Deepinfra Model Pricing
137 models · input & output costs per 1M tokens · updated every 5 minutes
ModelContextInput / 1MOutput / 1MData
DeepSeek-V4.1-Flash-1017
text
1M
$0.1400
$0.4200
MEDIUM
DeepSeek-V4.1-Flash
text
1M
$0.1400
$0.4200
MEDIUM
meta-llama/Llama-4-Scout-17B-16E-Instruct
text
328K
$0.1000
$0.3000
MEDIUM
google/gemma-3-12b-it
text
131K
$0.0500
$0.1500
MEDIUM
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
text
131K
$0.4000
$0.4000
MEDIUM
deepseek-ai/DeepSeek-V3.1
text
164K
$0.2500
$0.9500
MEDIUM
Gryphe/MythoMax-L2-13b
text
4K
$0.4000
$0.4000
MEDIUM
mistralai/Mistral-Nemo-Instruct-2407
text
131K
$0.0190
$0.0300
MEDIUM
meta-llama/Llama-3.3-70B-Instruct-Turbo
text
131K
$0.1000
$0.3200
MEDIUM
NousResearch/Hermes-3-Llama-3.1-70B
text
131K
$0.7000
$0.7000
MEDIUM
deepseek-ai/DeepSeek-V3-0324
text
164K
$0.2400
$0.9000
MEDIUM
Sao10K/L3.1-70B-Euryale-v2.2
text
131K
$0.8500
$0.8500
MEDIUM
openai/gpt-oss-120b
text
131K
$0.0370
$0.1700
MEDIUM
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
text
131K
$0.0200
$0.0400
MEDIUM
google/gemma-3-4b-it
text
131K
$0.0500
$0.1000
MEDIUM
Qwen/Qwen3-Next-80B-A3B-Instruct
text
262K
$0.0900
$1.1000
MEDIUM
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
text
1M
$0.2000
$0.8000
MEDIUM
Qwen/Qwen2.5-72B-Instruct
text
33K
$0.3600
$0.4000
MEDIUM
openai/gpt-oss-20b
text
131K
$0.0300
$0.1400
MEDIUM
Qwen/Qwen3-32B
text
41K
$0.0800
$0.2800
MEDIUM
google/gemma-3-27b-it
text
131K
$0.0800
$0.1600
MEDIUM
Qwen/Qwen3-235B-A22B-Instruct-2507
text
262K
$0.0900
$0.5500
MEDIUM
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
text
262K
$0.3000
$1.0000
MEDIUM
Qwen/Qwen3-30B-A3B
text
41K
$0.1200
$0.5000
MEDIUM
NVIDIA-Nemotron-3.5-Lightning
text
262K
$0.0800
$0.2000
MEDIUM
Qwen/Qwen3-14B
text
41K
$0.1200
$0.2400
MEDIUM
deepseek-ai/DeepSeek-V3
text
164K
$0.3200
$0.8900
MEDIUM
Qwen3.8-Max
text
256K
$1.6500
$4.9510
MEDIUM
gemma-4-31B-it-turbo
text
262K
$0.0900
$0.3400
MEDIUM
Qwen3.6-27B
text
262K
$0.3200
$3.2000
MEDIUM
gemini-3.5-flash
text
1M
$1.5000
$9.0000
MEDIUM
Step-3.7-Flash
text
262K
$0.2000
$1.1500
MEDIUM
NVIDIA-Nemotron-3-Ultra-550B-A55B
text
262K
$0.5000
$2.2000
MEDIUM
gpt-oss-120b-Ultra
text
131K
$0.2000
$0.9500
MEDIUM
Qwen3.8-27B
text
262K
$0.4000
$3.0000
MEDIUM
Kimi-K2.5
text
262K
$0.4500
$2.2500
MEDIUM
Nemotron-3-Nano-30B-A3B
text
262K
$0.0500
$0.2000
MEDIUM
Inkling
text
524K
$0.9500
$4.0500
MEDIUM
claude-opus-4-8
text
1M
$5.0000
$25.0000
MEDIUM
MiMo-V2.5-Pro
text
1M
$1.0000
$3.0000
MEDIUM
claude-haiku-4-5
text
200K
$1.0000
$5.0000
MEDIUM
Kimi-K2.7-Code
text
262K
$0.6800
$3.4000
MEDIUM
Qwen3-VL-30B-A3B-Instruct
text
262K
$0.1500
