Skip to content
OneAtlas

Deep Infra

Docs @ai-sdk/deepinfraDEEPINFRA_API_KEY
77
Models
16
Labs

Models on this provider

USD per 1M tokens

ModelProvider model IDContextOutputInput $Output $Cache readCache writeReasoningToolsStructuredUpdated
DeepSeek V4.1 Flash 1017DeepSeekdeepseek-ai/DeepSeek-V4.1-Flash-10171.05M384K$0.20$0.60$0.006—YesYesYesOct 17, 2026
MiMo-V2.6-FlashXiaomiXiaomiMiMo/MiMo-V2.6-Flash1.05M131K$0.14$0.28$0.0028—YesYesYesSep 22, 2026
MiMo-V2.6-ProXiaomiXiaomiMiMo/MiMo-V2.6-Pro1.05M131K$0.43$0.87$0.0036—YesYesYesSep 22, 2026
Step 5 PreviewStepFun (China)stepfun-ai/Step-5-Preview1.05M1M$1.00$2.70$0.10—YesYesYesSep 20, 2026
DeepSeek V4.1 FlashDeepSeekdeepseek-ai/DeepSeek-V4.1-Flash1.05M384K$0.20$0.60$0.006—YesYesYesSep 10, 2026
DeepSeek V4 Flash Vision ExpDeepSeekdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp1.05M384K$0.44$1.32$0.01—YesYesYesSep 1, 2026
Hy4 previewTencenttencent/Hy4-preview1.05M64K$0.83$2.50$0.04—YesYesYesAug 28, 2026
GLM-5.3-FlashZhipu AIzai-org/GLM-5.3-Flash1.05M131K$0.15$0.50$0.03—YesYesYesAug 26, 2026
Qwen3.8 FlashAlibabaQwen/Qwen3.8-Flash1M131K$0.11$0.38$0.01—NoYesYesAug 26, 2026
DeepSeek V4 Pro 0813DeepSeekdeepseek-ai/DeepSeek-V4-Pro-08131.05M384K$1.30$2.60$0.10—YesYesYesAug 22, 2026
GLM-5.3Zhipu AIzai-org/GLM-5.31.05M131K$0.90$4.00$0.20—YesYesYesAug 14, 2026
Qwen3.8 27BAlibabaQwen/Qwen3.8-27B262K33K$0.20$2.50$0.05—YesYesYesAug 14, 2026
Qwen3.8 2.4T A95BAlibabaQwen/Qwen3.8-2.4T-A95B262K131K$2.00$6.00$0.20—YesYesYesAug 12, 2026
Qwen3.8 MaxAlibabaQwen/Qwen3.8-Max256K131K$1.65$4.95$0.21—NoYesYesAug 3, 2026
DeepSeek V4 Flash 0731DeepSeekdeepseek-ai/DeepSeek-V4-Flash-07311.05M384K$0.06$0.18$0.01—YesYesYesJul 31, 2026
Inkling SmallThinking Machinesthinkingmachines/Inkling-Small524K1.05M$0.45$1.20$0.10—YesYesYesJul 30, 2026
Kimi K3Moonshot AImoonshotai/Kimi-K31.05M131K$2.85$14.25$0.28$3.56YesYesYesJul 16, 2026
InklingThinking Machinesthinkingmachines/Inkling524K1.05M$0.95$4.05$0.16—YesYesYesJul 15, 2026
Hy3Tencenttencent/Hy3262K128K$0.13$0.53$0.03—YesYesYesJul 6, 2026
GLM-5.2Zhipu AIzai-org/GLM-5.21.05M33K$0.75$2.40$0.14$0.94YesYesYesJun 13, 2026
Kimi K2.7 CodeMoonshot AImoonshotai/Kimi-K2.7-Code262K262K$0.68$3.40$0.14$0.85YesYesYesJun 12, 2026
Claude Fable 5Anthropicanthropic/claude-fable-51M128K$10.00$50.00——YesYesYesJun 9, 2026
MiniMax-M3MiniMaxMiniMaxAI/MiniMax-M3524K512K$0.28$1.10$0.06—YesYesYesJun 1, 2026
Step 3.7 FlashStepFun (China)stepfun-ai/Step-3.7-Flash262K256K$0.20$1.15$0.04—YesYesUnknownMay 29, 2026
