Skip to content
SF·SIX
SF·SIX / SOURCE-BACKED RESEARCH

DeepInfra Model and Price References

Browse 71 models with a current, dated DeepInfra price record, billing units and capabilities.

Checked · Source: OpenRouter · Methodology

DeepInfra API pricing: every model’s live price in one table

Models

GLM 5.3

Z.ai (Zhipu) · text

From $0.50 in / $1.51 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 45 current source-qualified records

DeepSeek V4.1 Flash

DeepSeek · text

From $0.09 in / $0.18 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 35 current source-qualified records

GLM 5.3 Flash

Z.ai (Zhipu) · text

From $0.075 in / $0.25 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 32 current source-qualified records

GLM 5.2

Z.ai (Zhipu) · text

From $0.189 in / $0.594 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 34 current source-qualified records

DeepSeek V4 Flash 0731

DeepSeek · text

From $0.0598 in / $0.1795 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 27 current source-qualified records

DeepSeek V4 Pro 0813

DeepSeek · text

From $0.1333 in / $0.40 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 23 current source-qualified records

gpt-oss-120b

OpenAI · text

From $0.03 in / $0.15 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 22 current source-qualified records

Qwen3.8 27B

Qwen (Alibaba) · text

From $0.02 in / $0.50 out per 1M tokens · observed 2026-10-17

1,000,000 context tokens · 19 current source-qualified records

Kimi K3

Moonshot AI · text

From $0.504 in / $8.10 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 23 current source-qualified records

Kimi K2.6

Moonshot AI · text

From $0.4323 in / $1.82 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 17 current source-qualified records

DeepSeek V4 Pro 0423

DeepSeek · text

From $0.1775 in / $0.3549 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 15 current source-qualified records

DeepSeek V4 Flash 0423

DeepSeek · text

From $0.0181 in / $0.0361 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 15 current source-qualified records

MiniMax M3

MiniMax · text

From $0.23 in / $0.96 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 14 current source-qualified records

Gemma 4 26B A4B

Google DeepMind · text

From $0.042 in / $0.22 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 12 current source-qualified records

DeepSeek V3.2

DeepSeek · text

From $0.2088 in / $0.3096 out per 1M tokens · observed 2026-10-17

163,840 context tokens · 12 current source-qualified records

Gemma 4 31B

Google DeepMind · text

From $0.10 in / $0.34 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 14 current source-qualified records

Qwen3.6 35B A3B

Qwen (Alibaba) · text

From $0.05 in / $0.70 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 10 current source-qualified records

gpt-oss-20b

OpenAI · text

From $0.018 in / $0.09 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 11 current source-qualified records

Llama 3.3 70B Instruct

Meta · text

From $0.135 in / $0.40 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 11 current source-qualified records

MiMo-V2.6-Flash

Xiaomi · text

From $0.10 in / $0.28 out per 1M tokens · observed 2026-10-17

1,050,000 context tokens · 7 current source-qualified records

Qwen3.6 27B

Qwen (Alibaba) · text

From $0.25 in / $2.00 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 7 current source-qualified records

Qwen3.5-35B-A3B

Qwen (Alibaba) · text

From $0.065 in / $0.75 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 7 current source-qualified records

Qwen3.5-27B

Qwen (Alibaba) · text

From $0.195 in / $1.56 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 7 current source-qualified records

GLM 4.7

Z.ai (Zhipu) · text

From $0.40 in / $1.75 out per 1M tokens · observed 2026-10-17

204,800 context tokens · 7 current source-qualified records

Qwen3 235B A22B Instruct 2507

Qwen (Alibaba) · text

From $0.0875 in / $0.35 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 6 current source-qualified records

Qwen3.5-9B

Qwen (Alibaba) · text

From $0.08 in / $0.13 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 5 current source-qualified records

Gemma 3 27B

Google DeepMind · text

From $0.08 in / $0.16 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 5 current source-qualified records

Llama 3.1 8B Instruct

Meta · text

From $0.02 in / $0.04 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 5 current source-qualified records

Mistral Nemo

Mistral AI · text

From $0.0166 in / $0.0216 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 5 current source-qualified records

Step 5 Preview

StepFun · text

From $1.00 in / $2.70 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 4 current source-qualified records

MiMo-V2.6-Pro

Xiaomi · text

From $0.43 in / $0.87 out per 1M tokens · observed 2026-10-17

1,050,000 context tokens · 4 current source-qualified records

Hy4 preview

Tencent · text

From $0.834 in / $2.50 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 4 current source-qualified records

Nemotron 3.5 Lightning

NVIDIA · text

From $0.025 in / $0.12 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 4 current source-qualified records

GLM 4.6

Z.ai (Zhipu) · text

From $0.43 in / $1.75 out per 1M tokens · observed 2026-10-17

204,800 context tokens · 5 current source-qualified records

DeepSeek V3.1

DeepSeek · text

From $0.25 in / $0.95 out per 1M tokens · observed 2026-10-17

163,840 context tokens · 4 current source-qualified records

Mistral Small 3.2 24B

Mistral AI · text

From $0.075 in / $0.20 out per 1M tokens · observed 2026-10-17

256,000 context tokens · 4 current source-qualified records

R1 0528

DeepSeek · text

From $0.50 in / $2.15 out per 1M tokens · observed 2026-10-17

163,840 context tokens · 4 current source-qualified records

DeepSeek V4.1 Flash 1017

DeepSeek · text

From $0.10 in / $0.50 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 5 current source-qualified records