$0.6000
MEDIUM
GLM-4.6
text
203K
$0.5000
$2.0000
MEDIUM
Kimi-K3
text
1M
$2.8500
$14.2500
MEDIUM
claude-opus-4-7
text
1M
$5.0000
$25.0000
MEDIUM
Seed-2.0-pro
text
256K
$0.5000
$3.0000
MEDIUM
gemma-4-31B-it
text
262K
$0.1300
$0.3800
MEDIUM
Qwen3.5-27B
text
262K
$0.2600
$2.6000
MEDIUM
Inkling-Small
text
524K
$0.4500
$1.2000
MEDIUM
Qwen3.5-9B
text
262K
$0.1000
$0.1500
MEDIUM
DeepSeek-V4-Flash-0731
text
1M
$0.0800
$0.1800
MEDIUM
Qwen3.5-397B-A17B
text
262K
$0.4500
$3.0000
MEDIUM
Seed-2.0-code
text
256K
$0.5000
$3.0000
MEDIUM
Qwen3.5-35B-A3B
text
262K
$0.1400
$1.0000
MEDIUM
Ling-3.0-flash
text
131K
$0.0600
$0.1800
MEDIUM
gpt-oss-120b-Turbo
text
131K
$0.1500
$0.6000
MEDIUM
Qwen3.6-35B-A3B
text
262K
$0.1000
$0.9500
MEDIUM
gemini-3.1-pro
text
1M
$2.0000
$12.0000
MEDIUM
gemini-3.7-flash
text
1M
$0.7500
$3.7500
MEDIUM
Nemotron-Content-Safety-3.5
text
131K
$0.2000
$0.2000
MEDIUM
MiniMax-M2.7-Turbo
text
197K
$0.3800
$1.7000
MEDIUM
DeepSeek-V4-Pro-0813
text
1M
$1.3000
$2.6000
MEDIUM
Qwen3.8-2.4T-A95B
text
262K
$2.0000
$6.0000
MEDIUM
gemma-4-E4B-it
text
131K
$0.0200
$0.1000
MEDIUM
GLM-5.1
text
203K
$1.0500
$3.5000
MEDIUM
Seed-2.0-mini
text
256K
$0.1000
$0.4000
MEDIUM
Hy3
text
262K
$0.1400
$0.5800
MEDIUM
DeepSeek-V4-Flash
text
1M
$0.0900
$0.1800
MEDIUM
NVIDIA-Nemotron-3-Super-120B-A12B
text
262K
$0.0850
$0.4000
MEDIUM
GLM-4.7-Flash
text
203K
$0.0600
$0.4000
MEDIUM
Qwen3-Max-Thinking
text
256K
$1.2000
$6.0000
MEDIUM
Kimi-K2.6
text
262K
$0.7500
$3.5000
MEDIUM
Qwen3-Max
text
256K
$1.2000
$6.0000
MEDIUM
Muse-Glimmer-30B
text
131K
$0.3000
$1.2000
MEDIUM
gemma-4-26B-A4B-it
text
262K
$0.0700
$0.3400
MEDIUM
Qwen3.5-122B-A10B
text
262K
$0.2900
$2.4000
MEDIUM
gemini-3.1-flash-lite
text
1M
$0.2500
$1.5000
MEDIUM
MiniMax-M2.7
text
197K
$0.2500
$1.0000
MEDIUM
claude-sonnet-4-6
text
1M
$3.0000
$15.0000
MEDIUM
GLM-4.7
text
203K
$0.4000
$1.7500
MEDIUM
DeepSeek-V4-Pro
text
1M
$1.3000
$2.6000
MEDIUM
claude-sonnet-5
text
1M
$2.0000
$10.0000
MEDIUM
GLM-5.2
text
1M
$0.7500
$2.4000
MEDIUM
MiniMax-M3
text
524K
$0.2800
$1.1000
MEDIUM
DeepSeek-V3.2
text
164K
$0.2600
$0.3800
MEDIUM
claude-opus-5
text
1M
$5.0000
$25.0000
MEDIUM
Qwen3-VL-235B-A22B-Instruct
text
262K
$0.2000
$0.8800
MEDIUM
Seed-1.8
text
256K
$0.2500
$2.0000
MEDIUM
MiMo-V2.5
text
262K
$0.4000
$2.0000
MEDIUM
Qwen3.7-Max
text
256K
$2.5000
$7.5000
MEDIUM
claude-fable-5
text
1M
$10.0000
$50.0000
MEDIUM
gemma-4-31B-it-Ultra
text
131K
$0.2700
$0.7600
MEDIUM
GLM-5
text
203K
$0.6000
$2.0800
MEDIUM
deepseek-ai/DeepSeek-R1
text
164K
$0.7000
$2.4000
MEDIUM
meta-llama/Meta-Llama-3-8B-Instruct
text
8K
$0.0300
$0.0600
MEDIUM
anthropic/claude-4-sonnet
text
200K
$3.3000
