fal
Direct API
- Models
- 744
- Endpoints
- 744
- Usable quotes
- 807
Image458Video142Audio84Language383D22
Image model access
API and web tools
DISCOVER / PROVIDERS
Find your next provider.
Explore model APIs and gateways by what they offer and where their prices stand out.
97 observed providers1,652 models with routes190 models with competing token quotes
97 observed providers
How value is comparedOpenRouter
Direct API
- Models
- 543
- Endpoints
- 544
- Usable quotes
- 111
Language473Embedding37Decision27Audio6
5 token price wins3 tied
1M input + 250K output tokens · USD · Newest first
- drex-v1.5$0.04Tied lowest
OpenRouter
- OpenAI: GPT-6 Luna Decisions$0.10Tied lowest
OpenRouter
- Cloudflare: Clef Flash$0.021Lowest collected
OpenRouter
- Cloudflare: Clef$0.042Lowest collected
OpenRouter
- Qwen: Qwen3 235B A22B Instruct 2507$0.2275Tied lowest
OpenRouter
Experiential Labs
Direct API
- Models
- 292
- Endpoints
- 292
- Usable quotes
- 319
Language286Embedding5Decision1
49 token price wins48 tied
1M input + 250K output tokens · USD · Newest first
- Anthropic: Claude Haiku 5.5$0.225Tied lowest
Experiential
Standard · fewer than 100,001 input tokens
- OpenAI: GPT-6 Luna Decisions$0.10Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Sonnet 5.5$4.50Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Opus 5.5$9.00Tied lowest
Experiential
Standard list rate
- SpaceXAI: Grok 4.7$3.50Tied lowest
Experiential
Standard · fewer than 200,000 input tokens
- Anthropic: Claude Fable 5.1$22.50Tied lowest
Experiential
Standard list rate
- SpaceXAI: Grok 4.6$3.50Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Opus 5$11.25Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-5.6 Sol$4.50Tied lowest
Experiential
Flex service tier
- SpaceXAI: Grok 4.5$3.50Tied lowest
Experiential
Standard list rate
- claude-sonnet-5$4.50Tied lowest
Experiential
Standard list rate
- claude-fable-5$22.50Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Opus 4.8$11.25Tied lowest
Experiential
Standard list rate
- SpaceXAI: Grok Build 0.1$1.50Tied lowest
Experiential
Standard list rate
- SpaceXAI: Grok 4.3$1.875Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Opus 4.7$11.25Tied lowest
Experiential
Standard list rate
- Z.ai: GLM 5V Turbo$2.20Tied lowest
Experiential
Standard list rate
- SpaceXAI: Grok 4.20 Multi-Agent$1.875Tied lowest
Experiential
Standard list rate
- SpaceXAI: Grok 4.20$1.875Tied lowest
Experiential
Standard list rate
- Z.ai: GLM 5 Turbo$2.20Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-5.3-Codex$5.25Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Sonnet 4.6$6.75Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Opus 4.6$11.25Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-5.2-Codex$5.25Tied lowest
Experiential
Standard list rate
- Z.ai: GLM 4.6V$0.525Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-5.1-Codex-Max$3.75Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Opus 4.5$11.25Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-5.1-Codex$3.75Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-5.1-Codex-Mini$0.75Tied lowest
Experiential
Standard list rate
- MoonshotAI: Kimi K2 Thinking$1.225Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Haiku 4.5$2.25Tied lowest
Experiential
Standard list rate
- Anthropic: Claude Sonnet 4.5$6.75Tied lowest
Experiential
Standard list rate
- DeepSeek: DeepSeek V3.2 Exp$0.3725Tied lowest
Experiential
Standard list rate
- OpenAI: gpt-oss-safeguard-20b$0.12Lowest collected
Experiential
Standard list rate
- OpenAI: GPT-5$3.75Tied lowest
Experiential
Standard list rate
- DeepSeek: R1 0528$1.0375Tied lowest
Experiential
Standard list rate
- OpenAI: o3$4.00Tied lowest
Experiential
Standard list rate
- OpenAI: o4 Mini$2.20Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-4.1$4.00Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-4.1 Mini$0.80Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-4.1 Nano$0.20Tied lowest
Experiential
Standard list rate
- OpenAI: o3 Mini$2.20Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-4o-mini$0.30Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-4o$5.00Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-4 Turbo$17.50Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-3.5 Turbo (older v0613)$1.50Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-3.5 Turbo Instruct$2.00Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-3.5 Turbo 16k$4.00Tied lowest
Experiential
Standard list rate
- OpenAI: GPT-3.5 Turbo$0.875Tied lowest
Experiential
Standard list rate
Hosted API; paid BYOK; self-hosted gateway
DeepInfra
Direct API · via Hugging Face · OpenRouter
- Models
- 187
- Endpoints
- 317
- Usable quotes
- 338
Language138Audio23Video19Decision4Image3
55 token price wins21 tied
1M input + 250K output tokens · USD · Newest first
- DeepSeek-V4.1-Flash-1017$0.196Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp8/flex · tier=flex · quantization=fp8
- Ling-3.1-flash$0.525Tied lowest
DeepInfra
- drex-v1.5$0.04Tied lowest
DeepInfra
- Anthropic: Claude Sonnet 5.5$4.50Tied lowest
DeepInfra
- Anthropic: Claude Opus 5.5$9.00Tied lowest
DeepInfra
- Xiaomi: MiMo-V2.6-Pro$0.6475Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp8 · quantization=fp8
- Step-5-Preview$1.675Tied lowest
DeepInfra
- NVIDIA-Nemotron-3.5-Super-VL$0.20Lowest collected
DeepInfra
- Qwen3.8-Flash$0.2085Lowest collected
DeepInfra
- Ling-3.0-flash-VL$0.105Lowest collected
DeepInfra
- Ling-3.0-flash-Fin$0.105Lowest collected
