lower latency means faster initial response time.

The most affordable model on DeepInfra by blended price is Llama 3.1 8B (Turbo, FP8) at $0.02 per 1M tokens (7:2:1 cache hit/input/output ratio).

Prices on DeepInfra vary up to 57x across models, from $0.02 per 1M tokens for Llama 3.1 8B (Turbo, FP8) to $1.20 per 1M tokens for Llama 3.1 Nemotron 70B.

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

88 of 91 models on DeepInfra support JSON mode for structured output.

88 of 91 models on DeepInfra support function calling (tool use).

Yes, DeepInfra offers 43 reasoning models: GLM-5.2 (max) (FP4), DeepSeek V4 Pro (max) (FP4), Kimi K2.6 (FP4), DeepSeek V4 Pro (high) (FP4), MiMo-V2.5-Pro, Kimi K2.7 Code, Hy3 (FP8), DeepSeek V4 Flash (max) (FP4), GLM-5.1 (FP4), GLM-5 (FP4), Nemotron 3 Ultra, DeepSeek V4 Flash (high) (FP4), MiMo-V2.5, Qwen3.6 27B FP8, Kimi K2.5, Qwen3.5 27B (FP8), GLM-4.7 (FP4), Qwen3.5 397B A17B (FP8), MiniMax-M2.5 (FP8), Qwen3.5 122B A10B (FP4), DeepSeek V3.2 (FP4), Qwen3.6 35B A3B (FP8), Step 3.7 Flash, Gemma 4 31B, Qwen3.5 35B A3B (FP8), GLM-4.6 (FP4), Gemma 4 26B A4B, gpt-oss-120b (high), gpt-oss-120b (high) (Turbo), GLM-4.7-Flash, Qwen3.5 4B (FP8), DeepSeek R1 0528, Qwen3 235B A22B 2507 (FP8), gpt-oss-20b (high), NVIDIA Nemotron 3 Nano, Llama Nemotron Super 49B v1.5, Gemma 4 E4B, Qwen3 32B (FP8), Qwen3 14B (FP8), DeepSeek R1 Distill Llama 70B, Qwen3 30B (FP8), NVIDIA Nemotron Nano 12B v2 VL (FP8), and NVIDIA Nemotron Nano 9B V2. Reasoning models use extended thinking to work through complex problems before providing an answer.

Yes, all 91 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.

DeepInfra: Models Intelligence, Performance & Price

Most Intelligent

Fastest

Lowest Price

Intelligence