theserverless.dev InferenceList

Models

Showing 1351–1400 of 2,347 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
zai-org/GLM-5.2 Friendli text $1.4/1M $4.4/1M 1.0M
zai-org/glm-5.3-p Novita text $1.4/1M $4.4/1M 1.0M
grok-4-20 Venice text $1.42/1M $2.83/1M 2M
grok-4-20-multi-agent Venice text $1.42/1M $2.83/1M 2M
grok-4-3 Venice text $1.42/1M $2.83/1M 1M
DeepSeek: DeepSeek V4 Pro 0813 Phala text $1.45/1M $4.36/1M 1.0M
Qwen: Qwen3.7 Max
Cheaper on Novita (−15.3%)
Alibaba text $1.475/1M $4.425/1M 1M
Llama 3 70B Euryale V2.1 Novita text $1.48/1M $1.48/1M 8K
Z.ai: GLM 5.2 Io Net text $1.484/1M $5.604/1M 262K
DeepSeek: DeepSeek V4 Pro Io Net text $1.49/1M $2.922/1M 1.0M
DeepSeek: DeepSeek V3.2 Io Net text $1.494/1M $2.138/1M 164K
Anthropic: Claude Sonnet 4.5 (batch) Anthropic text image $1.5/1M $7.5/1M 1M
Anthropic: Claude Sonnet 4.6 (batch) Anthropic text image $1.5/1M $7.5/1M 1M
Gemini 3.5 Flash AtlasCloud text image video audio $1.5/1M $9/1M 1.0M
Gemini 3.5 Flash NEAR AI text image $1.5/1M $9/1M 1M
gemini-3.5-flash Inference.net text image $1.5/1M $9/1M 1.0M
gemini-3.6-flash Inference.net text image $1.5/1M $7.5/1M 1.0M
gemini-3.7-flash Inference.net text image audio video $1.5/1M $7.5/1M 1.0M
google/gemini-3.5-flash DeepInfra text image $1.5/1M $9/1M 1M
Google: Gemini 3.5 Flash Google text image video audio $1.5/1M $9/1M 1.0M
Google: Gemini 3.6 Flash Phala text image video audio $1.5/1M $7.5/1M 1.0M
Google: Nano Banana 2.1 Google image text $1.5/1M $7.5/1M 66K
Mistral: Mistral Medium 3.5 Mistral AI text image $1.5/1M $7.5/1M 262K
z-ai-glm-5v-turbo Venice text $1.5/1M $5/1M 200K
zai-org-glm-5-1 Venice text $1.54/1M $4.84/1M 200K
gemini-3-5-flash Venice text $1.55/1M $9.45/1M 1M
muse-spark-open Venice text $1.563/1M $5.313/1M 1.0M
Z.ai: GLM 5.3 Io Net text $1.584/1M $5.648/1M 262K
DeepSeek R1 Distill Qwen 14B Together text $1.6/1M $1.6/1M 131K
DeepSeek V4 Pro Novita text $1.6/1M $3.2/1M 1.0M
Gemini 4 Argon AtlasCloud text image video audio $1.6/1M $8/1M 1.0M
Tencent: Hy Image 3.5 Preview Tencent text image $1.6/1M Not published— 100K
deepseek-v4-pro Venice text $1.65/1M $3.301/1M 1M
deepseek-v4-pro-0813 Venice text $1.65/1M $4.95/1M 1M
Qwen/Qwen3.8-Max DeepInfra text $1.65/1M $4.951/1M 256K
Recraft: Recraft V4.1 Flash Recraft text image $1.677/1M Not published— 66K
DeepSeek V4 Pro AtlasCloud text $1.68/1M $3.38/1M 1.0M
e2ee-glm-5-2-p Venice text $1.75/1M $5.75/1M 524K
e2ee-glm-5-3-p Venice text $1.75/1M $5.5/1M 1M
GPT 5.2 chat opt Gl Azure text $1.75/1M $14/1M —
Llama 3.3 70B Tinfoil text $1.75/1M $2.75/1M 131K
Microsoft AI: MAI-Image-2.6 Flash Microsoft text image $1.75/1M $0/1M 4K
OpenAI GPT-5.2 NEAR AI text image $1.75/1M $14/1M 400K
openai-gpt-52 Venice text $1.75/1M $14/1M 256K
openai-gpt-53-codex Venice text $1.75/1M $14/1M 400K
OpenAI: GPT-5.2 OpenAI text image $1.75/1M $14/1M 400K
OpenAI: GPT-5.2 Phala image text $1.75/1M $14/1M 400K
OpenAI: GPT-5.2 Chat OpenAI text image $1.75/1M $14/1M 128K
OpenAI: GPT-5.2-Codex OpenAI text image $1.75/1M $14/1M 400K
OpenAI: GPT-5.3-Codex OpenAI text image $1.75/1M $14/1M 400K

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