Search and overview
Alibaba (China)
DeepSeek R1 Distill Qwen 7B
Input$0.07
Output$0.14
Context33K
Max Output16K
ReasoningTool Call
2025-01-01
Alibaba (China)
DeepSeek R1 Distill Qwen 32B
Input$0.29
Output$0.86
Context33K
Max Output16K
ReasoningTool Call
2025-01-01
Alibaba (China)
DeepSeek R1 Distill Qwen 1.5B
InputFree
OutputFree
Context33K
Max Output16K
ReasoningTool Call
2025-01-01
Alibaba (China)
DeepSeek V3.2 Exp
Input$0.29
Output$0.43
Context131K
Max Output66K
Tool Call
2025-01-01
Alibaba (China)
DeepSeek R1 Distill Qwen 14B
Input$0.14
Output$0.43
Context33K
Max Output16K
ReasoningTool Call
2025-01-01
StepFun (Global)
Step 2 (16K)
Input$5.21
Output$16.44
Context16K
Max Output8K
Tool Call
2025-01-01
StepFun (Global)
Step 1 (32K)
Input$2.05
Output$9.59
Context33K
Max Output33K
Tool Call
2025-01-01
Inference
Osmosis Structure 0.6B
Input$0.10
Output$0.50
Context4K
Max Output2K
Tool CallOpen Weights
2025-01-01
Inference
Llama 3.2 11B Vision Instruct
Input$0.06
Output$0.06
Context16K
Max Output4K
Tool CallVisionOpen Weights
2025-01-01
Inference
Llama 3.1 8B Instruct
Input$0.03
Output$0.03
Context16K
Max Output4K
Tool CallOpen Weights
2025-01-01
Inference
Llama 3.2 3B Instruct
Input$0.02
Output$0.02
Context16K
Max Output4K
Tool CallOpen Weights
2025-01-01
Inference
Llama 3.2 1B Instruct
Input$0.01
Output$0.01
Context16K
Max Output4K
Tool CallOpen Weights
2025-01-01
Inference
Qwen 3 Embedding 4B
Input$0.01
OutputFree
Context32K
Max Output2K
Open Weights
2025-01-01
Inference
Qwen 2.5 7B Vision Instruct
Input$0.20
Output$0.20
Context125K
Max Output4K
Tool CallVisionOpen Weights
2025-01-01
Inference
Mistral Nemo 12B Instruct
Input$0.04
Output$0.10
Context16K
Max Output4K
Tool CallOpen Weights
2025-01-01
Inference
Google Gemma 3
Input$0.15
Output$0.30
Context125K
Max Output4K
Tool CallVisionOpen Weights
2025-01-01
Azure Cognitive Services
Codestral 25.01
Input$0.30
Output$0.90
Context256K
Max Output256K
Tool Call
2025-01-01
GreenPT
Green S
Input$0.004
OutputFree
Context0
Max Output8K
2025-01
Alibaba (China)
Qwen-MT Plus
Input$0.26
Output$0.78
Context16K
Max Output8K
2025-01
Alibaba (China)
Qwen-MT Turbo
Input$0.10
Output$0.28
Context16K
Max Output8K
2025-01
Alibaba
Qwen-MT Plus
Input$2.46
Output$7.37
Context16K
Max Output8K
2025-01
Alibaba
Qwen-MT Turbo
Input$0.16
Output$0.49
Context16K
Max Output8K
2025-01
LucidQuery
LucidNova RF1 100B
Input$2.00
Output$5.00
Context120K
Max Output8K
ReasoningTool Call
2024-12-28
Hugging Face
DeepSeek-V3
Input$0.40
Output$1.30
Context64K
Max Output8K
Tool CallOpen Weights
2024-12-26
SiliconFlow (China)
deepseek-ai/DeepSeek-V3
Input$0.25
Output$1.00
Context164K
Max Output164K
Tool Call
2024-12-26
SiliconFlow (China)
Pro/deepseek-ai/DeepSeek-V3
Input$0.25
Output$1.00
Context164K
Max Output164K
Tool Call
2024-12-26
Novita AI
DeepSeek-V3
Input$0.89
Output$0.89
Context64K
Max Output16K
Tool CallOpen Weights
2024-12-26
