8,429 prices on 4,154 listings · last collected 5 h ago · 36 flagged changes in 30 days
Every price, as each platform publishes it
A collector reads every public price on six platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.
Model
Gemini 
Claude 
Qwen 
DeepSeek 
GLM 
Llama 
Mistral 
Kimi 
MiniMax 
Nemotron 
Hunyuan Unit
All 2,608Per second of output 5Per image 32Per million input tokens 866Per million output tokens 859Per million tokens 5Per million cached input tokens (read) 425Per million cache-write tokens 188Per thousand characters 2Per second of compute time 12Per run (default parameters) 200Other units (see the platform’s wording) 14
Showing 401–500 of 859
Per million output tokens100
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouter | Anthropic: Claude Haiku 4.5 (batch) | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | Anthropic: Claude Haiku 5.5Prompt > 100K | $2.5/M out | completion: 0.0000025 / token (>100000) | |
| OpenRouter | ByteDance Seed: Seed 2.1 Turbo | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | Google: Gemini 2.5 Flash | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | Google: Gemini 2.5 FlashReasoning | $2.5/M out | internal_reasoning: 0.0000025 / token | |
| OpenRouter | Google: Gemini 3.5 Flash Lite | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | Google: Gemini 3.5 Flash LiteReasoning | $2.5/M out | internal_reasoning: 0.0000025 / token | |
| OpenRouter | Moondream: Moondream 3 Preview | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | Moondream: Moondream 3.1 | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | MoonshotAI: Kimi K2 0905 | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | MoonshotAI: Kimi K2 Thinking | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra Pro (batch) | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra (batch) | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | SpaceXAI: Grok 4.20 | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | SpaceXAI: Grok 4.20 Multi-Agent | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | SpaceXAI: Grok 4.3 | $2.5/M out | completion: 0.0000025 / token | |
| OpenRouter | Anthropic: Claude Haiku LatestPrompt > 100K | $2.5/M out | completion: 0.0000025 / token (>100000) | |
| Replicate | google/gemini-2.5-flash | $2.5/M out | $2.50 per million output tokens | |
| OpenRouter | Tencent: Hy4 preview | $2.501/M out | completion: 0.000002501 / token | |
| OpenRouter | Qwen: Qwen3 Coder FlashPrompt > 128K | $2.6/M out | completion: 0.0000026 / token (>128000) | |
| OpenRouter | Qwen: Qwen3.5-27B | $2.6/M out | completion: 0.0000026 / token | |
| OpenRouter | StepFun: Step 5 Preview | $2.7/M out | completion: 0.0000027 / token | |
| Replicate | moonshotai/kimi-k2-thinking | $2.7/M out | $2.70 per million output tokens | |
| Replicate | meta/llama-2-70b | $2.75/M out | $2.75 per million output tokens | |
| Replicate | meta/llama-2-70b-chat | $2.75/M out | $2.75 per million output tokens | |
| Replicate | meta/meta-llama-3-70b | $2.75/M out | $2.75 per million output tokens | |
| Replicate | meta/meta-llama-3-70b-instruct | $2.75/M out | $2.75 per million output tokens | |
| APIMart | gemini-3.7-flash | $3/M out | Input $0.6 / Output $3 · Per 1M tokens | |
| APIMart | gemini-3.8-flash | $3/M out | Input $0.6 / Output $3 · Per 1M tokens | |
| kie.ai | gpt-6-1-sol | $3/M out | 600 credits per million tokens ($3)Claims fal charges $10/M out | |
| kie.ai | gpt-6-sol | $3/M out | 600 credits per million tokens ($3.00)Claims fal charges $10/M out | |
| OpenRouter | ByteDance Seed: Seed-2.0-Code | $3/M out | completion: 0.000003 / token | |
| OpenRouter | Elorian: Glimpse | $3/M out | completion: 0.000003 / token | |
| OpenRouter | Google: Gemini 3 Flash Preview | $3/M out | completion: 0.000003 / token | |
| OpenRouter | Google: Gemini 3 Flash PreviewReasoning | $3/M out | internal_reasoning: 0.000003 / token | |
| OpenRouter | Nous: Hermes 4 405B | $3/M out | completion: 0.000003 / token | |
| OpenRouter | Perplexity: Sonar Deep ResearchReasoning | $3/M out | internal_reasoning: 0.000003 / token | |
| OpenRouter | Qwen: Qwen3.6 FlashPrompt > 256K | $3/M out | completion: 0.000003 / token (>256000) | |
| OpenRouter | Relace: Relace Search | $3/M out | completion: 0.000003 / token | |
| Replicate | google/gemini-3-flash | $3/M out | $3 per million output tokens | |
| APIMart | kimi-k2.6 | $3.083/M out | Input $0.7429 / Output $3.083 · Per 1M tokens | |
| APIMart | kimi-k2.7-code | $3.083/M out | Input $0.7429 / Output $3.083 · Per 1M tokens | |
| APIMart | glm-5.2 | $3.1998/M out | Input $0.9142 / Output $3.1998 · Per 1M tokens | |
| OpenRouter | Amazon: Nova Pro 1.0 | $3.2/M out | completion: 0.0000032 / token | |
| OpenRouter | Qwen: Qwen3.6 27B | $3.2/M out | completion: 0.0000032 / token | |
| OpenRouter | Pareto 26.10 | $3.2/M out | completion: 0.0000032 / token | |