deepinfra · via Hugging Face
- Hy4-preview$1.4593Tied lowest
DeepInfra
- GLM-5.3-Flash$0.1375Tied lowest
DeepInfra · via OpenRouter
deepinfra/fp4 · quantization=fp4
- DeepSeek-V4-Flash-Vision-Exp$0.3773Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp8 · quantization=fp8
- Meta: Muse Glimmer 30B$0.60Lowest collected
DeepInfra
- Qwen: Qwen3.8 2.4T A95B$3.50Tied lowest
deepinfra · via Hugging Face
- granite-4.2-8b$0.1225Lowest collected
DeepInfra
- Anthropic: Claude Opus 5$11.25Tied lowest
DeepInfra
- Thinking Machines: Inkling$1.9625Lowest collected
deepinfra · via Hugging Face
- Tencent: Hy3$0.2625Lowest collected
deepinfra · via Hugging Face
- claude-fable-5$22.50Tied lowest
DeepInfra
- NVIDIA: Nemotron 3 Ultra$0.84Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp4/flex · tier=flex · quantization=fp4
- MiniMax-M3$0.555Lowest collected
DeepInfra
- MiniMax: MiniMax M3$0.444Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp8/flex · tier=flex · quantization=fp8
- Anthropic: Claude Opus 4.8$11.25Tied lowest
DeepInfra
- StepFun: Step 3.7 Flash$0.4875Tied lowest
deepinfra · via Hugging Face
- Xiaomi: MiMo-V2.5$0.21Lowest collected
deepinfra · via Hugging Face
- Anthropic: Claude Opus 4.7$11.25Tied lowest
DeepInfra
- NVIDIA: Nemotron 3 Super$0.185Lowest collected
DeepInfra · via OpenRouter
deepinfra/bf16 · quantization=bf16
- Anthropic: Claude Sonnet 4.6$6.75Tied lowest
DeepInfra
- StepFun: Step 3.5 Flash$0.175Tied lowest
deepinfra · via Hugging Face
- Z.ai: GLM 4.7 Flash$0.16Tied lowest
deepinfra · via Hugging Face
- MoonshotAI: Kimi K2.5$1.0125Lowest collected
deepinfra · via Hugging Face
- GLM-4.7$0.67Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp4/flex · tier=flex · quantization=fp4
- Anthropic: Claude Haiku 4.5$2.25Tied lowest
DeepInfra
- Qwen3-VL-30B-A3B-Instruct$0.30Lowest collected
DeepInfra
- GLM-4.6$0.80Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp4/flex · tier=flex · quantization=fp4
- DeepSeek: DeepSeek V3.1 Terminus$0.5075Lowest collected
deepinfra · via Hugging Face
- Qwen3-VL-235B-A22B-Instruct$0.42Lowest collected
DeepInfra
- Qwen3-Next-80B-A3B-Instruct$0.292Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp8/flex · tier=flex · quantization=fp8
- DeepSeek-V3.1$0.4875Lowest collected
DeepInfra
- Qwen: Qwen3 235B A22B Thinking 2507$0.805Lowest collected
deepinfra · via Hugging Face
- Qwen: Qwen3 Coder 480B A35B$0.55Lowest collected
DeepInfra · via OpenRouter
deepinfra/turbo · quantization=fp4
- Qwen: Qwen3 235B A22B Instruct 2507$0.2275Tied lowest
DeepInfra
- Mistral-Small-3.2-24B-Instruct-2506$0.125Lowest collected
DeepInfra
- DeepSeek: R1 0528$1.0375Tied lowest
DeepInfra
- DeepSeek: DeepSeek V3 0324$0.465Lowest collected
deepinfra · via Hugging Face
- gemma-3-12b-it$0.07Lowest collected
DeepInfra · via OpenRouter
deepinfra/bf16/flex · tier=flex · quantization=bf16
- gemma-3-27b-it$0.12Lowest collected
DeepInfra
- DeepSeek-V3$0.434Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp4/flex · tier=flex · quantization=fp4
- Meta: Llama 3.3 70B Instruct$0.18Lowest collected
DeepInfra · via OpenRouter
deepinfra/turbo · quantization=fp8
- Sao10K: Llama 3 8B Lunaris$0.0525Tied lowest
DeepInfra · via OpenRouter
deepinfra/turbo · quantization=fp8
- Meta: Llama 3.1 8B Instruct$0.03Lowest collected
DeepInfra · via OpenRouter
deepinfra/fp8 · quantization=fp8
- Meta: Llama 3.1 70B Instruct$0.50Lowest collected
DeepInfra · via OpenRouter
deepinfra/turbo · quantization=fp8
- Llama-3.1-8B-Instruct$0.0325Tied lowest
deepinfra · via Hugging Face
API; web chat; GPU services
OpenAI
Via OpenRouter
- Models
- 96
- Endpoints
- 144
- Usable quotes
- 136
Language88Image8
41 token price wins18 tied
1M input + 250K output tokens · USD · Newest first
- OpenAI: GPT-6.1 Sol Pro$2.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-6.1 Sol$2.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-6 Luna Pro$0.1125Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-6 Sol Pro$2.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-6 Sol$2.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-6 Luna$0.1125Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-6 Astra Pro$11.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-6 Astra$11.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.6 Luna Pro$0.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.6 Luna$0.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.6 Terra Pro$2.50Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.6 Terra$2.50Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.6 Sol Pro$4.50Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.6 Sol$4.50Tied lowest
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.5 Pro$37.50Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.5$6.25Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.4 Nano$0.2563Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex
- OpenAI: GPT-5.4 Mini$0.9375Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex
- OpenAI: GPT-5.4 Pro$37.50Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.4$3.125Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex · prompt ≤ 272000 tokens
- OpenAI: GPT-5.3-Codex$5.25Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-5.2$2.625Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex
- OpenAI: GPT-5.1$1.875Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex
- OpenAI: GPT-5$3.75Tied lowest
OpenAI · via OpenRouter
openai/default