D.Run (China)
DeepSeek V3
Input$0.28
Output$1.10
Context131K
Max Output8K
Tool CallOpen Weights
2024-12-26
Eden AI
DeepSeek-V3 (Deep Infra)
Input$0.32
Output$0.89
Context164K
Max Output8K
Tool CallOpen Weights
2024-12-26
Pioneer
DeepSeek-V3
Input$0.27
Output$1.12
Context164K
Max Output8K
Tool CallOpen Weights
2024-12-26
iFlow
DeepSeek-V3
InputFree
OutputFree
Context128K
Max Output32K
Tool CallOpen Weights
2024-12-26
Merge Gateway
DeepSeek V3
Input$0.27
Output$1.10
Context164K
Max Output82K
Tool CallOpen Weights
2024-12-26
Deep Infra
DeepSeek-V3
Input$0.32
Output$0.89
Context164K
Max Output8K
Tool CallOpen Weights
2024-12-26
Helicone
DeepSeek V3
Input$0.56
Output$1.68
Context128K
Max Output8K
Tool Call
2024-12-26
DigitalOcean
DeepSeek V3
Input—
Output—
Context164K
Max Output131K
Tool CallOpen Weights
2024-12-26
Alibaba (China)
siliconflow/deepseek-v3-0324
Input$0.25
Output$1.00
Context164K
Max Output164K
Tool Call
2024-12-26
SiliconFlow
deepseek-ai/DeepSeek-V3
Input$0.25
Output$1.00
Context164K
Max Output164K
Tool Call
2024-12-26
OpenRouter
o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
Eden AI
o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
AI/ML API
o3 Mini
Input$1.43
Output$5.72
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
Impossibl
o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
Abacus
o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
Merge Gateway
o3 Mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
DigitalOcean
OpenAI o3 mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool CallVision
2024-12-20
AnyAPI
o3-mini
Input—
Output—
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
Cloudflare AI Gateway
o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
LLM Gateway
o3 Mini (OpenAI)
Input$1.10
Output$4.40
Context200K
Max Output100K
2024-12-20
NEAR AI Cloud
o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
Kilo Gateway
o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
DevPass (LLM Gateway)
o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
NanoGPT
OpenAI o3-mini
Input$1.10
Output$4.40
Context200K
Max Output100K
ReasoningTool Call
2024-12-20
OpenRouter
Llama 3.3 Euryale 70B
Input$0.65
Output$0.75
Context131K
Max Output16K
Open Weights
2024-12-18
AI/ML API
Llama 3.3 Euryale 70B
Input$0.89
Output$1.03
Context131K
Max Output16K
Open Weights
2024-12-18
Kilo Gateway
Sao10K: Llama 3.3 Euryale 70B
Input$0.65
Output$0.75
Context131K
Max Output16K
2024-12-18
Poe
o1
Input$14.00
Output$54.00
Context200K
Max Output100K
ReasoningTool CallVision
2024-12-18
Azure
Phi-4-mini
Input$0.07
Output$0.30
Context128K
Max Output4K
Tool CallOpen Weights
2024-12-11
Azure
Phi-4
Input$0.13
Output$0.50
Context128K
Max Output4K
Open Weights
2024-12-11
Azure
Phi-4-reasoning-plus
Input$0.13
Output$0.50
Context32K
Max Output4K
ReasoningOpen Weights
2024-12-11
Azure
Phi-4-multimodal
Input$0.08
Output$0.32
Context128K
