Providers/DeepInfra

DeepInfra

Cloud platform · docs.litellm.ai

DeepInfra models via API.

Models
135
Endpoints
4
Regions
0
Avg input
$0.79
Auth
API key
SDKs
0

Endpoints

POST/v1/chat/completionsCompletionsStream
POST/v1/messagesMessagesStream
POST/v1/moderationsModerations-
POST/v1/responsesResponsesStream

Models · 135

ModelContextInputOutputCapabilities
Qwen3.8-27BOpen262K$0.40$3.00ReasoningVisionToolsgemini-3.7-flash1M$0.75$3.75ReasoningVisionToolsDeepSeek-V4-Pro-0813Open1.0M$1.30$2.60ToolsJSONQwen3.8-2.4T-A95BOpen262K$2.00$6.00ReasoningToolsJSONSeed-2.0-code256K$0.50$3.00ReasoningVisionToolsMuse-Glimmer-30BOpen131K$0.30$1.20ReasoningVisionToolsDeepSeek-V4-Flash-0731Open1.0M$0.08$0.18ReasoningToolsJSONInkling-SmallOpen524K$0.45$1.20ReasoningVisionToolsclaude-opus-51M$5.00$25.00ReasoningVisionToolsLing-3.0-flashOpen131K$0.06$0.18ReasoningToolsJSONInklingOpen524K$0.95$4.05ReasoningVisionToolsKimi-K3Open1.0M$2.85$14.25VisionToolsJSONHy3Open262K$0.14$0.58ReasoningToolsJSONclaude-sonnet-51M$2.00$10.00ReasoningVisionToolsGLM-5.2Open1.0M$0.75$2.40ReasoningToolsJSONKimi-K2.7-CodeOpen262K$0.68$3.40ReasoningVisionToolsclaude-fable-51M$10.00$50.00ReasoningVisionToolsMiniMax-M3Open524K$0.28$1.10ReasoningVisionToolsStep-3.7-FlashOpen262K$0.20$1.15VisionToolsclaude-opus-4-81M$5.00$25.00ReasoningVisionToolsQwen3.7-MaxOpen256K$2.50$7.50ToolsJSONgemini-3.5-flash1M$1.50$9.00ReasoningVisionToolsgemini-3.1-flash-lite1M$0.25$1.50ReasoningVisionToolsQwen3.6-27BOpen262K$0.32$3.20ReasoningVisionToolsQwen3.6-35B-A3BOpen262K$0.10$0.95ReasoningVisionToolsDeepSeek-V4-FlashOpen1.0M$0.09$0.18ReasoningToolsJSONDeepSeek-V4-ProOpen1.0M$1.30$2.60ToolsJSONMiMo-V2.5Open262K$0.40$2.00ReasoningVisionToolsMiMo-V2.5-ProOpen1.0M$1.00$3.00ReasoningToolsJSONKimi-K2.6Open262K$0.75$3.50ReasoningVisionToolsclaude-opus-4-71M$5.00$25.00ReasoningVisionToolsGLM-5.1Open203K$1.05$3.50ReasoningToolsJSONgemma-4-26B-A4B-itOpen262K$0.07$0.34ReasoningVisionToolsgemma-4-31B-itOpen262K$0.13$0.38ReasoningVisionToolsMiniMax-M2.7Open197K$0.25$1.00ReasoningToolsJSONQwen3.5-9BOpen262K$0.10$0.15VisionToolsJSONSeed-2.0-mini256K$0.10$0.40ReasoningVisionToolsQwen3.5-122B-A10BOpen262K$0.29$2.40ReasoningVisionToolsQwen3.5-27BOpen262K$0.26$2.60ReasoningVisionToolsQwen3.5-35B-A3BOpen