- OpenAI: GPT-5 Mini$0.375Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex
- OpenAI: GPT-5 Nano$0.075Lowest collected
OpenAI · via OpenRouter
openai/flex · tier=flex
- OpenAI: o3$4.00Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: o4 Mini$2.20Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4.1$4.00Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4.1 Mini$0.80Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4.1 Nano$0.20Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: o3 Mini$2.20Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4o (2024-08-06)$5.00Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4o-mini$0.30Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4o$5.00Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4o (2024-05-13)$8.75Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4 Turbo$17.50Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-3.5 Turbo Instruct$2.00Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-3.5 Turbo 16k$4.00Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-3.5 Turbo$0.875Tied lowest
OpenAI · via OpenRouter
openai
- OpenAI: GPT-4$45.00Tied lowest
OpenAI · via OpenRouter
openai
API and web tools
Featherless
Via Hugging Face · OpenRouter
- Models
- 68
- Endpoints
- 68
- Usable quotes
- 1
Language68
1 token price win1 tied
1M input + 250K output tokens · USD · Newest first
- Step-5-Preview$1.675Tied lowest
Featherless · via OpenRouter
featherless/fp4 · quantization=fp4
API; interactive chat; dedicated GPUs
Novita AI
Via Hugging Face · OpenRouter
- Models
- 64
- Endpoints
- 103
- Usable quotes
- 99
Language64
13 token price wins8 tied
1M input + 250K output tokens · USD · Newest first
- Ling-3.1-flash$0.525Tied lowest
novita · via Hugging Face
- inclusionAI: Ling 3.1 Flash$0.1313Lowest collected
Novita · via OpenRouter
novita
- Hy4-preview$1.4593Tied lowest
novita · via Hugging Face
- Qwen: Qwen3.8 2.4T A95B$3.50Tied lowest
novita · via Hugging Face
- inclusionAI: Ling 3.0 Flash$0.0368Lowest collected
Novita · via OpenRouter
novita
- StepFun: Step 3.7 Flash$0.4875Tied lowest
Novita · via OpenRouter
novita/fp8 · quantization=fp8
- NVIDIA: Nemotron 3 Nano 30B A3B$0.10Lowest collected
Novita · via OpenRouter
novita/fp4 · quantization=fp4
- Z.ai: GLM 4.6V$0.525Tied lowest
Novita · via OpenRouter
novita/bf16 · quantization=bf16
- MoonshotAI: Kimi K2 Thinking$1.225Tied lowest
Novita · via OpenRouter
novita/bf16 · quantization=bf16
- Z.ai: GLM 4.5V$1.05Tied lowest
novita · via Hugging Face
- Z.ai: GLM 4.5 Air$0.3425Lowest collected
novita · via Hugging Face
- DeepSeek: R1$1.325Lowest collected
novita · via Hugging Face
- Llama-3.1-8B-Instruct$0.0325Tied lowest
novita · via Hugging Face
Serverless APIs; dedicated endpoints; console
Azure
Via OpenRouter
- Models
- 60
- Endpoints
- 103
- Usable quotes
- 98
Language56Image4
30 token price wins30 tied
1M input + 250K output tokens · USD · Newest first
- Anthropic: Claude Haiku 5.5$0.225Tied lowest
Azure · via OpenRouter
azure/global · prompt ≤ 100000 tokens
- Anthropic: Claude Sonnet 5.5$4.50Tied lowest
Azure · via OpenRouter
azure/global
- Anthropic: Claude Opus 5.5$9.00Tied lowest
Azure · via OpenRouter
azure/global
- Anthropic: Claude Fable 5.1$22.50Tied lowest
Azure · via OpenRouter
azure
- Anthropic: Claude Opus 5$11.25Tied lowest
Azure · via OpenRouter
azure/global
- claude-sonnet-5$4.50Tied lowest
Azure · via OpenRouter
azure/global
- claude-fable-5$22.50Tied lowest
Azure · via OpenRouter
azure
- Anthropic: Claude Opus 4.8$11.25Tied lowest
Azure · via OpenRouter
azure/global
- Anthropic: Claude Opus 4.7$11.25Tied lowest
Azure · via OpenRouter
azure/global
- OpenAI: GPT-5.3-Codex$5.25Tied lowest
Azure · via OpenRouter
azure
- Anthropic: Claude Sonnet 4.6$6.75Tied lowest
Azure · via OpenRouter
azure/global
- Anthropic: Claude Opus 4.6$11.25Tied lowest
Azure · via OpenRouter
azure/global
- OpenAI: GPT-5.2-Codex$5.25Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-5.1-Codex-Max$3.75Tied lowest
Azure · via OpenRouter
azure
- Anthropic: Claude Opus 4.5$11.25Tied lowest
Azure · via OpenRouter
azure/global
- OpenAI: GPT-5.1-Codex$3.75Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-5.1-Codex-Mini$0.75Tied lowest
Azure · via OpenRouter
azure
- Anthropic: Claude Haiku 4.5$2.25Tied lowest
Azure · via OpenRouter
azure/global
- Anthropic: Claude Sonnet 4.5$6.75Tied lowest
Azure · via OpenRouter
azure/global
- OpenAI: GPT-5$3.75Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-4.1$4.00Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-4.1 Mini$0.80Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-4.1 Nano$0.20Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-4o (2024-08-06)$5.00Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-4o-mini$0.30Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-4o$5.00Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-4o (2024-05-13)$8.75Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-3.5 Turbo (older v0613)$1.50Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-3.5 Turbo 16k$4.00Tied lowest
Azure · via OpenRouter
azure
- OpenAI: GPT-4$45.00Tied lowest
Azure · via OpenRouter
azure
Google AI
Via OpenRouter
- Models
- 51
- Endpoints
- 106
- Usable quotes
- 95
Language51
18 token price wins18 tied
1M input + 250K output tokens · USD · Newest first
- Anthropic: Claude Haiku 5.5$0.225Tied lowest
Google · via OpenRouter
google-vertex/global · prompt ≤ 100000 tokens
- Anthropic: Claude Sonnet 5.5$4.50Tied lowest
