DeepInfra

Price history

Blended ($/Mtok, 75% input / 25% output) price over time for every model this host serves. Click a legend entry to hide or show its line.

Hosted offerings

ModelVariantInput $/MtokOutput $/MtokConfidence
Llama 3.2 3B Instruct–$0.0200$0.0200medium
Llama 3.1 8B Instructfp8$0.0200$0.0400high
Meta-Llama-3.1-8B-Instruct-Turbo–$0.0200$0.0400high
Mistral Nemofp8$0.0290$0.0300high
Mistral-Nemo-Instruct-2407–$0.0290$0.0300high
meta-llama/Meta-Llama-3.1-8B-Instruct–$0.0300$0.0500medium
meta-llama/Meta-Llama-3-8B-Instruct–$0.0300$0.0600medium
Gemma 4 E4B IT–$0.0200$0.10medium
Llama 3 8B Lunarisfp8+turbo$0.0400$0.0500high
Sao10K/L3-8B-Lunaris-v1-Turbo–$0.0400$0.0500medium
gpt-oss-20bflex$0.0240$0.11high
Llama 3.2 11b Vision Instruct–$0.0490$0.0490medium
Gemma 3 4Bflex$0.0400$0.0800high
Qwen2.5 7B Instruct–$0.0400$0.10medium
llama-guard-3-8b–$0.0550$0.0550medium
gpt-oss-20b–$0.0300$0.14high
Mistral Small 3fp8$0.0500$0.0800high
Mistral Small 3–$0.0500$0.0800high
Gemma 3 12Bflex$0.0400$0.12high
Gemma 3 4B–$0.0500$0.10high
nvidia/NVIDIA-Nemotron-Nano-9B-v2–$0.0400$0.16medium
Phi-4flex$0.0560$0.11high
gpt-oss-120b–$0.0370$0.17high
DeepSeek-V4-Flash-0731flex+fp8$0.0480$0.14high
Gemma 3 12B–$0.0500$0.15high
Gemma 3 27Bflex+fp8$0.0640$0.13high
NVIDIA-Nemotron-3.5-Lightning–$0.0600$0.16high
Mistral Small 3.2 24Bflex+fp8$0.0600$0.16high
Phi-4–$0.0700$0.14high
Nemotron 3 Nano 30B A3B–$0.0500$0.20medium
Ling 3.0 Flash VL–$0.0600$0.18high
Ling 3.0 Flash Finfp4$0.0600$0.18high
Ling 3.0 Flash–$0.0600$0.18high
DeepSeek-V4-Flash-0731–$0.0600$0.18high
DeepSeek-V4-Flash-0731fp8$0.0600$0.18high
Ling 3.0 Flash VLfp4$0.0600$0.18high
Qwen3.5-9Bflex$0.0800$0.12high
Ling 3.0 Flashfp4$0.0600$0.18high
DeepSeek V4 Flashflex+fp8$0.0720$0.14high
Gemma 3 4Bpriority$0.0750$0.15high
Gemma 3 27Bfp8$0.0800$0.16high
Gemma 3 27B–$0.0800$0.16high
DeepSeek V4 Flash 0731–$0.0800$0.18medium
Mistral Small 3.2 24Bfp8$0.0750$0.20high
Mistral-Small-3.2-24B-Instruct-2506–$0.0750$0.20high
Granite 4.2 8B–$0.0600$0.25high
DeepSeek V4 Flashfp8$0.0900$0.18high
Qwen3.5-9B–$0.10$0.15high
DeepSeek V4 Flash–$0.0900$0.18medium
DeepSeek-V4-Flash–$0.0900$0.18high
Gemma 3 12Bpriority$0.0750$0.23high
Llama 4 Scoutflex+fp8$0.0800$0.24high
Qwen3 32Bfp8$0.0800$0.28high
Qwen3 32B–$0.0800$0.28high
DeepSeek-V4-Flash-0731fp8+priority$0.0900$0.27high
Gemma 4 26B A4B–$0.0700$0.34high
Llama Guard 4 12Bflex$0.14$0.14high
GLM 4.7 Flash–$0.0600$0.40medium
Qwen3 14Bfp8$0.12$0.24high
Llama 4 Scoutfp8$0.10$0.30high