Qwen3.7 MaxAlibabaQwen/Qwen3.7-Max256K131K$2.50$7.50$0.50—NoYesYesMay 21, 2026
Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIAnvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning262K66K$0.20$0.80——YesYesYesApr 28, 2026
DeepSeek V4 FlashDeepSeekdeepseek-ai/DeepSeek-V4-Flash1.05M16K$0.09$0.18$0.02$0.11YesYesYesApr 24, 2026
DeepSeek V4 ProDeepSeekdeepseek-ai/DeepSeek-V4-Pro1.05M16K$1.30$2.60$0.10—YesYesYesApr 24, 2026
MiMo-V2.5XiaomiXiaomiMiMo/MiMo-V2.5262K16K$0.14$0.28$0.0028—YesYesYesApr 22, 2026
MiMo-V2.5-ProXiaomiXiaomiMiMo/MiMo-V2.5-Pro1.05M16K$1.00$3.00$0.20—YesYesYesApr 22, 2026
Qwen3.6 27BAlibabaQwen/Qwen3.6-27B262K66K$0.32$3.20——YesYesYesApr 22, 2026
Kimi K2.6Moonshot AImoonshotai/Kimi-K2.6262K16K$0.75$3.50$0.15—YesYesYesApr 20, 2026
Qwen3.6 35B-A3BAlibabaQwen/Qwen3.6-35B-A3B262K82K$0.10$0.95$0.10—YesYesYesApr 17, 2026
GLM-5.1Zhipu AIzai-org/GLM-5.1203K16K$1.05$3.50$0.20—YesYesYesApr 7, 2026
Gemma 4 26B A4B ITGooglegoogle/gemma-4-26B-A4B-it262K33K$0.07$0.34——YesYesYesApr 2, 2026
Gemma 4 31B ITGooglegoogle/gemma-4-31B-it262K33K$0.20$0.40——YesYesYesApr 2, 2026
Gemma 4 E4B Instruct (IQ4_XS)Googlegoogle/gemma-4-E4B-it131K8K$0.02$0.10——YesYesYesApr 2, 2026
MiniMax-M2.7MiniMaxMiniMaxAI/MiniMax-M2.7197K131K$0.25$1.00$0.05—YesYesUnknownMar 18, 2026
Qwen3.5 122B-A10BAlibabaQwen/Qwen3.5-122B-A10B262K66K$0.29$2.40——YesYesYesFeb 23, 2026
Qwen3.5 27BAlibabaQwen/Qwen3.5-27B262K66K$0.26$2.60——YesYesYesFeb 23, 2026
Qwen3.5 35B-A3BAlibabaQwen/Qwen3.5-35B-A3B262K82K$0.14$1.00$0.05—YesYesYesFeb 23, 2026
Qwen3.5 9BAlibabaQwen/Qwen3.5-9B262K66K$0.10$0.15——YesYesYesFeb 23, 2026
Qwen3.5 397B-A17BAlibabaQwen/Qwen3.5-397B-A17B262K82K$0.45$3.00$0.22—YesYesYesFeb 15, 2026
Seed 2.0 CodeByteDance SeedByteDance/Seed-2.0-code256K131K$0.50$3.00$0.10—YesYesYesFeb 14, 2026
Seed 2.0 MiniByteDance SeedByteDance/Seed-2.0-mini256K32K$0.10$0.40$0.02—YesYesYesFeb 14, 2026
Seed 2.0 ProByteDance SeedByteDance/Seed-2.0-pro256K128K$0.50$3.00$0.10—YesYesYesFeb 14, 2026
GLM-5Zhipu AIzai-org/GLM-5203K16K$0.60$2.08$0.12—YesYesYesFeb 12, 2026
MiniMax-M2.5MiniMaxMiniMaxAI/MiniMax-M2.5197K131K$0.15$1.15$0.03—YesYesUnknownFeb 12, 2026
Kimi K2.5Moonshot AImoonshotai/Kimi-K2.5262K33K$0.45$2.25$0.07—YesYesYesJan 27, 2026
GLM-4.7-FlashZhipu AIzai-org/GLM-4.7-Flash203K16K$0.06$0.40$0.01—YesYesYesJan 19, 2026
GLM-4.7Zhipu AIzai-org/GLM-4.7203K16K$0.40$1.75$0.08—YesYesYesDec 22, 2025