Max Output4K
VisionOpen Weights
2024-12-11
Azure
Phi-4-mini-reasoning
Input$0.07
Output$0.30
Context128K
Max Output4K
ReasoningTool CallOpen Weights
2024-12-11
| Model | Provider | Input | Output | Context | Max Output | Capabilities | Released |
|---|---|---|---|---|---|---|---|
| DeepSeek R1 Distill Qwen 7B | Alibaba (China) | $0.07 | $0.14 | 33K | 16K | ReasoningTool Call | 2025-01-01 |
| DeepSeek R1 Distill Qwen 32B | Alibaba (China) | $0.29 | $0.86 | 33K | 16K | ReasoningTool Call | 2025-01-01 |
| DeepSeek R1 Distill Qwen 1.5B | Alibaba (China) | Free | Free | 33K | 16K | ReasoningTool Call | 2025-01-01 |
| DeepSeek V3.2 Exp | Alibaba (China) | $0.29 | $0.43 | 131K | 66K | Tool Call | 2025-01-01 |
| DeepSeek R1 Distill Qwen 14B | Alibaba (China) | $0.14 | $0.43 | 33K | 16K | ReasoningTool Call | 2025-01-01 |
| Step 2 (16K) | StepFun (Global) | $5.21 | $16.44 | 16K | 8K | Tool Call | 2025-01-01 |
| Step 1 (32K) | StepFun (Global) | $2.05 | $9.59 | 33K | 33K | Tool Call | 2025-01-01 |
| Osmosis Structure 0.6B | Inference | $0.10 | $0.50 | 4K | 2K | Tool CallOpen Weights | 2025-01-01 |
| Llama 3.2 11B Vision Instruct | Inference | $0.06 | $0.06 | 16K | 4K | Tool CallVisionOpen Weights | 2025-01-01 |
| Llama 3.1 8B Instruct | Inference | $0.03 | $0.03 | 16K | 4K | Tool CallOpen Weights | 2025-01-01 |
| Llama 3.2 3B Instruct | Inference | $0.02 | $0.02 | 16K | 4K | Tool CallOpen Weights | 2025-01-01 |
| Llama 3.2 1B Instruct | Inference | $0.01 | $0.01 | 16K | 4K | Tool CallOpen Weights | 2025-01-01 |
| Qwen 3 Embedding 4B | Inference | $0.01 | Free | 32K | 2K | Open Weights | 2025-01-01 |
| Qwen 2.5 7B Vision Instruct | Inference | $0.20 | $0.20 | 125K | 4K | Tool CallVisionOpen Weights | 2025-01-01 |
| Mistral Nemo 12B Instruct | Inference | $0.04 | $0.10 | 16K | 4K | Tool CallOpen Weights | 2025-01-01 |
| Google Gemma 3 | Inference | $0.15 | $0.30 | 125K | 4K | Tool CallVisionOpen Weights | 2025-01-01 |
| Codestral 25.01 | Azure Cognitive Services | $0.30 | $0.90 | 256K | 256K | Tool Call | 2025-01-01 |
| Green S | GreenPT | $0.004 | Free | 0 | 8K | 2025-01 | |
| Qwen-MT Plus | Alibaba (China) | $0.26 | $0.78 | 16K | 8K | 2025-01 | |
| Qwen-MT Turbo | Alibaba (China) | $0.10 | $0.28 | 16K | 8K | 2025-01 | |
| Qwen-MT Plus | Alibaba | $2.46 | $7.37 | 16K | 8K | 2025-01 | |
| Qwen-MT Turbo | Alibaba | $0.16 | $0.49 | 16K | 8K | 2025-01 | |
| LucidNova RF1 100B | LucidQuery | $2.00 | $5.00 | 120K | 8K | ReasoningTool Call | 2024-12-28 |
| DeepSeek-V3 | Hugging Face | $0.40 | $1.30 | 64K | 8K | Tool CallOpen Weights | 2024-12-26 |
| deepseek-ai/DeepSeek-V3 | SiliconFlow (China) | $0.25 | $1.00 | 164K | 164K | Tool Call | 2024-12-26 |
| Pro/deepseek-ai/DeepSeek-V3 | SiliconFlow (China) | $0.25 | $1.00 | 164K | 164K | Tool Call | 2024-12-26 |
| DeepSeek-V3 | Novita AI | $0.89 | $0.89 | 64K | 16K | Tool CallOpen Weights | 2024-12-26 |