Qwen3 14B–$0.12$0.24high
Llama 4 Scout–$0.10$0.30medium
Llama-4-Scout-17B-16E–$0.10$0.30high
Gemma 3 27Bfp8+priority$0.12$0.24high
gemma-4-31B-it-turbo–$0.0900$0.34high
Llama 3.3 70B Instructfp8+turbo$0.10$0.32high
Llama-3.3-70B-Instruct-Turbo–$0.10$0.32high
Nemotron 3 Super–$0.0750$0.40high
NVIDIA-Nemotron-3-Super-120B-A12B–$0.0750$0.40high
Mistral Small 3.2 24Bfp8+priority$0.11$0.30high
Qwen3 235B A22B Instruct 2507flex+fp8$0.0720$0.44high
Qwen3.5-9Bpriority$0.15$0.23high
DeepSeek V4 Flashfp8+priority$0.14$0.27high
MiMo-V2.6-Flashfp8$0.14$0.28high
Llama 3.3 Nemotron Super 49B v1–$0.10$0.40medium
ByteDance/Seed-2.0-mini–$0.10$0.40medium
MiMo-V2.6-Flash–$0.14$0.28medium
MiMo-V2.5–$0.14$0.28medium
Seed-2.0-Mini–$0.10$0.40medium
XiaomiMiMo/MiMo-V2.6-Flash–$0.14$0.28medium
Llama Guard 4 12B–$0.18$0.18high
Qwen3.8 Flash–$0.11$0.38high
Nemotron-Content-Safety-3.5–$0.20$0.20high
Qwen3 235B A22B Instruct 2507fp8$0.0900$0.55high
Qwen3 235B-A22B Instruct 2507–$0.0900$0.55high
DeepSeek V4.1 Flash–$0.14$0.42medium
QwQ 32B–$0.15$0.40medium
Qwen3 30B A3Bfp8$0.12$0.50high
Qwen3 30B A3B–$0.12$0.50high
Llama 4 Scoutfp8+priority$0.15$0.45high
GLM 5.3 Flashfp4$0.15$0.50high
GLM 5.3 Flash–$0.15$0.50high
Nemotron 3.5 Super VLfp4$0.15$0.50high
Nemotron 3.5 Super VL 120B A12B–$0.15$0.50high
DeepSeek V4.1 Flashflex+fp8$0.16$0.48high
DeepSeek V4.1 Flash 1017flex+fp8$0.16$0.48high
Hy3–$0.14$0.58medium
Gemma 4 31B–$0.20$0.40high
Qwen3 VL 30B A3B Instructfp8$0.15$0.60high
openai/gpt-oss-120b-Turbo–$0.15$0.60medium
Qwen3 VL 30B A3B Instruct–$0.15$0.60high
Qwen3-235B-A22B–$0.18$0.54medium
DeepSeek R1 Distill Qwen 32B–$0.27$0.27medium
Llama Guard 4 12Bpriority$0.27$0.27high
Llama 3.3 70B Instruct–$0.23$0.40medium
Qwen3 Next 80B A3B Instructflex+fp8$0.0720$0.88high
DeepSeek V3.2fp4$0.26$0.38high
DeepSeek V3.2–$0.26$0.38high
DeepSeek V4.1 Flashfp8$0.20$0.60high
Qwen/Qwen2.5-VL-32B-Instruct–$0.20$0.60medium
DeepSeek R1 Distill LLama 70B–$0.20$0.60medium
DeepSeek V4.1 Flash 1017fp8$0.20$0.60high
DeepSeek-V4.1-Flash-101751% off–$0.20$0.60high
DeepSeek-V4.1-Flash30% off–$0.20$0.60high
Qwen3 235B A22B Instruct 2507fp8+priority$0.14$0.83high
Qwen3.6 35B A3Bfp8$0.10$0.95high
Qwen3.6 35B A3B–$0.10$0.95high
Qwen3 Next 80B A3B Instructfp8$0.0900$1.10high
Qwen3 Next 80B A3B Instruct–$0.0900$1.10high
Llama 4 Maverick–$0.20$0.80medium
Nemotron 3 Nano Omni (free)–$0.20$0.80medium
Qwen3.5-35B-A3Bfp8$0.14$1.00high
Qwen3.5-35B-A3B–$0.14$1.00high
Qwen3 VL 235B A22B Instructfp8$0.20$0.88high
Qwen2.5 72B Instructfp8$0.36$0.40high