Google · via OpenRouter
google-vertex/global
- Anthropic: Claude Opus 5.5$9.00Tied lowest
Google · via OpenRouter
google-vertex/global
- Anthropic: Claude Fable 5.1$22.50Tied lowest
Google · via OpenRouter
google-vertex/global
- Anthropic: Claude Opus 5$11.25Tied lowest
Google · via OpenRouter
google-vertex/global
- claude-sonnet-5$4.50Tied lowest
Google · via OpenRouter
google-vertex/global
- claude-fable-5$22.50Tied lowest
Google · via OpenRouter
google-vertex/global
- Anthropic: Claude Opus 4.8$11.25Tied lowest
Google · via OpenRouter
google-vertex/global
- Google: Gemini 3.5 Flash$1.875Tied lowest
Google · via OpenRouter
google-vertex/global/flex · tier=flex
- Anthropic: Claude Opus 4.7$11.25Tied lowest
Google · via OpenRouter
google-vertex/global
- Google: Gemini 3.1 Pro Preview$2.50Tied lowest
Google · via OpenRouter
google-vertex/global/flex · tier=flex · prompt ≤ 200000 tokens
- Anthropic: Claude Sonnet 4.6$6.75Tied lowest
Google · via OpenRouter
google-vertex/global
- Anthropic: Claude Opus 4.6$11.25Tied lowest
Google · via OpenRouter
google-vertex/global
- Anthropic: Claude Opus 4.5$11.25Tied lowest
Google · via OpenRouter
google-vertex/global
- MoonshotAI: Kimi K2 Thinking$1.225Tied lowest
Google · via OpenRouter
google-vertex
- Anthropic: Claude Haiku 4.5$2.25Tied lowest
Google · via OpenRouter
google-vertex/global
- Anthropic: Claude Sonnet 4.5$6.75Tied lowest
Google · via OpenRouter
google-vertex/global · prompt ≤ 200000 tokens
- Google: Gemini 2.5 Flash Lite (batch)$0.10Tied lowest
Google · via OpenRouter
google-vertex/eu
API and web tools
SiliconFlow
Via OpenRouter
- Models
- 40
- Endpoints
- 40
- Usable quotes
- 36
Language40
7 token price wins5 tied
1M input + 250K output tokens · USD · Newest first
- Hy4-preview$1.4593Tied lowest
SiliconFlow · via OpenRouter
siliconflow/fp8 · quantization=fp8
- Qwen: Qwen3.8 2.4T A95B$3.50Tied lowest
SiliconFlow · via OpenRouter
siliconflow/fp8 · quantization=fp8
- Qwen: Qwen3.5-122B-A10B$0.78Lowest collected
SiliconFlow · via OpenRouter
siliconflow/fp8 · quantization=fp8
- StepFun: Step 3.5 Flash$0.175Tied lowest
SiliconFlow · via OpenRouter
siliconflow/fp8 · quantization=fp8
- DeepSeek: DeepSeek V3.2 Exp$0.3725Tied lowest
SiliconFlow · via OpenRouter
siliconflow/fp8 · quantization=fp8
- Qwen: Qwen3 Coder 30B A3B Instruct$0.14Lowest collected
SiliconFlow · via OpenRouter
siliconflow/fp8 · quantization=fp8
- Qwen: Qwen3 30B A3B Instruct 2507$0.165Tied lowest
SiliconFlow · via OpenRouter
siliconflow/fp8 · quantization=fp8
OpenAI-compatible API; serverless; dedicated/custom
Amazon Bedrock
Via OpenRouter
- Models
- 38
- Endpoints
- 61
- Usable quotes
- 59
Language38
14 token price wins14 tied
1M input + 250K output tokens · USD · Newest first
- Anthropic: Claude Haiku 5.5$0.225Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock · prompt ≤ 100000 tokens
- Anthropic: Claude Sonnet 5.5$4.50Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock
- Anthropic: Claude Opus 5.5$9.00Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock
- Anthropic: Claude Fable 5.1$22.50Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock
- Anthropic: Claude Opus 5$11.25Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock
- claude-sonnet-5$4.50Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock/global
- claude-fable-5$22.50Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock
- Anthropic: Claude Opus 4.8$11.25Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock
- Anthropic: Claude Opus 4.7$11.25Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock/global
- Anthropic: Claude Sonnet 4.6$6.75Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock/global
- Anthropic: Claude Opus 4.6$11.25Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock
- Anthropic: Claude Opus 4.5$11.25Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock
- Anthropic: Claude Haiku 4.5$2.25Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock/global
- Anthropic: Claude Sonnet 4.5$6.75Tied lowest
Amazon Bedrock · via OpenRouter
amazon-bedrock · prompt ≤ 200000 tokens
Parasail
Via OpenRouter
- Models
- 38
- Endpoints
- 40
- Usable quotes
- 36
Language38
4 token price wins1 tied
1M input + 250K output tokens · USD · Newest first
- gemma-3-4b-it$0.0525Lowest collected
Parasail · via OpenRouter
parasail/bf16 · quantization=bf16
- Qwen: Qwen2.5 VL 72B Instruct$1.05Lowest collected
Parasail · via OpenRouter
parasail/fp8 · quantization=fp8
- Sao10K: Llama 3 8B Lunaris$0.0525Tied lowest
Parasail · via OpenRouter
parasail/bf16 · quantization=bf16
- MythoMax 13B$0.1075Lowest collected
Parasail · via OpenRouter
parasail/fp16 · quantization=fp16
OpenAI-compatible API; serverless; elastic; dedicated; batch
Venice
Via OpenRouter
- Models
- 38
- Endpoints
- 38
- Usable quotes
- 37
Language38
4 token price wins3 tied
1M input + 250K output tokens · USD · Newest first
- Qwen: Qwen3.8 2.4T A95B$3.50Tied lowest
Venice · via OpenRouter
venice
- MiniMax: MiniMax M2.5$0.5075Lowest collected
Venice · via OpenRouter
venice
- Z.ai: GLM 4.7 Flash$0.16Tied lowest
Venice · via OpenRouter
venice/fp8 · quantization=fp8
- gpt-oss-120b$0.0675Tied lowest
Venice · via OpenRouter
venice/int4 · quantization=int4
Web/mobile; OpenAI-compatible API
Alibaba
Via OpenRouter
- Models
- 33
- Endpoints
- 44
- Usable quotes
- 35
Language33
3 token price wins1 tied
1M input + 250K output tokens · USD · Newest first
- Qwen: Qwen3.8 2.4T A95B$3.50Tied lowest
Alibaba · via OpenRouter
alibaba