Nemotron 3 Nano 30B A3BNVIDIAnvidia/Nemotron-3-Nano-30B-A3B262K262K$0.05$0.20$0.03—YesYesUnknownDec 15, 2025
DeepSeek V3.2DeepSeekdeepseek-ai/DeepSeek-V3.2164K64K$0.26$0.38$0.13—YesYesYesDec 1, 2025
Qwen3 VL 30B A3B InstructAlibabaQwen/Qwen3-VL-30B-A3B-Instruct262K33K$0.15$0.60——NoYesYesOct 4, 2025
GLM-4.6Zhipu AIzai-org/GLM-4.6203K131K$0.50$2.00$0.10—YesYesYesSep 30, 2025
Qwen3 MaxAlibabaQwen/Qwen3-Max256K66K$1.20$6.00$0.24—NoYesYesSep 23, 2025
Qwen3 VL 235B A22B InstructAlibabaQwen/Qwen3-VL-235B-A22B-Instruct262K33K$0.20$0.88$0.11—NoYesYesSep 23, 2025
Qwen3-Next 80B-A3B InstructAlibabaQwen/Qwen3-Next-80B-A3B-Instruct262K33K$0.09$1.10——NoYesYesSep 2025
DeepSeek V3.1DeepSeekdeepseek-ai/DeepSeek-V3.1164K8K$0.25$0.95$0.13—YesYesYesAug 21, 2025
GPT OSS 120BOpenAIopenai/gpt-oss-120b131K16K$0.04$0.17——YesYesYesAug 5, 2025
GPT OSS 20BOpenAIopenai/gpt-oss-20b131K16K$0.03$0.14——YesYesYesAug 5, 2025
Llama 3.3 Nemotron Super 49B v1.5NVIDIAnvidia/Llama-3.3-Nemotron-Super-49B-v1.5131K131K$0.40$0.40——YesYesYesJul 25, 2025
Qwen3 Coder 480B A35B InstructAlibabaQwen/Qwen3-Coder-480B-A35B-Instruct-Turbo262K67K$0.30$1.00$0.10—NoYesYesJul 22, 2025
Qwen3 235B A22B Instruct 2507AlibabaQwen/Qwen3-235B-A22B-Instruct-2507262K16K$0.09$0.55——NoYesYesJul 21, 2025
DeepSeek R1 0528DeepSeekdeepseek-ai/DeepSeek-R1-0528164K64K$0.50$2.15$0.35—YesYesYesMay 28, 2025
Llama Guard 4 12BMetameta-llama/Llama-Guard-4-12B164K164K$0.18$0.18——NoNoUnknownApr 29, 2025
Qwen3 30B A3BAlibabaQwen/Qwen3-30B-A3B41K16K$0.12$0.50——YesYesYesApr 28, 2025
Qwen3 32BAlibabaQwen/Qwen3-32B41K16K$0.08$0.28——YesYesYesApr 28, 2025
Llama 4 Maverick 17B InstructMetameta-llama/Llama-4-Maverick-17B-128E-Instruct-FP81.05M16K$0.20$0.80——NoNoYesApr 5, 2025
Llama 4 Scout 17B InstructMetameta-llama/Llama-4-Scout-17B-16E-Instruct328K16K$0.10$0.30——NoYesYesApr 5, 2025
DeepSeek V3 0324DeepSeekdeepseek-ai/DeepSeek-V3-0324164K164K$0.24$0.90$0.14—NoYesYesMar 24, 2025
Gemma 3 12B ITGooglegoogle/gemma-3-12b-it131K131K$0.05$0.15——NoYesYesMar 12, 2025
Gemma 3 27B ITGooglegoogle/gemma-3-27b-it131K131K$0.08$0.16——NoYesYesMar 12, 2025
Gemma 3 4B ITGooglegoogle/gemma-3-4b-it131K131K$0.05$0.10——NoYesYesMar 12, 2025
Mistral Small 3Mistralmistralai/Mistral-Small-24B-Instruct-250133K16K$0.05$0.08——NoNoYesJan 30, 2025
DeepSeek-V3DeepSeekdeepseek-ai/DeepSeek-V3164K8K$0.32$0.89——NoYesYesDec 26, 2024
Llama-3.3-70B-InstructMetameta-llama/Llama-3.3-70B-Instruct-Turbo131K16K$0.10$0.32——NoYesYesDec 6, 2024