Qwen3 VL 235B A22B Instruct–$0.20$0.88high
DeepSeek V3.2 (chat)flex+fp4$0.26$0.71high
openai/gpt-oss-120b-Ultra–$0.20$0.95medium
MiniMax M3flex+fp8$0.22$0.88high
gemma-4-31B-it-Ultra–$0.27$0.76high
Llama 3.1 70B Instructfp8+turbo$0.40$0.40high
MythoMax 13B–$0.40$0.40high
Meta-Llama-3.1-70B-Instruct–$0.40$0.40medium
Meta-Llama-3.1-70B-Instruct-Turbo–$0.40$0.40high
mistralai/Mixtral-8x7B-Instruct-v0.1–$0.40$0.40medium
MiniMax M2.5–$0.15$1.15medium
DeepSeek V3 0324–$0.24$0.90medium
DeepSeek V3.1fp4$0.25$0.95high
DeepSeek V3.2 (chat)–$0.25$0.95medium
DeepSeek V3.1–$0.25$0.95high
MiniMax-M2.7–$0.25$1.00medium
Step 3.7 Flash–$0.20$1.15medium
Step 3.7 Flash–$0.20$1.15medium
DeepSeek V4.1 Flashfp8+priority$0.30$0.90high
DeepSeek V4.1 Flash 1017fp8+priority$0.30$0.90high
Ling 3.1 Flashfp4$0.30$0.90high
DeepSeek V3.1 Terminus–$0.27$1.00medium
Qwen3 Next 80B A3B Thinking–$0.14$1.40medium
DeepSeek V3.2 (chat)fp4$0.32$0.89high
DeepSeek-V3–$0.32$0.89high
Qwen3 Coder 480B A35Bfp4+turbo$0.30$1.00high
Qwen3-Coder-480B-A35B-Instruct-Turbo–$0.30$1.00high
Inkling 2 Small–$0.30$1.00medium
WizardLM-2 8x22B–$0.48$0.48medium
MiniMax M3fp8$0.28$1.10high
MiniMax-M3–$0.28$1.10medium
Qwen3 Next 80B A3B Instructfp8+priority$0.14$1.65high
Muse Glimmer 30B–$0.30$1.20high
meta-models/Muse-Glimmer-30B–$0.30$1.20medium
MiMo-V2.6-Profp8$0.43$0.87high
MiMo-V2.6-Pro–$0.43$0.87medium
Gemini 3.1 Flash Lite–$0.25$1.50high
allenai/olmOCR-7B-0725-FP8–$0.27$1.50medium
GLM 4.7flex+fp4$0.32$1.40high
Llama 3.1 Nemotron 70B Instruct–$0.60$0.60medium
Inkling Smallfp8$0.45$1.20high
Inkling Small–$0.45$1.20medium
Inkling Smallfp4$0.45$1.20high
DeepSeek V4 Flash Vision Expfp8$0.44$1.32high
DeepSeek V4 Flash Vision Exp–$0.44$1.32medium
DeepSeek-V4-Flash-Vision-Exp51% off–$0.44$1.32high
Sao10K/L3.3-70B-Euryale-v2.3–$0.65$0.75medium
ByteDance/Seed-1.8–$0.25$2.00medium
Hermes 3 70B Instructfp8$0.70$0.70high
Hermes 3 70B Instruct–$0.70$0.70medium
Qwen3-Coder-480B-A35B–$0.40$1.60medium
GLM 4.5–$0.40$1.60medium
GLM-4.6flex+fp4$0.40$1.60high
MiniMaxAI/MiniMax-M2.7-Turbo–$0.38$1.70medium
GLM 4.7fp4$0.40$1.75high
GLM 4.7–$0.40$1.75high
Qwen3.8 27B–$0.20$2.50high
Qwen3.8-27B25% off–$0.20$2.50high
xiaomimimo/mimo-v2.5–$0.40$2.00medium
Qwen3.5-122B-A10B–$0.29$2.40medium
Qwen3.5-27Bfp8$0.26$2.60high
Qwen3.5-27B–$0.26$2.60high
Llama 3.1 Euryale 70B v2.2fp8$0.85$0.85high
Sao10K/L3.1-70B-Euryale-v2.2–$0.85$0.85medium
Gemini 2.5 Flash–$0.30$2.50high
Qwen3.5 397B A17Bflex+fp8$0.36$2.40high
GLM-4.6fp4$0.50$2.00high