$16.5000
MEDIUM
anthropic/claude-4-opus
text
200K
$16.5000
$82.5000
MEDIUM
deepseek-ai/DeepSeek-R1-Turbo
text
41K
$1.0000
$3.0000
MEDIUM
moonshotai/Kimi-K2-Instruct-0905
text
262K
$0.5000
$2.0000
MEDIUM
mistralai/Mistral-Small-24B-Instruct-2501
text
33K
$0.0500
$0.0800
MEDIUM
google/gemini-2.5-pro
text
1M
$1.2500
$10.0000
MEDIUM
Qwen/Qwen3-235B-A22B
text
41K
$0.1800
$0.5400
MEDIUM
microsoft/WizardLM-2-8x22B
text
66K
$0.4800
$0.4800
MEDIUM
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
text
131K
$0.1000
$0.4000
MEDIUM
microsoft/phi-4
text
16K
$0.0700
$0.1400
MEDIUM
deepseek-ai/DeepSeek-R1-0528-Turbo
text
33K
$1.0000
$3.0000
MEDIUM
Sao10K/L3-8B-Lunaris-v1-Turbo
text
8K
$0.0400
$0.0500
MEDIUM
Qwen/Qwen2.5-VL-32B-Instruct
text
128K
$0.2000
$0.6000
MEDIUM
nvidia/NVIDIA-Nemotron-Nano-9B-v2
text
131K
$0.0400
$0.1600
MEDIUM
mistralai/Mistral-Small-3.2-24B-Instruct-2506
text
128K
$0.0750
$0.2000
MEDIUM
meta-llama/Llama-3.3-70B-Instruct
text
131K
$0.2300
$0.4000
MEDIUM
moonshotai/Kimi-K2-Instruct
text
131K
$0.5000
$2.0000
MEDIUM
nvidia/Llama-3.1-Nemotron-70B-Instruct
text
131K
$0.6000
$0.6000
MEDIUM
mistralai/Mixtral-8x7B-Instruct-v0.1
text
33K
$0.4000
$0.4000
MEDIUM
meta-llama/Llama-3.2-3B-Instruct
text
131K
$0.0200
$0.0200
MEDIUM
Sao10K/L3.3-70B-Euryale-v2.3
text
131K
$0.6500
$0.7500
MEDIUM
Qwen/Qwen3-Coder-480B-A35B-Instruct
text
262K
$0.4000
$1.6000
MEDIUM
google/gemini-2.0-flash-001
text
1M
$0.1000
$0.4000
LOW
meta-llama/Llama-3.2-11B-Vision-Instruct
text
131K
$0.0490
$0.0490
MEDIUM
Qwen/Qwen2.5-7B-Instruct
text
33K
$0.0400
$0.1000
MEDIUM
meta-llama/Llama-Guard-3-8B
text
131K
$0.0550
$0.0550
MEDIUM
deepseek-ai/DeepSeek-V3.1-Terminus
text
164K
$0.2700
$1.0000
MEDIUM
deepseek-ai/DeepSeek-R1-0528
text
164K
$0.5000
$2.1500
MEDIUM
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
text
131K
$0.2000
$0.6000
MEDIUM
NousResearch/Hermes-3-Llama-3.1-405B
text
131K
$1.0000
$1.0000
MEDIUM
Qwen/Qwen3-Next-80B-A3B-Thinking
text
262K
$0.1400
$1.4000
MEDIUM
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
text
131K
$0.2700
$0.2700
MEDIUM
zai-org/GLM-4.5
text
131K
$0.4000
$1.6000
MEDIUM
Qwen/QwQ-32B
text
131K
$0.1500
$0.4000
MEDIUM
Qwen/Qwen3-235B-A22B-Thinking-2507
text
262K
$0.3000
$2.9000
MEDIUM
meta-llama/Meta-Llama-3.1-8B-Instruct
text
131K
$0.0300
$0.0500
MEDIUM
meta-llama/Llama-Guard-4-12B
text
164K
$0.1800
$0.1800
MEDIUM
allenai/olmOCR-7B-0725-FP8
text
16K
$0.2700
$1.5000
MEDIUM
anthropic/claude-3-7-sonnet-latest
text
200K
$3.3000
$16.5000
MEDIUM
google/gemini-2.5-flash
text
1M
$0.3000
$2.5000
MEDIUM
meta-llama/Meta-Llama-3.1-70B-Instruct
text
131K
$0.4000
$0.4000
MEDIUM