Skip to content
Reference

deepinfra model pricing

68 listings
All providers
Listings
68
Input $/1M
$0.02 – $16.50
Sources
litellm
Captured
2026-08-244 days ago

Reference data, captured and dated. These figures are what a source publishes, not a claim that Bayeto verified them, and they never enter a recommendation. The narrower, human-verified basis every uploaded workspace is priced against is on the catalog page.

68 listings

MakerHostRegionBasisCache readCache write
allenai/olmOCR-7B-0725-FP8deepinfra/allenai/olmOCR-7B-0725-FP8not in the model keyfiled as deepinfradeepinfravia litellmlisted16K$0.27$1.50··
anthropic/claude-3-7-sonnet-latestdeepinfra/anthropic/claude-3-7-sonnet-latestnot in the model keyfiled as deepinfradeepinfravia litellmlisted200K$3.30$16.50$0.33·
anthropic/claude-4-opusdeepinfra/anthropic/claude-4-opusnot in the model keyfiled as deepinfradeepinfravia litellmlisted200K$16.50$82.50··
anthropic/claude-4-sonnetdeepinfra/anthropic/claude-4-sonnetnot in the model keyfiled as deepinfradeepinfravia litellmlisted200K$3.30$16.50··
deepseek-ai/DeepSeek-R1deepinfra/deepseek-ai/DeepSeek-R1not in the model keyfiled as deepinfradeepinfravia litellmlisted164K$0.70$2.40··
deepseek-ai/DeepSeek-R1-0528deepinfra/deepseek-ai/DeepSeek-R1-0528not in the model keyfiled as deepinfradeepinfravia litellmlisted164K$0.50$2.15$0.40·
deepseek-ai/DeepSeek-R1-0528-Turbodeepinfra/deepseek-ai/DeepSeek-R1-0528-Turbonot in the model keyfiled as deepinfradeepinfravia litellmlisted33K$1.00$3.00··
deepseek-ai/DeepSeek-R1-Distill-Llama-70Bdeepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.20$0.60··
deepseek-ai/DeepSeek-R1-Distill-Qwen-32Bdeepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.27$0.27··
deepseek-ai/DeepSeek-R1-Turbodeepinfra/deepseek-ai/DeepSeek-R1-Turbonot in the model keyfiled as deepinfradeepinfravia litellmlisted41K$1.00$3.00··
deepseek-ai/DeepSeek-V3deepinfra/deepseek-ai/DeepSeek-V3not in the model keyfiled as deepinfradeepinfravia litellmlisted164K$0.38$0.89··
deepseek-ai/DeepSeek-V3-0324deepinfra/deepseek-ai/DeepSeek-V3-0324not in the model keyfiled as deepinfradeepinfravia litellmlisted164K$0.25$0.88··
deepseek-ai/DeepSeek-V3.1deepinfra/deepseek-ai/DeepSeek-V3.1not in the model keyfiled as deepinfradeepinfravia litellmlisted164K$0.27$1.00$0.216·
deepseek-ai/DeepSeek-V3.1-Terminusdeepinfra/deepseek-ai/DeepSeek-V3.1-Terminusnot in the model keyfiled as deepinfradeepinfravia litellmlisted164K$0.27$1.00$0.216·
google/gemini-2.0-flash-001deepinfra/google/gemini-2.0-flash-001not in the model keyfiled as deepinfradeepinfravia litellmlisted1M$0.10$0.40··
google/gemini-2.5-flashdeepinfra/google/gemini-2.5-flashnot in the model keyfiled as deepinfradeepinfravia litellmlisted1M$0.30$2.50··
google/gemini-2.5-prodeepinfra/google/gemini-2.5-pronot in the model keyfiled as deepinfradeepinfravia litellmlisted1M$1.25$10.00··
google/gemma-3-12b-itdeepinfra/google/gemma-3-12b-itnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.05$0.10··
google/gemma-3-27b-itdeepinfra/google/gemma-3-27b-itnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.09$0.16··
google/gemma-3-4b-itdeepinfra/google/gemma-3-4b-itnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.04$0.08··
Gryphe/MythoMax-L2-13bdeepinfra/Gryphe/MythoMax-L2-13bnot in the model keyfiled as deepinfradeepinfravia litellmlisted4K$0.08$0.09··
meta-llama/Llama-3.2-11B-Vision-Instructdeepinfra/meta-llama/Llama-3.2-11B-Vision-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.049$0.049··
meta-llama/Llama-3.2-3B-Instructdeepinfra/meta-llama/Llama-3.2-3B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.02$0.02··
meta-llama/Llama-3.3-70B-Instructdeepinfra/meta-llama/Llama-3.3-70B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.23$0.40··
meta-llama/Llama-3.3-70B-Instruct-Turbodeepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbonot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.13$0.39··
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8not in the model keyfiled as deepinfradeepinfravia litellmlisted1M$0.15$0.60··
meta-llama/Llama-4-Scout-17B-16E-Instructdeepinfra/meta-llama/Llama-4-Scout-17B-16E-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted328K$0.08$0.30··
meta-llama/Llama-Guard-3-8Bdeepinfra/meta-llama/Llama-Guard-3-8Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.055$0.055··
meta-llama/Llama-Guard-4-12Bdeepinfra/meta-llama/Llama-Guard-4-12Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted164K$0.18$0.18··
meta-llama/Meta-Llama-3-8B-Instructdeepinfra/meta-llama/Meta-Llama-3-8B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted8K$0.03$0.06··
meta-llama/Meta-Llama-3.1-70B-Instructdeepinfra/meta-llama/Meta-Llama-3.1-70B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.40$0.40··
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbodeepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbonot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.10$0.28··
meta-llama/Meta-Llama-3.1-8B-Instructdeepinfra/meta-llama/Meta-Llama-3.1-8B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.03$0.05··