- Qwen3.5-27B$0.585Lowest collected
Alibaba · via OpenRouter
alibaba
- Qwen3.5-397B-A17B$0.975Lowest collected
Alibaba · via OpenRouter
alibaba
Anthropic
Via OpenRouter
- Models
- 29
- Endpoints
- 32
- Usable quotes
- 32
Language29
14 token price wins14 tied
1M input + 250K output tokens · USD · Newest first
- Anthropic: Claude Haiku 5.5$0.225Tied lowest
Anthropic · via OpenRouter
anthropic · prompt ≤ 100000 tokens
- Anthropic: Claude Sonnet 5.5$4.50Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Opus 5.5$9.00Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Fable 5.1$22.50Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Opus 5$11.25Tied lowest
Anthropic · via OpenRouter
anthropic
- claude-sonnet-5$4.50Tied lowest
Anthropic · via OpenRouter
anthropic
- claude-fable-5$22.50Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Opus 4.8$11.25Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Opus 4.7$11.25Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Sonnet 4.6$6.75Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Opus 4.6$11.25Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Opus 4.5$11.25Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Haiku 4.5$2.25Tied lowest
Anthropic · via OpenRouter
anthropic
- Anthropic: Claude Sonnet 4.5$6.75Tied lowest
Anthropic · via OpenRouter
anthropic · prompt ≤ 200000 tokens
API and web tools
Mistral
Via OpenRouter
- Models
- 26
- Endpoints
- 57
- Usable quotes
- 57
Language26
Token prices compared on 4 models
GMICloud
Via OpenRouter
- Models
- 25
- Endpoints
- 25
- Usable quotes
- 23
Language25
4 token price wins1 tied
1M input + 250K output tokens · USD · Newest first
- Xiaomi: MiMo-V2.5-Pro$0.4568Lowest collected
GMICloud · via OpenRouter
gmicloud/bf16 · quantization=bf16
- MiniMax: MiniMax M2.7$0.42Lowest collected
GMICloud · via OpenRouter
gmicloud/fp8 · quantization=fp8
- Z.ai: GLM 5$1.08Tied lowest
GMICloud · via OpenRouter
gmicloud/fp8 · quantization=fp8
- DeepSeek-V3.2$0.2862Lowest collected
GMICloud · via OpenRouter
gmicloud/fp8 · quantization=fp8
AtlasCloud
Via OpenRouter
- Models
- 24
- Endpoints
- 24
- Usable quotes
- 23
Language24
Token prices compared on 21 models
Z.ai
Via Hugging Face · OpenRouter
- Models
- 24
- Endpoints
- 33
- Usable quotes
- 13
Language24
3 token price wins3 tied
1M input + 250K output tokens · USD · Newest first
- Z.ai: GLM 5V Turbo$2.20Tied lowest
Z.AI · via OpenRouter
z-ai/fp8 · quantization=fp8
- Z.ai: GLM 5 Turbo$2.20Tied lowest
Z.AI · via OpenRouter
z-ai
- Z.ai: GLM 4.5V$1.05Tied lowest
Z.AI · via OpenRouter
z-ai/fp8 · quantization=fp8
API and web tools
Google AI Studio
Via OpenRouter
- Models
- 23
- Endpoints
- 50
- Usable quotes
- 42
Language17Image6
13 token price wins3 tied
1M input + 250K output tokens · USD · Newest first
- Google: Gemini 4 Argon$2.25Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 3.8 Flash$0.8438Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 3.7 Flash$0.8438Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 3.6 Flash$0.8438Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 3.5 Flash Lite$0.4625Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 3.5 Flash$1.875Tied lowest
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 3.1 Flash Lite$0.3125Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 3.1 Pro Preview$2.50Tied lowest
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex · prompt ≤ 200000 tokens
- Google: Gemini 3 Flash Preview$0.625Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 2.5 Flash Lite$0.10Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- Google: Gemini 2.5 Flash Lite (batch)$0.10Tied lowest
Google AI Studio · via OpenRouter
google-ai-studio
- gemini-2.5-flash$0.4625Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex
- gemini-2.5-pro$1.875Lowest collected
Google AI Studio · via OpenRouter
google-ai-studio/flex · tier=flex · prompt ≤ 200000 tokens
cohere
Via Hugging Face · OpenRouter
- Models
- 22
- Endpoints
- 22
- Usable quotes
- 7
Language22
Token prices compared on 1 models
CoreWeave
Via OpenRouter
- Models
- 22
- Endpoints
- 22
- Usable quotes
- 20
Language22
1 token price win
1M input + 250K output tokens · USD · Newest first
- Google: Gemma 4 31B$0.185Lowest collected
CoreWeave · via OpenRouter
coreweave/fp4 · quantization=fp4
Together AI
Via Hugging Face · OpenRouter
- Models
- 21
- Endpoints
- 33
- Usable quotes
- 33
Language21
2 token price wins2 tied
1M input + 250K output tokens · USD · Newest first
- Meta: Muse Spark Open$2.3125Tied lowest
Together · via OpenRouter
together
- Qwen: Qwen3.8 2.4T A95B$3.50Tied lowest
together · via Hugging Face
Serverless API; dedicated endpoints
Chutes
Direct API · via OpenRouter
- Models
- 20
- Endpoints
- 20
- Usable quotes
- 19
Language20
1 token price win
1M input + 250K output tokens · USD · Newest first
- Qwen: Qwen3.6 27B$0.75Lowest collected
Chutes · via OpenRouter
chutes/fp8 · quantization=fp8
OpenAI-compatible API; SDK
Phala
Via OpenRouter
- Models
- 20
- Endpoints
- 20
- Usable quotes
- 20
Language20
Token prices compared on 18 models
StreamLake
Via OpenRouter
- Models
- 19
- Endpoints
- 19
- Usable quotes
- 18
Language19
3 token price wins2 tied
1M input + 250K output tokens · USD · Newest first
- GLM-5.3-Flash$0.1375Tied lowest
StreamLake · via OpenRouter
streamlake/fp8 · quantization=fp8
- MoonshotAI: Kimi K2.7 Code$1.4625Lowest collected
StreamLake · via OpenRouter
streamlake
- Z.ai: GLM 5$1.08Tied lowest
StreamLake · via OpenRouter
