theserverless.dev InferenceList

Models

Showing 51–79 of 79 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
MiniMaxAI/MiniMax-M3 DeepInfra text image $0.28/1M $1.1/1M 524K
google/gemini-2.5-flash DeepInfra text image $0.3/1M $2.5/1M 1M
meta-models/Muse-Glimmer-30B DeepInfra text image $0.3/1M $1.2/1M 131K
Qwen/Qwen3.6-27B DeepInfra text image $0.32/1M $3.2/1M 262K
XiaomiMiMo/MiMo-V2.6-Pro DeepInfra text image $0.43/1M $0.87/1M 1.0M
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp DeepInfra text image $0.44/1M $1.32/1M 1.0M
Qwen/Qwen3.5-397B-A17B DeepInfra text image $0.45/1M $3/1M 262K
thinkingmachines/Inkling-Small DeepInfra text image $0.45/1M $1.2/1M 524K
ByteDance/Seed-2.0-code DeepInfra text image $0.5/1M $3/1M 256K
ByteDance/Seed-2.0-pro DeepInfra text image $0.5/1M $3/1M 256K
google/gemini-3.7-flash DeepInfra text image $0.75/1M $3.75/1M 1M
moonshotai/Kimi-K2.6 DeepInfra text image $0.75/1M $3.5/1M 262K
anthropic/claude-haiku-4-5 DeepInfra text image $1/1M $5/1M 200K
google/gemini-2.5-pro DeepInfra text image $1.25/1M $10/1M 1M
google/gemini-3.5-flash DeepInfra text image $1.5/1M $9/1M 1M
anthropic/claude-sonnet-5-5 DeepInfra text image $2/1M $10/1M 1M
google/gemini-3.1-pro DeepInfra text image $2/1M $12/1M 1M
moonshotai/Kimi-K3 DeepInfra text image $2.85/1M $14.25/1M 1.0M
anthropic/claude-sonnet-4-6 DeepInfra text image $3/1M $15/1M 1M
anthropic/claude-sonnet-5 DeepInfra text image $3/1M $15/1M 1M
anthropic/claude-opus-5-5 DeepInfra text image $4/1M $20/1M 1M
anthropic/claude-opus-4-7 DeepInfra text image $5/1M $25/1M 1M
anthropic/claude-opus-4-8 DeepInfra text image $5/1M $25/1M 1M
anthropic/claude-opus-5 DeepInfra text image $5/1M $25/1M 1M
anthropic/claude-fable-5 DeepInfra text image $10/1M $50/1M 1M
google/gemini-3-pro-image DeepInfra image Not published— Not published— —
google/nano-banana-2 DeepInfra image Not published— Not published— —
google/nano-banana-2-lite DeepInfra image Not published— Not published— —
google/nano-banana-pro DeepInfra image Not published— Not published— —

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.