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbodeepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbonot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.02$0.03··
microsoft/phi-4deepinfra/microsoft/phi-4not in the model keyfiled as deepinfradeepinfravia litellmlisted16K$0.07$0.14··
microsoft/WizardLM-2-8x22Bdeepinfra/microsoft/WizardLM-2-8x22Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted66K$0.48$0.48··
mistralai/Mistral-Nemo-Instruct-2407deepinfra/mistralai/Mistral-Nemo-Instruct-2407not in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.02$0.04··
mistralai/Mistral-Small-24B-Instruct-2501deepinfra/mistralai/Mistral-Small-24B-Instruct-2501not in the model keyfiled as deepinfradeepinfravia litellmlisted33K$0.05$0.08··
mistralai/Mistral-Small-3.2-24B-Instruct-2506deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506not in the model keyfiled as deepinfradeepinfravia litellmlisted128K$0.075$0.20··
mistralai/Mixtral-8x7B-Instruct-v0.1deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1not in the model keyfiled as deepinfradeepinfravia litellmlisted33K$0.40$0.40··
moonshotai/Kimi-K2-Instructdeepinfra/moonshotai/Kimi-K2-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.50$2.00··
moonshotai/Kimi-K2-Instruct-0905deepinfra/moonshotai/Kimi-K2-Instruct-0905not in the model keyfiled as deepinfradeepinfravia litellmlisted262K$0.50$2.00$0.40·
NousResearch/Hermes-3-Llama-3.1-405Bdeepinfra/NousResearch/Hermes-3-Llama-3.1-405Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$1.00$1.00··
NousResearch/Hermes-3-Llama-3.1-70Bdeepinfra/NousResearch/Hermes-3-Llama-3.1-70Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.30$0.30··
nvidia/Llama-3.1-Nemotron-70B-Instructdeepinfra/nvidia/Llama-3.1-Nemotron-70B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.60$0.60··
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5not in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.10$0.40··
nvidia/NVIDIA-Nemotron-3.5-Lightningdeepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightningnot in the model keyfiled as deepinfradeepinfravia litellmlisted262K$0.05$0.20··
nvidia/NVIDIA-Nemotron-Nano-9B-v2deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2not in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.04$0.16··
openai/gpt-oss-120bdeepinfra/openai/gpt-oss-120bnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.05$0.45··
openai/gpt-oss-20bdeepinfra/openai/gpt-oss-20bnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.04$0.15··
Qwen/Qwen2.5-72B-Instructdeepinfra/Qwen/Qwen2.5-72B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted33K$0.12$0.39··
Qwen/Qwen2.5-7B-Instructdeepinfra/Qwen/Qwen2.5-7B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted33K$0.04$0.10··
Qwen/Qwen2.5-VL-32B-Instructdeepinfra/Qwen/Qwen2.5-VL-32B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted128K$0.20$0.60··
Qwen/Qwen3-14Bdeepinfra/Qwen/Qwen3-14Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted41K$0.06$0.24··
Qwen/Qwen3-235B-A22Bdeepinfra/Qwen/Qwen3-235B-A22Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted41K$0.18$0.54··
Qwen/Qwen3-235B-A22B-Instruct-2507deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507not in the model keyfiled as deepinfradeepinfravia litellmlisted262K$0.09$0.60··
Qwen/Qwen3-235B-A22B-Thinking-2507deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507not in the model keyfiled as deepinfradeepinfravia litellmlisted262K$0.30$2.90··
Qwen/Qwen3-30B-A3Bdeepinfra/Qwen/Qwen3-30B-A3Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted41K$0.08$0.29··
Qwen/Qwen3-32Bdeepinfra/Qwen/Qwen3-32Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted41K$0.10$0.28··
Qwen/Qwen3-Coder-480B-A35B-Instructdeepinfra/Qwen/Qwen3-Coder-480B-A35B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted262K$0.40$1.60··
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbodeepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbonot in the model keyfiled as deepinfradeepinfravia litellmlisted262K$0.29$1.20··
Qwen/Qwen3-Next-80B-A3B-Instructdeepinfra/Qwen/Qwen3-Next-80B-A3B-Instructnot in the model keyfiled as deepinfradeepinfravia litellmlisted262K$0.14$1.40··
Qwen/Qwen3-Next-80B-A3B-Thinkingdeepinfra/Qwen/Qwen3-Next-80B-A3B-Thinkingnot in the model keyfiled as deepinfradeepinfravia litellmlisted262K$0.14$1.40··
Qwen/QwQ-32Bdeepinfra/Qwen/QwQ-32Bnot in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.15$0.40··
Sao10K/L3-8B-Lunaris-v1-Turbodeepinfra/Sao10K/L3-8B-Lunaris-v1-Turbonot in the model keyfiled as deepinfradeepinfravia litellmlisted8K$0.04$0.05··
Sao10K/L3.1-70B-Euryale-v2.2deepinfra/Sao10K/L3.1-70B-Euryale-v2.2not in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.65$0.75··
Sao10K/L3.3-70B-Euryale-v2.3deepinfra/Sao10K/L3.3-70B-Euryale-v2.3not in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.65$0.75··
zai-org/GLM-4.5deepinfra/zai-org/GLM-4.5not in the model keyfiled as deepinfradeepinfravia litellmlisted131K$0.40$1.60··
© 2026 Bayeto