Kimi K2–$0.50$2.00medium
GLM-4.6–$0.50$2.00high
Kimi K2.5–$0.45$2.25medium
R1 0528fp4$0.50$2.15high
R1 0528–$0.50$2.15high
NVIDIA-Nemotron-3-Ultra-550B-A55B–$0.50$2.20high
GLM 5.2flex+fp4$0.60$1.92high
GLM 5–$0.60$2.08medium
Hermes 3 405B Instructfp8$1.00$1.00high
Hermes 3 405B Instruct–$1.00$1.00medium
Qwen3.6 27Bfp8$0.32$3.20high
Qwen3.6 27B–$0.32$3.20high
Qwen3.5 397B A17Bfp8$0.45$3.00high
Qwen3.5 397B A17B–$0.45$3.00high
DeepSeek V3.2 (reasoner)–$0.70$2.40medium
ByteDance/Seed-2.0-code–$0.50$3.00medium
Seed 2.0 Pro–$0.50$3.00medium
Seed-2.0-Code–$0.50$3.00medium
Kimi K2.6flex+fp4$0.60$2.80high
GLM 5.2fp4$0.75$2.40high
GLM 5.2–$0.75$2.40medium
GLM-5.225% off–$0.75$2.40high
Hy4 preview–$0.83$2.50medium
Hy4 previewfp4$0.83$2.50high
DeepSeek V4 Pro 0813flex+fp8$1.04$2.08high
DeepSeek V4 Proflex+fp8$1.04$2.08high
GLM 5.3flex+fp4$0.72$3.20high
Kimi K2.7 Code–$0.68$3.40medium
Nemotron 3 Ultrafp4+priority$0.75$3.30high
Step 5 Preview–$1.00$2.70medium
Kimi K2.6fp4$0.75$3.50high
Kimi K2.6–$0.75$3.50high
deepseek-ai/DeepSeek-R1-0528-Turbo–$1.00$3.00medium
DeepSeek R1 (Turbo)–$1.00$3.00medium
Gemini 3.7 Flash–$0.75$3.75high
xiaomimimo/mimo-v2.5-pro–$1.00$3.00medium
MiMo-V2.5-Pro–$1.00$3.00medium
DeepSeek V4 Pro 0813fp8$1.30$2.60high
DeepSeek V4 Profp8$1.30$2.60high
DeepSeek V4 Pro 0813–$1.30$2.60high
DeepSeek V4 Pro–$1.30$2.60medium
DeepSeek-V4-Pro–$1.30$2.60high
Qwen3.5 397B A17Bfp8+priority$0.68$4.50high
GLM 5.1–$1.05$3.50medium
GLM 5.3fp4$0.90$4.00high
GLM 5.3–$0.90$4.00medium
GLM-5.338% off–$0.90$4.00high
Inkling–$0.95$4.05medium
GLM 5.2fp4+priority$1.13$3.60high
Claude Haiku 4.5–$1.00$5.00high
claude-haiku-4-5–$1.00$5.00high
Qwen4 Max–$1.41$4.24high
Kimi K2.6fp4+priority$1.13$5.25high
Qwen3-Max–$1.20$6.00high
Qwen3 Max Thinking–$1.20$6.00high
DeepSeek V4 Pro 0813fp8+priority$1.95$3.90high
DeepSeek V4 Profp8+priority$1.95$3.90high
Qwen3.8 Max–$1.65$4.95high
Qwen3.8 2.4T A95B–$2.00$6.00medium
Gemini 3.5 Flash–$1.50$9.00high
Gemini 2.5 Pro–$1.25$10.00high
Qwen3.7 Max–$2.50$7.50high
Kimi K3.1 Pro–$2.00$10.00high
Kimi-K3.1-Pro5% off–$2.00$10.00high
Claude Sonnet 5.5–$2.00$10.00high
gemini-3.1-pro–$2.00$12.00high
Kimi K3–$2.85$14.25high
Kimi K3mxfp4$2.85$14.25high
Claude Sonnet 5–$3.00$15.00high
anthropic/claude-3-7-sonnet-latest–$3.30$16.50medium
anthropic/claude-4-sonnet–$3.30$16.50medium
Claude Opus 5.5–$4.00$20.00high
Claude Opus 5–$5.00$25.00high
Claude Fable 5–$10.00$50.00high
anthropic/claude-4-opus–$16.50$82.50medium
Qwen3-Coder 480B-A35B Instruct––––
gpt-oss-120bfp8–––