| OpenRouter | Z.ai: GLM 5 | $3.2/M out | completion: 0.0000032 / token | |
| OpenRouter | Pareto Latest | $3.2/M out | completion: 0.0000032 / token | |
| Replicate | qwen/qwen3-7-plus256000 | $3.301/M out | $3.301 per million output tokens (256000,) | |
| OpenRouter | MoonshotAI: Kimi K2.5 | $3.325/M out | completion: 0.000003325 / token | |
| kie.ai | gpt-5.6-terra | $3.36/M out | 672 credits per million tokens ($3.36)Claims fal charges $12/M out | |
| OpenRouter | MoonshotAI: Kimi K2.6 | $3.41/M out | completion: 0.00000341 / token | |
| fal | Moondream3 Preview [Caption] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| fal | Moondream3 Preview [Detect] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| fal | Moondream3 Preview [Point] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| fal | Moondream 3 Preview [Query] | $3.5/M out | Your request will cost $0.40 per million input tokens, and $3.50 per million output tokens. | |
| kie.ai | Gemini 3.1 Pro | $3.5/M out | 700 credits per million tokens ($3.50)Claims fal charges $12/M out | |
| kie.ai | Gemini 3 Pro | $3.5/M out | 700 credits per million tokens ($3.5)Claims fal charges $12/M out | |
| kie.ai | gpt-5-2 | $3.5/M out | 700 credits per million tokens ($3.5)Claims fal charges $14/M out | |
| OpenRouter | MoonshotAI: Kimi K2.7 Code | $3.5/M out | completion: 0.0000035 / token | |
| OpenRouter | Qwen: Qwen3 235B A22B Thinking 2507 | $3.5/M out | completion: 0.0000035 / token | |
| APIMart | glm-5.3 | $3.52/M out | Input $1.12 / Output $3.52 · Per 1M tokens | |
| APIMart | o1-mini | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o1-mini-2024-09-12 | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-2025-01-31 | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-2025-01-31-high | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-2025-01-31-low | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-2025-01-31-medium | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-high | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-low | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o3-mini-medium | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o4-mini | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | o4-mini-2025-04-16 | $3.52/M out | Input $0.88 / Output $3.52 · Per 1M tokens | |
| APIMart | gpt-5.4-mini | $3.6/M out | Input $0.6 / Output $3.6 · Per 1M tokens | |
| OpenRouter | Qwen: Qwen3.5 397B A17B | $3.6/M out | completion: 0.0000036 / token | |
| Replicate | moonshotai/kimi-k2.5 | $3.6/M out | $3.60 per million output tokens | |
| OpenRouter | Google: Gemini 3.6 Flash | $3.75/M out | completion: 0.00000375 / token | |
| OpenRouter | Google: Gemini 3.6 FlashReasoning | $3.75/M out | internal_reasoning: 0.00000375 / token | |
| OpenRouter | Google: Gemini 3.7 Flash | $3.75/M out | completion: 0.00000375 / token | |
| OpenRouter | Google: Gemini 3.7 FlashReasoning | $3.75/M out | internal_reasoning: 0.00000375 / token | |
| OpenRouter | Mistral: Mistral Medium 3.5 (batch) | $3.75/M out | completion: 0.00000375 / token | |
| OpenRouter | OpenAI: GPT-6.1 Terra Pro (batch)Prompt > 272K | $3.75/M out | completion: 0.00000375 / token (>272000) | |
| OpenRouter | OpenAI: GPT-6.1 Terra (batch)Prompt > 272K | $3.75/M out | completion: 0.00000375 / token (>272000) | |
| OpenRouter | Google: Gemini Flash Latest | $3.75/M out | completion: 0.00000375 / token | |
| OpenRouter | Google: Gemini Flash LatestReasoning | $3.75/M out | internal_reasoning: 0.00000375 / token | |
| OpenRouter | Qwen: Qwen3.7 PlusPrompt > 256K | $3.84/M out | completion: 0.00000384 / token (>256000) | |
| OpenRouter | Qwen: Qwen3.6 PlusPrompt > 256K | $3.9/M out | completion: 0.0000039 / token (>256000) | |
| APIMart | claude-haiku-4-5-20251001 | $4/M out | Input $0.8 / Output $4 · Per 1M tokens | |
| APIMart | claude-haiku-4-5-20251001-thinking | $4/M out | Input $0.8 / Output $4 · Per 1M tokens | |
| APIMart | gpt-4o-mini-transcribe | $4/M out | Input $1 / Output $4 · Per 1M tokens | |
| APIMart | gpt-6.1-terra | $4/M out | Input $0.8 / Output $4 · Per 1M tokens | |
| kie.ai | claude-sonnet-5-5 | $4/M out | 800 credits per million tokens ($4)Claims fal charges $10/M out | |
| kie.ai | Gemini 4 Argon | $4/M out | 800 credits per million tokens ($4.00)Claims fal charges $10/M out | |
| kie.ai | Kimi K3.1 Pro | $4/M out | 800 credits per million tokens ($4.00)Claims fal charges $10/M out | |
| OpenRouter | ByteDance Seed: Seed 1.6Prompt > 128K | $4/M out | completion: 0.000004 / token (>128000) | |
| OpenRouter | ByteDance Seed: Seed-2.0-LitePrompt > 128K | $4/M out | completion: 0.000004 / token (>128000) | |
| OpenRouter | OpenAI: GPT-3.5 Turbo 16k | $4/M out | completion: 0.000004 / token | |
| OpenRouter | OpenAI: GPT-4.1 (batch) | $4/M out | completion: 0.000004 / token | |
| OpenRouter | OpenAI: o3 (batch) | $4/M out | completion: 0.000004 / token |
