Provider / deepinfra

DeepInfra

Source-backed price evidence and all available provider routes.

Models
135
Canonical entries
Endpoints
135
Active routes
Fresh endpoints
113
Current source components
Latest evidence
Source retrieval

Available offers

Endpoint ledger

Includes stale and conditional offers for a complete provider view.

01
Mistral Nemo Instruct 2407mistralai/Mistral-Nemo-Instruct-2407
DeepInfraglobal
openai chat completions
Fresh
$0.049for selected workload
02
Meta Llama 3 1 8b Instruct Turbometa-llama/Meta-Llama-3.1-8B-Instruct-Turbo
DeepInfraglobal
openai chat completions
Fresh
$0.06for selected workload
no independent observations
03
L3 8b Lunaris V1 TurboSao10K/L3-8B-Lunaris-v1-Turbo
DeepInfraglobal
openai chat completions
Fresh
$0.09for selected workload
no independent observations
04
Gemma 4 E4b Itgoogle/gemma-4-E4B-it
DeepInfraglobal
openai chat completions
Fresh
$0.12for selected workload
no independent observations
05
Mistral Small 24b Instruct 2501mistralai/Mistral-Small-24B-Instruct-2501
DeepInfraglobal
openai chat completions
Fresh
$0.13for selected workload
no independent observations
06
Gemma 3 4b Itgoogle/gemma-3-4b-it
DeepInfraglobal
openai chat completions
Fresh
$0.15for selected workload
no independent observations
07
Granite 4 2 3bibm-granite/granite-4.2-3b
DeepInfraglobal
openai chat completions
Fresh
$0.15for selected workload
no independent observations
08
GPT OSS 20bopenai/gpt-oss-20b
DeepInfraglobal
openai chat completions
Fresh
$0.17for selected workload
no independent observations
09
Gemma 3 12b Itgoogle/gemma-3-12b-it
DeepInfraglobal
openai chat completions
Fresh
$0.20for selected workload
no independent observations
10
GPT OSS 120bopenai/gpt-oss-120b
DeepInfraglobal
openai chat completions
Fresh
$0.207for selected workload
no independent observations
11
Phi 4microsoft/phi-4
DeepInfraglobal
openai chat completions
Fresh
$0.21for selected workload
no independent observations
12
Ling 3 0 FlashinclusionAI/Ling-3.0-flash
DeepInfraglobal
openai chat completions
Fresh
$0.24for selected workload
no independent observations
13
Gemma 3 27b Itgoogle/gemma-3-27b-it
DeepInfraglobal
openai chat completions
Fresh
$0.24for selected workload
no independent observations
14
Ling 3 0 Flash FininclusionAI/Ling-3.0-flash-Fin
DeepInfraglobal
openai chat completions
Fresh
$0.24for selected workload
no independent observations
15
DeepSeek V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-0731
DeepInfraglobal
openai chat completions
Fresh
$0.24for selected workload
no independent observations
16
Ling 3 0 Flash VlinclusionAI/Ling-3.0-flash-VL
DeepInfraglobal
openai chat completions
Fresh
$0.24for selected workload
no independent observations
17
Nemotron 3 Nano 30b A3bnvidia/Nemotron-3-Nano-30B-A3B
DeepInfraglobal
openai chat completions
Fresh
$0.25for selected workload
no independent observations
18
Qwen3 5 9bQwen/Qwen3.5-9B
DeepInfraglobal
openai chat completions
Fresh
$0.25for selected workload
no independent observations
19
DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash
DeepInfraglobal
openai chat completions
Fresh
$0.27for selected workload
no independent observations
20
Mistral Small 3 2 24b Instruct 2506mistralai/Mistral-Small-3.2-24B-Instruct-2506
DeepInfraglobal
openai chat completions
Fresh
$0.275for selected workload
no independent observations
21
Nvidia Nemotron 3 5 Lightningnvidia/NVIDIA-Nemotron-3.5-Lightning
DeepInfraglobal
openai chat completions
Fresh
$0.28for selected workload
no independent observations
22
Granite 4 2 8bibm-granite/granite-4.2-8b
DeepInfraglobal
openai chat completions
Fresh
$0.31for selected workload
no independent observations
23
Qwen3 32bQwen/Qwen3-32B
DeepInfraglobal
openai chat completions
Fresh
$0.36for selected workload
no independent observations
24
Qwen3 14bQwen/Qwen3-14B