streamlake/fp8 · quantization=fp8
Cloudflare
Via OpenRouter
- Models
- 18
- Endpoints
- 18
- Usable quotes
- 17
Language18
Token prices compared on 13 models
nscale
Via Hugging Face
- Models
- 17
- Endpoints
- 17
- Usable quotes
- 17
Language17
4 token price wins
1M input + 250K output tokens · USD · Newest first
- Qwen3-32B$0.1425Lowest collected
nscale · via Hugging Face
- Qwen3-14B$0.12Lowest collected
nscale · via Hugging Face
- Llama-4-Scout-17B-16E-Instruct$0.1625Lowest collected
nscale · via Hugging Face
- Qwen2.5 Coder 32B Instruct$0.11Lowest collected
nscale · via Hugging Face
DigitalOcean
Via OpenRouter
- Models
- 16
- Endpoints
- 16
- Usable quotes
- 14
Language16
1 token price win
1M input + 250K output tokens · USD · Newest first
- Meta: Llama 4 Maverick$0.3506Lowest collected
DigitalOcean · via OpenRouter
digitalocean
Recraft
Via OpenRouter
- Models
- 16
- Endpoints
- 16
- Usable quotes
- 12
Image16
Image model access
API; web app
baseten
Via Hugging Face · OpenRouter
- Models
- 12
- Endpoints
- 31
- Usable quotes
- 29
Language12
1 token price win1 tied
1M input + 250K output tokens · USD · Newest first
- Meta: Muse Spark Open$2.3125Tied lowest
baseten · via Hugging Face
Claude Platform on AWS
Via OpenRouter
- Models
- 12
- Endpoints
- 12
- Usable quotes
- 12
Language12
12 token price wins12 tied
1M input + 250K output tokens · USD · Newest first
- Anthropic: Claude Haiku 5.5$0.225Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws · prompt ≤ 100000 tokens
- Anthropic: Claude Sonnet 5.5$4.50Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- Anthropic: Claude Opus 5.5$9.00Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- Anthropic: Claude Opus 5$11.25Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- claude-sonnet-5$4.50Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- claude-fable-5$22.50Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- Anthropic: Claude Opus 4.8$11.25Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- Anthropic: Claude Opus 4.7$11.25Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- Anthropic: Claude Sonnet 4.6$6.75Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- Anthropic: Claude Opus 4.6$11.25Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- Anthropic: Claude Opus 4.5$11.25Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws
- Anthropic: Claude Sonnet 4.5$6.75Tied lowest
Claude Platform on AWS · via OpenRouter
claude-on-aws · prompt ≤ 200000 tokens
Fireworks AI
Direct API · via Hugging Face · OpenRouter
- Models
- 12
- Endpoints
- 32
- Usable quotes
- 34
Language12
2 token price wins2 tied
1M input + 250K output tokens · USD · Newest first
- Meta: Muse Spark Open$2.3125Tied lowest
Fireworks · via OpenRouter
fireworks
- Qwen: Qwen3.8 2.4T A95B$3.50Tied lowest
Fireworks AI
Standard · service_tier=default
Serverless API; on-demand GPU deployment
Nebius Token Factory
Via OpenRouter
- Models
- 12
- Endpoints
- 12
- Usable quotes
- 10
Language12
2 token price wins1 tied
1M input + 250K output tokens · USD · Newest first
- Reflection: Beam 1.0 501B A23B$0.50Lowest collected
Nebius · via OpenRouter
nebius/fp8 · quantization=fp8
- Meta: Muse Spark Open$2.3125Tied lowest
Nebius · via OpenRouter
nebius/fp4 · quantization=fp4
API; playground; dedicated endpoints
Baidu
Via OpenRouter
- Models
- 11
- Endpoints
- 12
- Usable quotes
- 12
Language11
7 token price wins
1M input + 250K output tokens · USD · Newest first
- DeepSeek-V4-Pro-0813$0.2333Lowest collected
Baidu · via OpenRouter
baidu/fp8 · quantization=fp8
- DeepSeek-V4-Flash-0731$0.1047Lowest collected
Baidu · via OpenRouter
baidu/fp8 · quantization=fp8
- GLM-5.2$0.3375Lowest collected
Baidu · via OpenRouter
baidu/fp8 · quantization=fp8
- DeepSeek-V4-Pro$0.2662Lowest collected
Baidu · via OpenRouter
baidu/fp8 · quantization=fp8
- DeepSeek-V4-Flash$0.0239Lowest collected
Baidu · via OpenRouter
baidu/fp8 · quantization=fp8
- MoonshotAI: Kimi K2.6$0.8873Lowest collected
Baidu · via OpenRouter
baidu/fp4 · quantization=fp4
- Z.ai: GLM 5.1$1.7225Lowest collected
Baidu · via OpenRouter
baidu/fp8 · quantization=fp8
Relace
Via OpenRouter
- Models
- 11
- Endpoints
- 11
- Usable quotes
- 11
Language11
Token prices compared on 9 models
DekaLLM
Via OpenRouter
- Models
- 10
- Endpoints
- 10
- Usable quotes
- 8
Language10
1 token price win1 tied
1M input + 250K output tokens · USD · Newest first
- Qwen: Qwen3 30B A3B Instruct 2507$0.165Tied lowest
DekaLLM · via OpenRouter
dekallm
Seed
Via OpenRouter
- Models
- 10
- Endpoints
- 10
- Usable quotes
- 9
Language6Image4
Language model access
Darkbloom
Via OpenRouter
- Models
- 9
- Endpoints
- 9
- Usable quotes
- 9
Language9
7 token price wins
1M input + 250K output tokens · USD · Newest first
- Xiaomi: MiMo-V2.6-Flash$0.17Lowest collected
Darkbloom · via OpenRouter
darkbloom/fp4 · quantization=fp4
- NVIDIA: Nemotron 3.5 Lightning$0.055Lowest collected
Darkbloom · via OpenRouter
darkbloom/int4 · quantization=int4
- Qwen3.6-35B-A3B$0.225Lowest collected
Darkbloom · via OpenRouter
darkbloom/fp4 · quantization=fp4
- Google: Gemma 4 26B A4B$0.097Lowest collected
Darkbloom · via OpenRouter
darkbloom
- Qwen3.5-9B$0.1125Lowest collected
Darkbloom · via OpenRouter
darkbloom/fp4 · quantization=fp4
- Qwen3.5-35B-A3B$0.2525Lowest collected
Darkbloom · via OpenRouter
darkbloom/fp4 · quantization=fp4
- gpt-oss-20b$0.0405Lowest collected
Darkbloom · via OpenRouter
darkbloom/fp8 · quantization=fp8
Mancer 2
Via OpenRouter
- Models