| DeepSeek V3 | D.Run (China) | $0.28 | $1.10 | 131K | 8K | Tool CallOpen Weights | 2024-12-26 |
| DeepSeek-V3 (Deep Infra) | Eden AI | $0.32 | $0.89 | 164K | 8K | Tool CallOpen Weights | 2024-12-26 |
| DeepSeek-V3 | Pioneer | $0.27 | $1.12 | 164K | 8K | Tool CallOpen Weights | 2024-12-26 |
| DeepSeek-V3 | iFlow | Free | Free | 128K | 32K | Tool CallOpen Weights | 2024-12-26 |
| DeepSeek V3 | Merge Gateway | $0.27 | $1.10 | 164K | 82K | Tool CallOpen Weights | 2024-12-26 |
| DeepSeek-V3 | Deep Infra | $0.32 | $0.89 | 164K | 8K | Tool CallOpen Weights | 2024-12-26 |
| DeepSeek V3 | Helicone | $0.56 | $1.68 | 128K | 8K | Tool Call | 2024-12-26 |
| DeepSeek V3 | DigitalOcean | — | — | 164K | 131K | Tool CallOpen Weights | 2024-12-26 |
| siliconflow/deepseek-v3-0324 | Alibaba (China) | $0.25 | $1.00 | 164K | 164K | Tool Call | 2024-12-26 |
| deepseek-ai/DeepSeek-V3 | SiliconFlow | $0.25 | $1.00 | 164K | 164K | Tool Call | 2024-12-26 |
| o3-mini | OpenRouter | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3-mini | Eden AI | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3 Mini | AI/ML API | $1.43 | $5.72 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3-mini | Impossibl | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3-mini | Abacus | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3 Mini | Merge Gateway | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| OpenAI o3 mini | DigitalOcean | $1.10 | $4.40 | 200K | 100K | ReasoningTool CallVision | 2024-12-20 |
| o3-mini | AnyAPI | — | — | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3-mini | Cloudflare AI Gateway | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3 Mini (OpenAI) | LLM Gateway | $1.10 | $4.40 | 200K | 100K | 2024-12-20 | |
| o3-mini | NEAR AI Cloud | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3-mini | Kilo Gateway | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| o3-mini | DevPass (LLM Gateway) | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| OpenAI o3-mini | NanoGPT | $1.10 | $4.40 | 200K | 100K | ReasoningTool Call | 2024-12-20 |
| Llama 3.3 Euryale 70B | OpenRouter | $0.65 | $0.75 | 131K | 16K | Open Weights | 2024-12-18 |
| Llama 3.3 Euryale 70B | AI/ML API | $0.89 | $1.03 | 131K | 16K | Open Weights | 2024-12-18 |
| Sao10K: Llama 3.3 Euryale 70B | Kilo Gateway | $0.65 | $0.75 | 131K | 16K | 2024-12-18 | |
| o1 | Poe | $14.00 | $54.00 | 200K | 100K | ReasoningTool CallVision | 2024-12-18 |
| Phi-4-mini | Azure | $0.07 | $0.30 | 128K | 4K | Tool CallOpen Weights | 2024-12-11 |
| Phi-4 | Azure | $0.13 | $0.50 | 128K | 4K | Open Weights | 2024-12-11 |
| Phi-4-reasoning-plus | Azure | $0.13 | $0.50 | 32K | 4K | ReasoningOpen Weights | 2024-12-11 |
| Phi-4-multimodal | Azure | $0.08 | $0.32 | 128K | 4K | VisionOpen Weights | 2024-12-11 |
| Phi-4-mini-reasoning | Azure | $0.07 | $0.30 | 128K | 4K | ReasoningTool CallOpen Weights | 2024-12-11 |