Providers· Inference host· 65 tracked models

DeepInfra — pricing & performance

Compare models All providers Data sources

Models served

of 908 tracked models

Mean output speed

tokens per second, averaged over
64 measured endpoints

Mean latency

1.3s

time to first token, averaged over
64 measured endpoints

Cheapest blended

$0.022

per 1M tokens at a 3:1
input:output blend

Output speed on DeepInfra

Median output tokens per second for each model this host serves, derived from OpenRouter endpoint telemetry. Higher is better. We do not run these measurements ourselves.

12 of 65 models ▾ ☰⚙⇩ +Add model from specific provider

246

194

139

131

Qwen3 Next 80B A3B
Instruct

Qwen3 14B

Phi 4

Nemotron 3 Nano
30B A3B

GLM 5.2

The Known Good

65 models on DeepInfra

Full leaderboard →

Model	Creator	Input $/M	Output $/M	Blended	Speed	TTFT	Context
DeepSeek: DeepSeek V3	DeepSeek	$0.32	$0.89	$0.46	20	0.5s	164k
DeepSeek: DeepSeek V3 0324	DeepSeek	$0.24	$0.90	$0.41	25	0.7s	164k
DeepSeek: DeepSeek V3.1	DeepSeek	$0.25	$0.95	$0.42	9	1.1s	164k
DeepSeek: DeepSeek V3.1 Terminus	DeepSeek	$0.27	$0.95	$0.44	33	0.6s	164k
DeepSeek: DeepSeek V3.2	DeepSeek	$0.26	$0.38	$0.29	9	1.0s	164k
DeepSeek: DeepSeek V4 Flash	DeepSeek	$0.090	$0.18	$0.11	34	0.9s	1.05M
DeepSeek: DeepSeek V4 Pro	DeepSeek	$1.30	$2.60	$1.62	65	0.5s	1.05M
DeepSeek: R1 0528	DeepSeek	$0.50	$2.15	$0.91	21	0.6s	164k
Google: Gemma 3 12B	Google	$0.050	$0.15	$0.075	41	0.4s	131k
Google: Gemma 3 27B	Google	$0.080	$0.16	$0.10	22	0.7s	131k
Google: Gemma 3 4B	Google	$0.050	$0.10	$0.062	5	2.3s	131k
Google: Gemma 4 26B A4B	Google	$0.070	$0.34	$0.14	24	0.4s	262k
Google: Gemma 4 31B	Google	$0.12	$0.37	$0.18	61	0.4s	262k
Meta: Llama 3.1 70B Instruct	Meta	$0.40	$0.40	$0.40	20	0.5s	131k
Meta: Llama 3.1 8B Instruct	Meta	$0.020	$0.040	$0.025	14	0.5s	131k
Meta: Llama 3.3 70B Instruct	Meta	$0.10	$0.32	$0.15	12	0.6s	131k
Meta: Llama 4 Maverick	Meta	$0.20	$0.80	$0.35	28	0.3s	1.05M
Meta: Llama 4 Scout	Meta	$0.10	$0.30	$0.15	24	0.3s	328k
Meta: Llama Guard 4 12B	Meta	$0.18	$0.18	$0.18	9	0.3s	164k
Microsoft: Phi 4	Microsoft	$0.070	$0.14	$0.087	70	0.3s	16k
MiniMax: MiniMax M2.7	MiniMax	$0.25	$1.00	$0.44	28	1.4s	197k
MiniMax: MiniMax M3	MiniMax	$0.30	$1.20	$0.53	66	0.4s	524k
Mistral: Mistral Nemo	Mistral	$0.019	$0.030	$0.022	24	0.7s	131k
Mistral: Mistral Small 3	Mistral	$0.050	$0.080	$0.058	43	0.3s	33k
Mistral: Mistral Small 3.2 24B	Mistral	$0.075	$0.20	$0.11	57	0.3s	128k
MoonshotAI: Kimi K2.5	Moonshot AI	$0.45	$2.25	$0.90	25	0.7s	262k
MoonshotAI: Kimi K2.6	Moonshot AI	$0.75	$3.50	$1.44	57	0.7s	262k