- 9
- Endpoints
- 9
- Usable quotes
- 9
Language9
1 token price win
1M input + 250K output tokens · USD · Newest first
- ReMM SLERP 13B$0.5125Lowest collected
Mancer 2 · via OpenRouter
mancer/fp8 · quantization=fp8
Reka
Via OpenRouter
- Models
- 9
- Endpoints
- 9
- Usable quotes
- 9
Language9
Token prices compared on 7 models
scaleway
Via Hugging Face
- Models
- 9
- Endpoints
- 9
- Usable quotes
- 8
Language9
Token prices compared on 8 models
Wafer
Via OpenRouter
- Models
- 9
- Endpoints
- 12
- Usable quotes
- 12
Language9
Token prices compared on 9 models
Crusoe
Via OpenRouter
- Models
- 8
- Endpoints
- 8
- Usable quotes
- 7
Language8
Token prices compared on 7 models
GroqCloud
Direct API · via Hugging Face · OpenRouter
- Models
- 8
- Endpoints
- 13
- Usable quotes
- 11
Language7Audio1
Token prices compared on 7 models
API; playground
InferenceNet
Via OpenRouter
- Models
- 8
- Endpoints
- 9
- Usable quotes
- 9
Language8
1 token price win1 tied
1M input + 250K output tokens · USD · Newest first
- Step-5-Preview$1.675Tied lowest
InferenceNet · via OpenRouter
inference-net/fp4 · quantization=fp4
Minimax
Via OpenRouter
- Models
- 8
- Endpoints
- 11
- Usable quotes
- 11
Language8
2 token price wins
1M input + 250K output tokens · USD · Newest first
- MiniMax: MiniMax M2$0.51Lowest collected
Minimax · via OpenRouter
minimax/fp8 · quantization=fp8
- MiniMax: MiniMax M1$0.95Lowest collected
Minimax · via OpenRouter
minimax
NextBit
Via OpenRouter
- Models
- 8
- Endpoints
- 8
- Usable quotes
- 7
Language8
Token prices compared on 6 models
ovhcloud
Via Hugging Face
- Models
- 8
- Endpoints
- 8
- Usable quotes
- 8
Language8
Token prices compared on 8 models
Sail Research
Via OpenRouter
- Models
- 8
- Endpoints
- 13
- Usable quotes
- 13
Language8
4 token price wins
1M input + 250K output tokens · USD · Newest first
- DeepSeek: DeepSeek V4.1 Flash (batch)$0.0875Lowest collected
Sail Research · via OpenRouter
sail-research/fp4 · quantization=fp4
- Z.ai: GLM 5.3 Flash (batch)$0.095Lowest collected
Sail Research · via OpenRouter
sail-research/fp4 · quantization=fp4
- GLM-5.3$0.8763Lowest collected
Sail Research · via OpenRouter
sail-research/fp8 · quantization=fp8
- Kimi-K3$2.529Lowest collected
Sail Research · via OpenRouter
sail-research/fp4 · quantization=fp4
xAI
Via OpenRouter
- Models
- 8
- Endpoints
- 31
- Usable quotes
- 31
Language8
7 token price wins7 tied
1M input + 250K output tokens · USD · Newest first
- SpaceXAI: Grok 4.7$3.50Tied lowest
xAI · via OpenRouter
xai/zdr · prompt ≤ 200000 tokens
- SpaceXAI: Grok 4.6$3.50Tied lowest
xAI · via OpenRouter
xai/zdr · prompt ≤ 200000 tokens
- SpaceXAI: Grok 4.5$3.50Tied lowest
xAI · via OpenRouter
xai/zdr · prompt ≤ 200000 tokens
- SpaceXAI: Grok Build 0.1$1.50Tied lowest
xAI · via OpenRouter
xai/zdr · prompt ≤ 200000 tokens
- SpaceXAI: Grok 4.3$1.875Tied lowest
xAI · via OpenRouter
xai/zdr · prompt ≤ 200000 tokens
- SpaceXAI: Grok 4.20 Multi-Agent$1.875Tied lowest
xAI · via OpenRouter
xai/zdr · prompt ≤ 200000 tokens
- SpaceXAI: Grok 4.20$1.875Tied lowest
xAI · via OpenRouter
xai/zdr · prompt ≤ 200000 tokens
AkashML
Via OpenRouter
- Models
- 7
- Endpoints
- 7
- Usable quotes
- 7
Language7
Token prices compared on 7 models
Friendli
Via OpenRouter
- Models
- 7
- Endpoints
- 7
- Usable quotes
- 7
Language7
Token prices compared on 7 models
Morph
Via OpenRouter
- Models
- 7
- Endpoints
- 7
- Usable quotes
- 7
Language7
Token prices compared on 5 models
Together AI
Direct API
- Models
- 7
- Endpoints
- 7
- Usable quotes
- 7
Language7
1 token price win1 tied
1M input + 250K output tokens · USD · Newest first
- Meta: Muse Spark Open$2.3125Tied lowest
Together AI
Serverless · quantization=NVFP4
Serverless API; dedicated endpoints
AionLabs
Via OpenRouter
- Models
- 6
- Endpoints
- 6
- Usable quotes
- 6
Language6
Language model access
Inceptron
Via OpenRouter
- Models
- 6
- Endpoints
- 6
- Usable quotes
- 6
Language6
Token prices compared on 6 models
Io Net
Via OpenRouter
- Models
- 6
- Endpoints
- 6
- Usable quotes
- 6
Language6
1 token price win
1M input + 250K output tokens · USD · Newest first
- Mistral: Mistral Nemo$0.022Lowest collected
Io Net · via OpenRouter
io-net/fp16 · quantization=fp16
Makora
Via OpenRouter
- Models
- 6
- Endpoints
- 6
- Usable quotes
- 6
Language6
Token prices compared on 6 models
Meta
Via OpenRouter
- Models
- 6
- Endpoints
- 6
- Usable quotes
- 6
Language6
Language model access
Nvidia
Via OpenRouter
- Models
- 6
- Endpoints
- 6
- Usable quotes
- 2
Language6
Language model access
SambaNova
Via OpenRouter
- Models
- 6
- Endpoints
- 6
- Usable quotes
- 5
Language6
Token prices compared on 5 models
Decart
Via OpenRouter
- Models
- 5
- Endpoints
- 5
- Usable quotes
- 5
Language5
1 token price win
1M input + 250K output tokens · USD · Newest first
- DeepSeek: DeepSeek V4.1 Flash$0.135Lowest collected
Decart · via OpenRouter
decart/fp4 · quantization=fp4
Modal
Via OpenRouter
- Models
- 5
- Endpoints
- 5
- Usable quotes
- 5
Language5
1 token price win1 tied
1M input + 250K output tokens · USD · Newest first
- Meta: Muse Spark Open$2.3125Tied lowest
Modal · via OpenRouter
modal
Perplexity
Via OpenRouter
- Models
- 5
- Endpoints
- 5
- Usable quotes
- 5
Language5
Language model access
Tencent
Via OpenRouter
- Models
- 5
- Endpoints
- 5
- Usable quotes
- 3
Language5
Language model access
Xiaomi
Via OpenRouter
- Models
- 5
- Endpoints
- 5
- Usable quotes
- 4
Language5
Token prices compared on 3 models
Alibaba Cloud Int.
