AI Model Overview

DeepInfra model lifecycle

38 DeepInfra models, with what each one costs and how long it has left. None are currently deprecated.

37 active 0 deprecated 1 retired snapshot

Open DeepInfra in the overview All upcoming shutdowns

Active models

Currently supported by DeepInfra — the pool to migrate into when something above reaches its date.

37 active DeepInfra models. Prices in USD per million tokens.
Provider Model Status Lifecycle date Input Output
DeepInfra Claude Opus 5 anthropic/claude-opus-5 Active — $5.00 $25.00
DeepInfra DeepSeek V3 deepseek-ai/DeepSeek-V3 Active — $0.32 $0.89
DeepInfra DeepSeek V3.2 deepseek-ai/DeepSeek-V3.2 Active — $0.26 $0.38
DeepInfra DeepSeek V4 Flash deepseek-ai/DeepSeek-V4-Flash Active — $0.09 $0.18
DeepInfra DeepSeek V4 Flash 0731 deepseek-ai/DeepSeek-V4-Flash-0731 Active — $0.06 $0.18
DeepInfra DeepSeek V4 Pro deepseek-ai/DeepSeek-V4-Pro Active — $1.30 $2.60
DeepInfra DeepSeek V4 Pro 0813 deepseek-ai/DeepSeek-V4-Pro-0813 Active — $1.30 $2.60
DeepInfra Gemini 3.7 Flash google/gemini-3.7-flash Active — $0.75 $3.75
DeepInfra GLM-4.7 zai-org/GLM-4.7 Active — $0.40 $1.75
DeepInfra GLM-5.1 zai-org/GLM-5.1 Active — $1.05 $3.50
DeepInfra GLM-5.2 zai-org/GLM-5.2 Active — $0.75 $2.40
DeepInfra GLM-5.3 zai-org/GLM-5.3 Active — $1.20 $4.00
DeepInfra GLM-5.3 Flash zai-org/GLM-5.3-Flash Active — $0.15 $0.50
DeepInfra gpt-oss-120b openai/gpt-oss-120b Active — $0.037 $0.17
DeepInfra gpt-oss-20b openai/gpt-oss-20b Active — $0.03 $0.14
DeepInfra Inkling thinkingmachines/Inkling Active — $0.95 $4.05
DeepInfra Inkling Small thinkingmachines/Inkling-Small Active — $0.45 $1.20
DeepInfra Kimi K2.6 moonshotai/Kimi-K2.6 Active — $0.75 $3.50
DeepInfra Kimi K2.7 Code moonshotai/Kimi-K2.7-Code Active — $0.68 $3.40
DeepInfra Kimi K3 moonshotai/Kimi-K3 Active — $2.85 $14.25
DeepInfra Ling-3.0-flash inclusionAI/Ling-3.0-flash Active — $0.06 $0.18
DeepInfra Llama 3.1 8B Instruct Turbo meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo Active — $0.02 $0.04
DeepInfra Llama 3.3 70B Instruct Turbo meta-llama/Llama-3.3-70B-Instruct-Turbo Active — $0.10 $0.32
DeepInfra Llama 4 Maverick 17B 128E Instruct FP8 meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 Active — $0.20 $0.80
DeepInfra Llama 4 Scout 17B 16E Instruct meta-llama/Llama-4-Scout-17B-16E-Instruct Active — $0.10 $0.30
DeepInfra MiMo V2.5 Pro XiaomiMiMo/MiMo-V2.5-Pro Active — $1.00 $3.00
DeepInfra MiniMax M3 MiniMaxAI/MiniMax-M3 Active — $0.28 $1.10
DeepInfra Muse Glimmer 30B meta-models/Muse-Glimmer-30B Active — $0.30 $1.20
DeepInfra Nemotron 3 Ultra 550B A55B nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B Active — $0.50 $2.20
DeepInfra Nemotron 3.5 Lightning nvidia/NVIDIA-Nemotron-3.5-Lightning Active — $0.08 $0.20
DeepInfra Qwen3 235B A22B Instruct 2507 Qwen/Qwen3-235B-A22B-Instruct-2507 Active — $0.09 $0.55
DeepInfra Qwen3 Coder 480B A35B Instruct Turbo Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo Active — $0.30 $1.00
DeepInfra Qwen3.7 Max Qwen/Qwen3.7-Max Active — $2.50 $7.50
DeepInfra Qwen3.8 2.4T A95B Qwen/Qwen3.8-2.4T-A95B Active — $2.00 $6.00
DeepInfra Qwen3.8 27B Qwen/Qwen3.8-27B Active — $0.40 $3.00
DeepInfra Qwen3.8 Max Qwen/Qwen3.8-Max Active — $1.65 $4.951
DeepInfra Seed 2.0 pro ByteDance/Seed-2.0-pro Active — $0.50 $3.00

Already shut down

Kept listed on purpose: if one of these ids is still in your code, this page tells you when it stopped and where to go instead.

1 retired DeepInfra models. Last observed prices in USD per million tokens.
Provider Model Status Lifecycle date Input Output
DeepInfra DeepSeek V3.1 Terminus deepseek-ai/DeepSeek-V3.1-Terminus Retired — —

Running DeepInfra in production?

Check your model ids against this list once, then let the overview keep track. Free to use, no account needed.

Open the overview