DeepInfraglobal
openai chat completions
Fresh
$0.36for selected workload
no independent observations
25
Llama Guard 4 12bmeta-llama/Llama-Guard-4-12B
DeepInfraglobal
openai chat completions
Fresh
$0.36for selected workload
no independent observations
26
Nemotron Content Safety 3 5nvidia/Nemotron-Content-Safety-3.5
DeepInfraglobal
openai chat completions
Fresh
$0.40for selected workload
no independent observations
27
Llama 4 Scout 17b 16e Instructmeta-llama/Llama-4-Scout-17B-16E-Instruct
DeepInfraglobal
openai chat completions
Fresh
$0.40for selected workload
no independent observations
28
Gemma 4 26b A4b Itgoogle/gemma-4-26B-A4B-it
DeepInfraglobal
openai chat completions
Fresh
$0.41for selected workload
no independent observations
29
Llama 3 3 70b Instruct Turbometa-llama/Llama-3.3-70B-Instruct-Turbo
DeepInfraglobal
openai chat completions
Fresh
$0.42for selected workload
no independent observations
30
Mimo V2 5XiaomiMiMo/MiMo-V2.5
DeepInfraglobal
openai chat completions
Fresh
$0.42for selected workload
no independent observations
31
Gemma 4 31b It Turbogoogle/gemma-4-31B-it-turbo
DeepInfraglobal
openai chat completions
Fresh
$0.43for selected workload
no independent observations
32
GLM 4 7 Flashzai-org/GLM-4.7-Flash
DeepInfraglobal
openai chat completions
Fresh
$0.46for selected workload
no independent observations
33
Nvidia Nemotron 3 Super 120b A12bnvidia/NVIDIA-Nemotron-3-Super-120B-A12B
DeepInfraglobal
openai chat completions
Fresh
$0.485for selected workload
no independent observations
34
Qwen3 8 FlashQwen/Qwen3.8-Flash
DeepInfraglobal
openai chat completions
Fresh
$0.495for selected workload
no independent observations
35
Seed 2 0 MiniByteDance/Seed-2.0-mini
DeepInfraglobal
openai chat completions
Fresh
$0.50for selected workload
no independent observations
36
Gemma 4 31b Itgoogle/gemma-4-31B-it
DeepInfraglobal
openai chat completions
Fresh
$0.51for selected workload
no independent observations
37
Qwen3 30b A3bQwen/Qwen3-30B-A3B
DeepInfraglobal
openai chat completions
Fresh
$0.62for selected workload
no independent observations
38
DeepSeek V3 2deepseek-ai/DeepSeek-V3.2
DeepInfraglobal
openai chat completions
Fresh
$0.64for selected workload
no independent observations
39
Qwen3 235b A22b Instruct 2507Qwen/Qwen3-235B-A22B-Instruct-2507
DeepInfraglobal
openai chat completions
Fresh
$0.64for selected workload
no independent observations
40
GLM 5 3 Flashzai-org/GLM-5.3-Flash
DeepInfraglobal
openai chat completions
Fresh
$0.65for selected workload
no independent observations
41
hy3tencent/Hy3
DeepInfraglobal
openai chat completions
Fresh
$0.72for selected workload
no independent observations
42
GPT OSS 120b Turboopenai/gpt-oss-120b-Turbo
DeepInfraglobal
openai chat completions
Fresh
$0.75for selected workload
no independent observations
43
Qwen3 Vl 30b A3b InstructQwen/Qwen3-VL-30B-A3B-Instruct
DeepInfraglobal
openai chat completions
Fresh
$0.75for selected workload
no independent observations
44
Qwen2 5 72b InstructQwen/Qwen2.5-72B-Instruct
DeepInfraglobal
openai chat completions
Fresh
$0.76for selected workload
no independent observations
45
Mythomax L2 13bGryphe/MythoMax-L2-13b
DeepInfraglobal
openai chat completions
Fresh
$0.80for selected workload
no independent observations
46
Meta Llama 3 1 70b Instruct Turbometa-llama/Meta-Llama-3.1-70B-Instruct-Turbo
DeepInfraglobal
openai chat completions
Fresh
$0.80for selected workload
no independent observations
47
DeepSeek V4 1 Flashdeepseek-ai/DeepSeek-V4.1-Flash
DeepInfraglobal
openai chat completions
Fresh
$0.80for selected workload
no independent observations
48
Granite 4 2 30bibm-granite/granite-4.2-30b
DeepInfraglobal
openai chat completions
Fresh
$0.81for selected workload
no independent observations
49
Llama 4 Maverick 17b 128e Instruct fp8meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