MoonshotAI: Kimi K2.7 Code	Moonshot AI	$0.74	$3.50	$1.43	—	—	262k
Gr MythoMax 13B	gryphe	$0.40	$0.40	$0.40	39	0.3s	4k
Nous: Hermes 3 405B Instruct	Nous Research	$1.00	$1.00	$1.00	20	0.5s	131k
Nous: Hermes 3 70B Instruct	Nous Research	$0.70	$0.70	$0.70	34	0.3s	131k
NVIDIA: Nemotron 3 Nano 30B A3B	NVIDIA	$0.050	$0.20	$0.087	69	1.5s	262k
NVIDIA: Nemotron 3 Super	NVIDIA	$0.085	$0.40	$0.16	6	0.4s	262k
NVIDIA: Nemotron 3 Ultra	NVIDIA	$0.50	$2.20	$0.93	40	1.9s	262k
OpenAI: gpt-oss-120b	OpenAI	$0.037	$0.17	$0.070	246	0.4s	131k
OpenAI: gpt-oss-20b	OpenAI	$0.030	$0.14	$0.058	82	0.4s	131k
Qwen2.5 72B Instruct	Alibaba	$0.36	$0.40	$0.37	36	0.3s	33k
Qwen: Qwen3 14B	Alibaba	$0.12	$0.24	$0.15	75	0.3s	41k
Qwen: Qwen3 235B A22B Instruct 2507	Alibaba	$0.090	$0.55	$0.20	18	0.4s	262k
Qwen: Qwen3 235B A22B Thinking 2507	Alibaba	$0.23	$2.30	$0.75	58	0.3s	262k
Qwen: Qwen3 30B A3B	Alibaba	$0.12	$0.50	$0.21	83	0.2s	41k
Qwen: Qwen3 32B	Alibaba	$0.080	$0.28	$0.13	39	0.2s	41k
Qwen: Qwen3 Coder 480B A35B	Alibaba	$0.30	$1.00	$0.47	50	0.3s	262k
Qwen: Qwen3 Next 80B A3B Instruct	Alibaba	$0.090	$1.10	$0.34	77	0.4s	262k
Qwen: Qwen3 VL 235B A22B Instruct	Alibaba	$0.20	$0.88	$0.37	6	0.8s	262k
Qwen: Qwen3 VL 30B A3B Instruct	Alibaba	$0.15	$0.60	$0.26	22	0.4s	262k
Qwen: Qwen3.5 397B A17B	Alibaba	$0.45	$3.00	$1.09	44	0.3s	262k
Qwen: Qwen3.5-122B-A10B	Alibaba	$0.29	$2.40	$0.82	35	44.1s	262k
Qwen: Qwen3.5-27B	Alibaba	$0.26	$2.60	$0.84	56	0.3s	262k
Qwen: Qwen3.5-35B-A3B	Alibaba	$0.14	$1.00	$0.35	131	0.2s	262k
Qwen: Qwen3.5-9B	Alibaba	$0.10	$0.15	$0.11	16	0.3s	262k
Qwen: Qwen3.6 27B	Alibaba	$0.32	$3.20	$1.04	51	0.7s	262k
Sa Sao10K: Llama 3 8B Lunaris	sao10k	$0.040	$0.050	$0.043	62	0.2s	8k
Sa Sao10K: Llama 3.1 Euryale 70B v2.2	sao10k	$0.85	$0.85	$0.85	36	0.5s	131k
St StepFun: Step 3.7 Flash	stepfun	$0.20	$1.15	$0.44	194	0.2s	262k
Tencent: Hy3	Tencent	$0.14	$0.58	$0.25	29	0.9s	262k
TM Thinking Machines: Inkling	Thinking Machines	$1.00	$4.05	$1.76	139	0.4s	524k
Mi Xiaomi: MiMo-V2.5	Xiaomi	$0.40	$2.00	$0.80	98	0.5s	262k
Mi Xiaomi: MiMo-V2.5-Pro	Xiaomi	$1.00	$3.00	$1.50	47	0.5s	1.05M
Z.ai: GLM 4.6	Z.ai	$0.50	$2.00	$0.88	39	0.6s	203k
Z.ai: GLM 4.7	Z.ai	$0.40	$1.75	$0.74	49	0.8s	203k
Z.ai: GLM 4.7 Flash	Z.ai	$0.060	$0.40	$0.14	60	0.3s	203k
Z.ai: GLM 5	Z.ai	$0.60	$2.08	$0.97	29	0.7s	203k
Z.ai: GLM 5.1	Z.ai	$1.05	$3.50	$1.66	66	0.9s	203k
Z.ai: GLM 5.2	Z.ai	$0.93	$3.00	$1.45	68	1.0s	1.05M

The Known Good

Source. Prices, endpoint availability and throughput for DeepInfra are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.