Nemotron 3.5 Super VL

NVIDIA · text

From $0.10 in / $0.40 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 3 current source-qualified records

DeepSeek V4 Flash Vision Exp

DeepSeek · text

From $0.2156 in / $0.6468 out per 1M tokens · observed 2026-10-17

1,048,576 context tokens · 3 current source-qualified records

Nemotron 3 Ultra

NVIDIA · text

From $0.50 in / $2.20 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 5 current source-qualified records

Nemotron 3 Super

NVIDIA · text

From $0.085 in / $0.40 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 3 current source-qualified records

Qwen3 VL 235B A22B Instruct

Qwen (Alibaba) · text

From $0.20 in / $0.88 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 3 current source-qualified records

Qwen3 Next 80B A3B Instruct

Qwen (Alibaba) · text

From $0.09 in / $1.10 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 5 current source-qualified records

Qwen3 Coder 480B A35B

Qwen (Alibaba) · text

From $0.35 in / $1.50 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 3 current source-qualified records

Qwen3 32B

Qwen (Alibaba) · text

From $0.08 in / $0.28 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 3 current source-qualified records

MythoMax 13B

gryphe · text

From $0.08 in / $0.11 out per 1M tokens · observed 2026-10-17

8,192 context tokens · 3 current source-qualified records

Ling 3.1 Flash

inclusionAI · text

From $0.075 in / $0.225 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 2 current source-qualified records

Granite 4.2 8B

IBM Granite · text

From $0.06 in / $0.25 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 2 current source-qualified records

Muse Glimmer 30B

Meta · text

From $0.30 in / $1.20 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 2 current source-qualified records

Ling 3.0 Flash

inclusionAI · text

From $0.021 in / $0.063 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 2 current source-qualified records

Inkling

Thinking Machines · text

From $0.95 in / $4.05 out per 1M tokens · observed 2026-10-17

524,288 context tokens · 2 current source-qualified records

Qwen3 VL 30B A3B Instruct

Qwen (Alibaba) · text

From $0.15 in / $0.60 out per 1M tokens · observed 2026-10-17

262,144 context tokens · 2 current source-qualified records

Qwen3 14B

Qwen (Alibaba) · text

From $0.10 in / $0.22 out per 1M tokens · observed 2026-10-17

40,960 context tokens · 2 current source-qualified records

Llama 4 Scout

Meta · text

From $0.10 in / $0.30 out per 1M tokens · observed 2026-10-17

1,310,720 context tokens · 2 current source-qualified records

Gemma 3 4B

Google DeepMind · text

From $0.04 in / $0.05 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 2 current source-qualified records

Gemma 3 12B

Google DeepMind · text

From $0.05 in / $0.15 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 4 current source-qualified records

DeepSeek V3

DeepSeek · text

From $0.2574 in / $1.03 out per 1M tokens · observed 2026-10-17

163,840 context tokens · 2 current source-qualified records

Llama 3 8B Lunaris

Sao10K · text

From $0.04 in / $0.05 out per 1M tokens · observed 2026-10-17

8,192 context tokens · 2 current source-qualified records

Llama 3.1 70B Instruct

Meta · text

From $0.72 in / $0.72 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 2 current source-qualified records

Ling 3.0 Flash VL

inclusionAI · text

From $0.06 in / $0.18 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 1 current source-qualified record

Inkling Small

Thinking Machines · text

From $0.45 in / $1.20 out per 1M tokens · observed 2026-10-17

524,288 context tokens · 1 current source-qualified record

Nemotron 3.5 Content Safety

NVIDIA · text

From $0.20 in / $0.20 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 1 current source-qualified record

Llama Guard 4 12B

Meta · text

From $0.18 in / $0.18 out per 1M tokens · observed 2026-10-17

163,840 context tokens · 3 current source-qualified records

Qwen3 30B A3B

Qwen (Alibaba) · text

From $0.12 in / $0.50 out per 1M tokens · observed 2026-10-17

40,960 context tokens · 1 current source-qualified record

Mistral Small 3

Mistral AI · text

From $0.05 in / $0.08 out per 1M tokens · observed 2026-10-17

32,768 context tokens · 1 current source-qualified record

Phi 4

Microsoft · text

From $0.07 in / $0.14 out per 1M tokens · observed 2026-10-17

16,384 context tokens · 2 current source-qualified records

Qwen2.5 72B Instruct

Qwen (Alibaba) · text

From $0.36 in / $0.40 out per 1M tokens · observed 2026-10-17

32,768 context tokens · 1 current source-qualified record

Llama 3.1 Euryale 70B v2.2

Sao10K · text

From $0.85 in / $0.85 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 1 current source-qualified record

Hermes 3 70B Instruct

Nous Research · text

From $0.70 in / $0.70 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 1 current source-qualified record

Hermes 3 405B Instruct

Nous Research · text

From $1.00 in / $1.00 out per 1M tokens · observed 2026-10-17

131,072 context tokens · 1 current source-qualified record

75 community catalog references (unverified models.dev price records) are listed in the interactive model directory.

Listing does not imply endorsement, partnership or guaranteed availability. Verify provider terms at the cited source.