DeepInfraglobal
openai chat completions
Fresh
$1.00for selected workload
no independent observations
50
Gemma 4 31b It Ultragoogle/gemma-4-31B-it-Ultra
DeepInfraglobal
openai chat completions
Fresh
$1.03for selected workload
no independent observations
51
Qwen3 6 35b A3bQwen/Qwen3.6-35B-A3B
DeepInfraglobal
openai chat completions
Fresh
$1.05for selected workload
no independent observations
52
Qwen3 Vl 235b A22b InstructQwen/Qwen3-VL-235B-A22B-Instruct
DeepInfraglobal
openai chat completions
Fresh
$1.08for selected workload
no independent observations
53
Qwen3 5 35b A3bQwen/Qwen3.5-35B-A3B
DeepInfraglobal
openai chat completions
Fresh
$1.14for selected workload
no independent observations
54
DeepSeek V3 0324deepseek-ai/DeepSeek-V3-0324
DeepInfraglobal
openai chat completions
Fresh
$1.14for selected workload
no independent observations
55
GPT OSS 120b Ultraopenai/gpt-oss-120b-Ultra
DeepInfraglobal
openai chat completions
Fresh
$1.15for selected workload
no independent observations
56
Qwen3 Next 80b A3b InstructQwen/Qwen3-Next-80B-A3B-Instruct
DeepInfraglobal
openai chat completions
Fresh
$1.19for selected workload
no independent observations
57
DeepSeek V3 1deepseek-ai/DeepSeek-V3.1
DeepInfraglobal
openai chat completions
Fresh
$1.20for selected workload
no independent observations
58
DeepSeek V3deepseek-ai/DeepSeek-V3
DeepInfraglobal
openai chat completions
Fresh
$1.21for selected workload
no independent observations
59
DeepSeek V3 1 Terminusdeepseek-ai/DeepSeek-V3.1-Terminus
DeepInfraglobal
openai chat completions
Fresh
$1.22for selected workload
no independent observations
60
Minimax M2 7MiniMaxAI/MiniMax-M2.7
DeepInfraglobal
openai chat completions
Fresh
$1.25for selected workload
no independent observations
61
Qwen3 Coder 480b A35b Instruct TurboQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
DeepInfraglobal
openai chat completions
Fresh
$1.30for selected workload
no independent observations
62
Step 3 7 Flashstepfun-ai/Step-3.7-Flash
DeepInfraglobal
openai chat completions
Fresh
$1.35for selected workload
no independent observations
63
Minimax M3MiniMaxAI/MiniMax-M3
DeepInfraglobal
openai chat completions
Fresh
$1.38for selected workload
no independent observations
64
Hermes 3 Llama 3 1 70bNousResearch/Hermes-3-Llama-3.1-70B
DeepInfraglobal
openai chat completions
Fresh
$1.40for selected workload
no independent observations
65
Muse Glimmer 30bmeta-models/Muse-Glimmer-30B
DeepInfraglobal
openai chat completions
Fresh
$1.50for selected workload
no independent observations
66
Inkling Smallthinkingmachines/Inkling-Small
DeepInfraglobal
openai chat completions
Fresh
$1.65for selected workload
no independent observations
67
L3 1 70b Euryale V2 2Sao10K/L3.1-70B-Euryale-v2.2
DeepInfraglobal
openai chat completions
Fresh
$1.70for selected workload
no independent observations
68
Gemini 3 1 Flash Litegoogle/gemini-3.1-flash-lite
DeepInfraglobal
openai chat completions
Fresh
$1.75for selected workload
no independent observations
69
DeepSeek V4 Flash Vision Expdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp
DeepInfraglobal
openai chat completions
Fresh
$1.76for selected workload
no independent observations
70
Hermes 3 Llama 3 1 405bNousResearch/Hermes-3-Llama-3.1-405B
DeepInfraglobal
openai chat completions
Fresh
$2.00for selected workload
no independent observations
71
Minimax M2 7 TurboMiniMaxAI/MiniMax-M2.7-Turbo
DeepInfraglobal
openai chat completions
Fresh
$2.08for selected workload
no independent observations
72
GLM 4 7zai-org/GLM-4.7
DeepInfraglobal
openai chat completions
Fresh
$2.15for selected workload
no independent observations
73
Seed 1 8ByteDance/Seed-1.8
DeepInfraglobal
openai chat completions
Fresh
$2.25for selected workload
no independent observations
74
GLM 4 6zai-org/GLM-4.6
DeepInfraglobal
