theserverless.dev InferenceList

Models

Showing 1201–1250 of 2,347 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
Qwen 3.8 27B Cerebras text $0.99/1M $1.49/1M 66K
anthropic/claude-haiku-4-5 DeepInfra text image $1/1M $5/1M 200K
Anthropic: Claude Haiku 4.5 Anthropic text image $1/1M $5/1M 200K
Anthropic: Claude Haiku 4.5 Phala text image $1/1M $5/1M 200K
Anthropic: Claude Sonnet 5 (batch) Anthropic text image $1/1M $5/1M 1M
Anthropic: Claude Sonnet 5.5 (batch) Anthropic text image $1/1M $5/1M 1M
Claude Haiku 4.5 NEAR AI text image $1/1M $5/1M 200K
Claude Haiku 4.5 20251001 AtlasCloud text $1/1M $5/1M 200K
Claude Haiku 4.5 20251001 AWS AtlasCloud text $1/1M $5/1M 200K
Claude Haiku 4.5 20251001 Coding AtlasCloud text $1/1M $5/1M 200K
claude-haiku-4-5 Inference.net text image $1/1M $5/1M 200K
deepseek-ai/DeepSeek-V3.2-TEE Chutes text $1/1M $1/1M 131K
DeepSeek: DeepSeek V3.2 Phala text $1/1M $1/1M 164K
FLUX.2-klein-4B NEAR AI text image $1/1M $1/1M 128K
GLM 5 Amazon Bedrock text $1/1M $3.2/1M —
GLM 5 Novita text $1/1M $3.2/1M 203K
GLM 5 Fp4 Together text $1/1M $3.2/1M 203K
Google: Gemini 3.1 Flash TTS Preview Google text audio $1/1M $20/1M 33K
Google: Gemini 3.1 Pro Preview (batch) Google audio text image video $1/1M $6/1M 1.0M
Google: Gemini 4 Argon (batch) Google audio text image video $1/1M $5/1M 1.0M
GPT 6.1 Terra Codex AtlasCloud text image $1/1M $5/1M 1.1M
GPT Image 2 API fal image $1/unit Not published— —
GPT Image 2 API fal image $1/unit Not published— —
GPT Image 2.5 Flare Edit fal image $1/unit Not published— —
GPT Image 2.5 Flare Text to Image fal image $1/unit Not published— —
GPT Image 2.5 Sunburst Edit fal image $1/unit Not published— —
GPT Image 2.5 Sunburst Text to Image fal image $1/unit Not published— —
Grok Build 0.1 AtlasCloud text $1/1M $2/1M 262K
grok-build-0-1 Venice text $1/1M $2/1M 256K
Inkling FP4 Together text $1/1M $4.05/1M 524K
ming image 0.1 design Novita text image video audio $1/1M $1/1M —
ming image 0.1 design layer Novita text image video audio $1/1M $1/1M —
Mistral Small Amazon Bedrock text $1/1M $3/1M —
Nano Banana 2.1 fal image $1/unit Not published— —
Nano Banana 2.1 Edit fal image $1/unit Not published— —
Nous: Hermes 3 405B Instruct Nousresearch text $1/1M $1/1M 131K
Nous: Hermes 3 405B Instruct Phala text $1/1M $1/1M 131K
Nous: Hermes 4 405B Nousresearch text $1/1M $3/1M 131K
openai-gpt-61-terra Venice text $1/1M $5/1M 1.1M
OpenAI: GPT Terra Latest OpenAI text image $1/1M $5/1M 1.1M
OpenAI: GPT-3.5 Turbo (older v0613) OpenAI text $1/1M $2/1M 4K
OpenAI: GPT-4.1 (batch) OpenAI image text $1/1M $4/1M 1.0M
OpenAI: GPT-5.6 Terra (batch) OpenAI text image $1/1M $6/1M 1.1M
OpenAI: GPT-5.6 Terra Pro (batch) OpenAI text image $1/1M $6/1M 1.1M
OpenAI: GPT-6 Sol (batch) OpenAI text image $1/1M $5/1M 1.1M
OpenAI: GPT-6 Sol Pro (batch) OpenAI text image $1/1M $5/1M 1.1M
OpenAI: GPT-6.1 Sol (batch) OpenAI text image $1/1M $5/1M 1.1M
OpenAI: GPT-6.1 Sol Pro (batch) OpenAI text image $1/1M $5/1M 1.1M
OpenAI: GPT-6.1 Terra OpenAI text image $1/1M $5/1M 1.1M
OpenAI: GPT-6.1 Terra Phala text image $1/1M $5/1M 272K

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