262K$0.14$1.00ReasoningVisionToolsclaude-sonnet-4-61M$3.00$15.00ReasoningVisionToolsQwen3.5-397B-A17BOpen262K$0.45$3.00ReasoningVisionToolsGLM-5Open203K$0.60$2.08ReasoningToolsJSONQwen3-Max-ThinkingOpen256K$1.20$6.00ToolsJSONKimi-K2.5Open262K$0.45$2.25ReasoningVisionToolsGLM-4.7-FlashOpen203K$0.06$0.40ReasoningToolsJSONGLM-4.7Open203K$0.40$1.75ReasoningToolsJSONNemotron-3-Nano-30B-A3BOpen262K$0.05$0.20ReasoningToolsDeepSeek-V3.2Open164K$0.26$0.38ToolsJSONclaude-haiku-4-5200K$1.00$5.00ReasoningVisionToolsQwen3-VL-30B-A3B-InstructOpen262K$0.15$0.60VisionToolsJSONGLM-4.6Open203K$0.50$2.00ReasoningToolsJSONQwen3-MaxOpen256K$1.20$6.00ToolsJSONQwen3-VL-235B-A22B-InstructOpen262K$0.20$0.88VisionToolsJSONDeepSeek-V3.1-TerminusOpen164K$0.27$1.00ToolsQwen3-Next-80B-A3B-InstructOpen262K$0.09$1.10ToolsQwen3-Next-80B-A3B-ThinkingOpen262K$0.14$1.40Toolsgpt-oss-120bOpen131K$0.04$0.17Toolsgpt-oss-20bOpen131K$0.03$0.14ToolsGLM-4.5Open131K$0.40$1.60ToolsQwen3-235B-A22B-Thinking-2507Open262K$0.30$2.90ToolsMistral-Small-3.2-24B-Instruct-2506Open128K$0.07$0.20Toolsgemini-2.5-flash1M$0.30$2.50ReasoningVisionToolsgemini-2.5-pro1M$1.25$10.00ReasoningVisionToolsDeepSeek-R1-0528Open164K$0.50$2.15ToolsLlama-Guard-4-12BOpen164K$0.18$0.18Qwen3-14BOpen41K$0.12$0.24ToolsQwen3-235B-A22BOpen41K$0.18$0.54ToolsQwen3-30B-A3BOpen41K$0.12$0.50ToolsQwen3-32BOpen41K$0.08$0.28ToolsLlama-4-Scout-17B-16E-InstructOpen328K$0.10$0.30Toolsgemma-3-12b-itOpen131K$0.05$0.15Toolsgemma-3-4b-itOpen131K$0.05$0.10Toolsgemma-3-27b-itOpen131K$0.08$0.16ToolsMistral-Small-24B-Instruct-2501Open33K$0.05$0.08ToolsDeepSeek-R1-Distill-Llama-70BOpen131K$0.20$0.60DeepSeek-R1Open164K$0.70$2.40Toolsphi-4Open16K$0.07$0.14ToolsLlama-3.3-70B-InstructOpen131K$0.23$0.40ToolsQwen2.5-7B-InstructOpen33K$0.04$0.10Llama-3.2-3B-InstructOpen131K$0.02$0.02ToolsQwen2.5-72B-InstructOpen33K$0.36$0.40ToolsHermes-3-Llama-3.1-70BOpen131K$0.70$0.70Hermes-3-Llama-3.1-405BOpen131K$1.00$1.00ToolsWizardLM-2-8x22B66K$0.48$0.48MythoMax-L2-13bOpen4K$0.40$0.40ToolsDeepSeek-R1-0528-TurboOpen33K$1.00$3.00ToolsDeepSeek-R1-Distill-Qwen-32BOpen131K$0.27$0.27ToolsDeepSeek-R1-TurboOpen41K$1.00$3.00ToolsDeepSeek-V3Open164K$0.32$0.89ToolsDeepSeek-V3-0324Open164K$0.24$0.90ToolsDeepSeek-V3.1Open164K$0.25$0.95ReasoningToolsKimi-K2-InstructOpen131K$0.50$2.00ToolsKimi-K2-Instruct-0905Open262K$0.50$2.00ToolsL3-8B-Lunaris-v1-Turbo8K$0.04$0.05L3.1-70B-Euryale-v2.2131K$0.85$0.85L3.3-70B-Euryale-v2.3131K$0.65$0.75Llama-3.1-Nemotron-70B-InstructOpen131K$0.60$0.60ToolsLlama-3.2-11B-Vision-InstructOpen131K$0.05$0.05Llama-3.3-70B-Instruct-TurboOpen131K$0.10$0.32ToolsLlama-3.3-Nemotron-Super-49B-v1.5Open131K$0.10$0.40ToolsLlama-4-Maverick-17B-128E-Instruct-FP8Open1.0M$0.20$0.80ToolsLlama-Guard-3-8BOpen131K$0.06$0.06Meta-Llama-3-8B-InstructOpen8K$0.03$0.06ToolsMeta-Llama-3.1-70B-InstructOpen131K$0.40$0.40ToolsMeta-Llama-3.1-70B-Instruct-TurboOpen131K$0.40$0.40ToolsMeta-Llama-3.1-8B-InstructOpen131K$0.03$0.05ToolsMeta-Llama-3.1-8B-Instruct-TurboOpen131K$0.02$0.04ToolsMiniMax-M2.7-TurboOpen197K$0.38$1.70ReasoningToolsJSONMistral-Nemo-Instruct-2407Open131K$0.02$0.03ToolsMixtral-8x7B-Instruct-v0.1Open33K$0.40$0.40ToolsNVIDIA-Nemotron-3-Super-120B-A12BOpen262K$0.08$0.40ReasoningToolsJSONNVIDIA-Nemotron-3-Ultra-550B-A55BOpen262K$0.50$2.20ReasoningVisionToolsNVIDIA-Nemotron-3.5-LightningOpen262K$0.08$0.20ReasoningToolsNVIDIA-Nemotron-Nano-9B-v2Open131K$0.04$0.16ToolsNemotron-Content-Safety-3.5Open131K$0.20$0.20VisionQwQ-32BOpen131K$0.15$0.40ToolsQwen2.5-VL-32B-InstructOpen128K$0.20$0.60VisionToolsQwen3-235B-A22B-Instruct-2507Open262K$0.09$0.55ToolsQwen3-Coder-480B-A35B-InstructOpen262K$0.40$1.60ToolsQwen3-Coder-480B-A35B-Instruct-TurboOpen262K$0.30$1.00ToolsQwen3.8-MaxOpen256K$1.65$4.95ToolsJSONSeed-1.8256K$0.25$2.00ReasoningVisionToolsSeed-2.0-pro256K$0.50$3.00ReasoningVisionToolsclaude-3-7-sonnet-latest200K$3.30$16.50Toolsclaude-4-opus200K$16.50$82.50Toolsclaude-4-sonnet200K$3.30$16.50Toolsgemini-2.0-flash-0011M$0.10$0.40Toolsgemini-3.1-pro1M$2.00$12.00ReasoningVisionToolsgemma-4-31B-it-UltraOpen131K$0.27$0.76ReasoningVisionToolsgemma-4-31B-it-turboOpen262K$0.09$0.34ReasoningVisionToolsgemma-4-E4B-itOpen131K$0.02$0.10ReasoningToolsgpt-oss-120b-Turbo131K$0.15$0.60ReasoningToolsJSONgpt-oss-120b-Ultra131K$0.20$0.95ReasoningToolsJSONolmOCR-7B-0725-FP8Open16K$0.27$1.50

Release timeline

Aug 2026
DeepSeek-V4-Pro-0813
Aug 2026
Qwen3.8-2.4T-A95B
Aug 2026
Seed-2.0-code
Aug 2026
gemini-3.7-flash
Aug 2026
Qwen3.8-27B

Details

CategoryCloud platform
AuthAPI key
Regions-