openai chat completions
Fresh
$2.50for selected workload
no independent observations
75
Qwen3 235b A22b Thinking 2507Qwen/Qwen3-235B-A22B-Thinking-2507
DeepInfraglobal
openai chat completions
Fresh
$2.53for selected workload
no independent observations
76
DeepSeek R1 0528deepseek-ai/DeepSeek-R1-0528
DeepInfraglobal
openai chat completions
Fresh
$2.65for selected workload
no independent observations
77
GLM 5zai-org/GLM-5
DeepInfraglobal
openai chat completions
Fresh
$2.68for selected workload
no independent observations
78
Qwen3 5 122b A10bQwen/Qwen3.5-122B-A10B
DeepInfraglobal
openai chat completions
Fresh
$2.69for selected workload
no independent observations
79
Qwen3 8 27bQwen/Qwen3.8-27B
DeepInfraglobal
openai chat completions
Fresh
$2.70for selected workload
no independent observations
80
Kimi K2 5moonshotai/Kimi-K2.5
DeepInfraglobal
openai chat completions
Fresh
$2.70for selected workload
no independent observations
81
Nvidia Nemotron 3 Ultra 550b A55bnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
DeepInfraglobal
openai chat completions
Fresh
$2.70for selected workload
no independent observations
82
Gemini 2 5 Flashgoogle/gemini-2.5-flash
DeepInfraglobal
openai chat completions
Fresh
$2.80for selected workload
no independent observations
83
Qwen3 5 27bQwen/Qwen3.5-27B
DeepInfraglobal
openai chat completions
Fresh
$2.86for selected workload
no independent observations
84
GLM 5 2zai-org/GLM-5.2
DeepInfraglobal
openai chat completions
Fresh
$3.15for selected workload
no independent observations
85
Qwen3 5 397b A17bQwen/Qwen3.5-397B-A17B
DeepInfraglobal
openai chat completions
Fresh
$3.45for selected workload
no independent observations
86
Seed 2 0 CodeByteDance/Seed-2.0-code
DeepInfraglobal
openai chat completions
Fresh
$3.50for selected workload
no independent observations
87
Seed 2 0 ProByteDance/Seed-2.0-pro
DeepInfraglobal
openai chat completions
Fresh
$3.50for selected workload
no independent observations
88
Qwen3 6 27bQwen/Qwen3.6-27B
DeepInfraglobal
openai chat completions
Fresh
$3.52for selected workload
no independent observations
89
DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro
DeepInfraglobal
openai chat completions
Fresh
$3.90for selected workload
no independent observations
90
DeepSeek V4 Pro 0813deepseek-ai/DeepSeek-V4-Pro-0813
DeepInfraglobal
openai chat completions
Fresh
$3.90for selected workload
no independent observations
91
Mimo V2 5 ProXiaomiMiMo/MiMo-V2.5-Pro
DeepInfraglobal
openai chat completions
Fresh
$4.00for selected workload
no independent observations
92
Kimi K2 7 Codemoonshotai/Kimi-K2.7-Code
DeepInfraglobal
openai chat completions
Fresh
$4.08for selected workload
no independent observations
93
Kimi K2 6moonshotai/Kimi-K2.6
DeepInfraglobal
openai chat completions
Fresh
$4.25for selected workload
no independent observations
94
Gemini 3 7 Flashgoogle/gemini-3.7-flash
DeepInfraglobal
openai chat completions
Fresh
$4.50for selected workload
no independent observations
95
GLM 5 1zai-org/GLM-5.1
DeepInfraglobal
openai chat completions
Fresh
$4.55for selected workload
no independent observations
96
Inklingthinkingmachines/Inkling
DeepInfraglobal
openai chat completions
Fresh
$5.00for selected workload
no independent observations
97
GLM 5 3zai-org/GLM-5.3
DeepInfraglobal
openai chat completions
Fresh
$5.20for selected workload
no independent observations
98
Claude Haiku 4 5anthropic/claude-haiku-4-5
DeepInfraglobal
openai chat completions
Fresh
$6.00for selected workload
no independent observations
99
Qwen3 8 MaxQwen/Qwen3.8-Max
DeepInfraglobal
openai chat completions
Fresh
$6.601for selected workload
no independent observations
100
Qwen3 Max ThinkingQwen/Qwen3-Max-Thinking
DeepInfraglobal
openai chat completions
Fresh
$7.20for selected workload
no independent observations
DeepInfra · ComputeLlama