theserverless.dev InferenceList

Models

Showing 1451–1500 of 1,880 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Model Provider Modality Input ↑ Output Context
Fireworks: Ember-1 Fireworks text image $3/1M $15/1M 1.0M
Kimi K3 AtlasCloud text image video $3/1M $15/1M 1.0M
Kimi K3 Novita text image video $3/1M $15/1M 1.0M
Kimi K3 Novita text image video $3/1M $15/1M 1.0M
Kimi K3 Together text $3/1M $15/1M 1.0M
kimi-k3-1-pro Venice text $3/1M $15/1M 1M
moonshotai/kimi-k3 Inference.net text image $3/1M $15/1M 1.0M
MoonshotAI: Kimi K3 Phala text image video $3/1M $15/1M 1.0M
OpenAI: GPT-3.5 Turbo 16k OpenAI text $3/1M $4/1M 16K
Perplexity: Sonar Pro Perplexity text image $3/1M $15/1M 200K
Perplexity: Sonar Pro Search Perplexity text image $3/1M $15/1M 200K
xAI: Grok 4 Phala text image $3/1M $15/1M 256K
Kimi K3 Amazon Bedrock text $3.3/1M $16.5/1M —
Kimi K3 NEAR AI text image $3.3/1M $16.5/1M 1.0M
Black Forest Labs: FLUX.2 Klein 4B Black Forest Labs text image $3.418/1M Not published— 41K
Meta Llama 3.1 405B Instruct Together text $3.5/1M $3.5/1M 4K
Krea: Krea 2 Medium Turbo Krea text image $3.593/1M Not published— 66K
aion-labs-aion-3-0 Venice text $3.75/1M $7.5/1M 128K
aion-labs-aion-3-5 Venice text $3.75/1M $7.5/1M 262K
e2ee-kimi-k3-p Venice text $3.75/1M $18.75/1M 1M
kimi-k3 Venice text $3.75/1M $18.75/1M 1M
anthropic/claude-opus-5-5 DeepInfra text image $4/1M $20/1M 1M
Anthropic: Claude Opus 5.5 Anthropic text image $4/1M $20/1M 1M
Anthropic: Claude Opus Latest Anthropic text image $4/1M $20/1M 1M
Claude Opus 5.5 AtlasCloud text image $4/1M $20/1M 1M
Claude Opus 5.5 NEAR AI text image $4/1M $20/1M 1M
claude-opus-5-5 Inference.net text image $4/1M $20/1M 1M
claude-opus-5-5 Venice text $4/1M $20/1M 1M
DeepSeek R1 Novita text $4/1M $4/1M 64K
Google: Gemini 3.1 Pro Preview Phala audio image text video $4/1M $18/1M 1.0M
GPT-5.6 Sol NEAR AI text image $4/1M $20/1M 1.1M
Kimi K3 Tinfoil text image $4/1M $20/1M 262K
Kimi K3.1 Pro HighSpeed AtlasCloud text image video $4/1M $20/1M 1.0M
Kimi K3.1 Pro Highspeed Novita text image video $4/1M $20/1M 1.0M
Meta: Muse Wonder Meta text image video audio $4/1M $20/1M 1.0M
Mistral Large Amazon Bedrock text $4/1M $12/1M —
openai-gpt-56-sol Venice text $4/1M $20/1M 1M
openai-gpt-56-sol-pro Venice text $4/1M $20/1M 1M
OpenAI: GPT-5.6 Sol OpenAI text image $4/1M $20/1M 1.1M
OpenAI: GPT-5.6 Sol Phala text image $4/1M $20/1M 272K
OpenAI: GPT-5.6 Sol Pro OpenAI text image $4/1M $20/1M 1.1M
Qwen: Qwen3.8 Max Prime Alibaba text image video $4/1M $12/1M 1M
ByteDance Seed: Seedream 5.0 Flash ByteDance text image $4.311/1M Not published— —
Xiaomi: MiMo-V2.6-Pro-UltraSpeed Xiaomi text image video audio $4.35/1M $8.7/1M 1.0M
Qwen: Qwen Image 2.1 Turbo Alibaba text image $4.407/1M Not published— 66K
kimi-k3-fast Inference.net text image $4.5/1M $22.5/1M 1.0M
kimi-k3-fast-api Venice text $4.5/1M $22.5/1M 1M
moonshotai/kimi-k3-fast Inference.net text image $4.5/1M $22.5/1M 1.0M
Sourceful: Riverflow V2.5 Fast Sourceful text image $4.551/1M Not published— 33K
Sourceful: Riverflow V2 Fast Sourceful text image $4.79/1M Not published— 8K

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