Model provider

Deep Infra

Explore models served by Deep Infra.

106models
ModelOrganizationContextProvidersInput / 1MWeightsReasoning
Kimi K3.1 Promoonshotai/kimi-k3.1-promoonshotai1,048,57635—Open—
Nemotron 3.5 Embed 1Bnvidia/nemotron-3.5-embed-1bnvidia32,7683—Open—
Nemotron 3.5 Embed 8Bnvidia/nemotron-3.5-embed-8bnvidia32,7683—Open—
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017deepseek1,000,00052—Open—
EmbeddingGemma 2google/embeddinggemma-2google8,1921—Open—
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flashxiaomi1,048,57628from $0.10Open—
MiMo-V2.6-Proxiaomi/mimo-v2.6-proxiaomi1,048,57626from $0.43Open—
Step 5 Previewstepfun/step-5-previewstepfun1,000,00021from $1.00Open—
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashdeepseek1,000,00063from $0.0001Open—
Hy4 previewtencent/hy4-previewtencent1,024,00019from $0.834Open—
Qwen3.8 Flashalibaba/qwen3.8-flashalibaba1,000,00032from $0.15Closed—
GLM-5.3-Flashzhipuai/glm-5.3-flashzhipuai1,000,00088from $0.04Open—
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-expdeepseek1,000,00015from $0.2156Open—
Qwen3.8 27Balibaba/qwen3.8-27balibaba262,14455from $0.03Open—
GLM-5.3zhipuai/glm-5.3zhipuai1,000,00094from $0.039Open—
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813deepseek1,000,00046from $0.30Open—
Qwen3.8 2.4T A95Balibaba/qwen3.8-2.4t-a95balibaba262,14425from $2.00Open—
Qwen3.8 Maxalibaba/qwen3.8-maxalibaba1,000,00034—Closed—
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731deepseek1,000,00057from $0.0103Open—
Inkling Smallthinkingmachines/inkling-smallthinkingmachines1,048,57612from $0.45Open—
Kimi K3moonshotai/kimi-k3moonshotai1,048,57684from $0.33Open—
Nemotron 3 Embed 1Bnvidia/nemotron-3-embed-1bnvidia32,7683—Open—
Nemotron 3 Embed 8Bnvidia/nemotron-3-embed-8bnvidia32,7681—Open—
Inklingthinkingmachines/inklingthinkingmachines1,048,57619from $0.95Open—
Hy3tencent/hy3tencent256,00023from $0.132Open—
GLM-5.2zhipuai/glm-5.2zhipuai1,000,00088from $0.06Open—
Kimi K2.7 Codemoonshotai/kimi-k2.7-codemoonshotai262,14455from $0.6712Open—
Claude Fable 5anthropic/claude-fable-5anthropic1,000,00046from $10.00Closed—
MiniMax-M3minimax/MiniMax-M3minimax1,048,57653from $0.23Open—
Step 3.7 Flashstepfun/step-3.7-flashstepfun256,00021from $0.20Open—
Qwen3.7 Maxalibaba/qwen3.7-maxalibaba1,000,00030from $1.475Closed—
Nemotron 3 Nano Omni 30B A3B Reasoningnvidia/nemotron-3-nano-omni-30b-a3b-reasoningnvidia256,0009from $0.00Open—
DeepSeek V4 Flashdeepseek/deepseek-v4-flashdeepseek1,000,00054from $0.019Open—
DeepSeek V4 Prodeepseek/deepseek-v4-prodeepseek1,000,00063from $0.30Open—
Qwen3.6 27Balibaba/qwen3.6-27balibaba262,14428from $0.29Open—
MiMo-V2.5xiaomi/mimo-v2.5xiaomi1,048,57623from $0.119Open—
MiMo-V2.5-Proxiaomi/mimo-v2.5-proxiaomi1,048,57620from $0.3045Open—
Kimi K2.6moonshotai/kimi-k2.6moonshotai262,14463from $0.465Open—
Qwen3.6 35B-A3Balibaba/qwen3.6-35b-a3balibaba262,14439from $0.05Open—
GLM-5.1zhipuai/glm-5.1zhipuai200,00049from $0.966Open—
1–40 of 106