Via OpenRouter
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 4
Image4
Image model access
Google Vertex
Via OpenRouter
- Models
- 4
- Endpoints
- 5
- Usable quotes
- 0
Image4
Image model access
Mara
Via OpenRouter
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 4
Language4
Token prices compared on 4 models
ModelRun
Via OpenRouter
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 4
Language4
Token prices compared on 4 models
OpenInference
Via OpenRouter
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 4
Language4
Token prices compared on 4 models
Poolside
Via OpenRouter
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 4
Language4
Language model access
PrimeIntellect
Via OpenRouter
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 4
Language4
Token prices compared on 2 models
publicai
Via Hugging Face
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 4
Language4
Language model access
Replicate
Direct API
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 0
Image2Audio1Video1
Image model access
Sakana AI
Via OpenRouter
- Models
- 4
- Endpoints
- 4
- Usable quotes
- 4
Language4
Language model access
DeepSeek
Direct API · via OpenRouter
- Models
- 3
- Endpoints
- 4
- Usable quotes
- 0
Language3
Language model access
API and web tools
Ionstream
Via OpenRouter
- Models
- 3
- Endpoints
- 3
- Usable quotes
- 3
Language3
Token prices compared on 3 models
Moonshot AI
Via OpenRouter
- Models
- 3
- Endpoints
- 4
- Usable quotes
- 4
Language3
Token prices compared on 3 models
API and web tools
Near AI
Via OpenRouter
- Models
- 3
- Endpoints
- 3
- Usable quotes
- 3
Language3
1 token price win1 tied
1M input + 250K output tokens · USD · Newest first
- gpt-oss-120b$0.0675Tied lowest
Near AI · via OpenRouter
near-ai/fp4 · quantization=fp4
Tenstorrent
Via OpenRouter
- Models
- 3
- Endpoints
- 3
- Usable quotes
- 3
Language3
1 token price win
1M input + 250K output tokens · USD · Newest first
- Qwen3.8-27B$0.145Lowest collected
Tenstorrent · via OpenRouter
tenstorrent/fp4 · quantization=fp4
Upstage
Via OpenRouter
- Models
- 3
- Endpoints
- 5
- Usable quotes
- 5
Language3
Language model access
Black Forest Labs
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 10
Image2
Image model access
Cerebras Inference
Via Hugging Face · OpenRouter
- Models
- 2
- Endpoints
- 4
- Usable quotes
- 4
Language2
Token prices compared on 2 models
API; playground; partners
Inception
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 2
Language2
Language model access
Liquid
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 2
Language2
Language model access
Nex AGI
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 2
Language2
Language model access
Perceptron
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 2
Language2
Language model access
ScaleDown
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 2
Language2
Language model access
Sourceful
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 5
Image2
Image model access
SpaceXAI
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 0
Image2
Image model access
StepFun
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 2
Language2
2 token price wins2 tied
1M input + 250K output tokens · USD · Newest first
- Step-5-Preview$1.675Tied lowest
StepFun · via OpenRouter
stepfun/fp8 · quantization=fp8
- StepFun: Step 3.7 Flash$0.4875Tied lowest
StepFun · via OpenRouter
stepfun/fp8 · quantization=fp8
Thinking Machines
Via OpenRouter
- Models
- 2
- Endpoints
- 2
- Usable quotes
- 2
Language2
Language model access
Arcee AI
Via OpenRouter
- Models
- 1
- Endpoints
- 1
- Usable quotes
- 1
Language1
Language model access
Tencent Cloud
Via OpenRouter
- Models
- 1
- Endpoints
- 1
- Usable quotes
- 0
Image1
Image model access
Unbiased
Via OpenRouter
- Models
- 1
- Endpoints
- 1
- Usable quotes
- 1
Language1
Language model access
What counts as a price win?
Value ranks providers by their lowest collected cost for 1M input tokens + 250K output tokens on the same model. A model needs quotes from at least two provider groups. Tied providers each receive one win; duplicate routes do not add wins.
Creative price wins require verified matching workloads on the same model and billing unit. Matching default labels alone do not qualify. Conditional prices and degraded endpoints are excluded from wins. These counts describe our collected quotes, not complete provider catalogs.
More places to explore
Researched services with no collected routes yet.
AI/ML APIImages · Video · Audio · LanguageAssemblyAIAudioCartesiaAudioDeepgramAudioElevenLabsAudioHugging Face Inference ProvidersLanguage · CodingKie.aiImages · Video · AudioMeshy3DMistral OCRResearch · LanguageNanoGPTLanguage · CodingRequestyLanguage · CodingRunwareImages · Video · Audio · 3DRunway DevVideo · ImagesSegmindImages · Video · LanguageSunoAudio · Images · LanguageSyntheticCoding · Language · ResearchTopaz LabsImages · VideoTripo3DWaveSpeedAIImages · Video · 3D