Search and overview
OpenRouter
DeepSeek V3.1 Terminus
Input$0.27
Output$1.00
Context164K
Max Output147K
ReasoningTool CallOpen Weights
2025-09-22
Helicone
DeepSeek V3.1 Terminus
Input$0.27
Output$1.00
Context128K
Max Output16K
ReasoningTool Call
2025-09-22
Helicone
DeepSeek V3.2
Input$0.27
Output$0.41
Context164K
Max Output66K
Tool Call
2025-09-22
Qiniu
DeepSeek/DeepSeek-V3.1-Terminus-Thinking
Input—
Output—
Context128K
Max Output32K
Reasoning
2025-09-22
Qiniu
DeepSeek/DeepSeek-V3.1-Terminus
Input—
Output—
Context128K
Max Output32K
Tool Call
2025-09-22
Kilo Gateway
DeepSeek: DeepSeek V3.1 Terminus
Input$0.27
Output$1.00
Context164K
Max Output147K
ReasoningTool Call
2025-09-22
Alibaba
Qwen3-LiveTranslate Flash Realtime
Input$10.00
Output$10.00
Context53K
Max Output4K
Vision
2025-09-22
Qiniu
x-AI/Grok-4-Fast
Input—
Output—
Context2.0M
Max Output2.0M
ReasoningTool CallVision
2025-09-20
NanoGPT
Manta Pro 1.0
Input$0.06
Output$0.50
Context66K
Max Output33K
2025-09-20
NanoGPT
Manta Flash 1.0
Input$0.02
Output$0.16
Context16K
Max Output16K
2025-09-20
NanoGPT
Manta Mini 1.0
Input$0.02
Output$0.16
Context8K
Max Output8K
2025-09-20
Helicone
xAI Grok 4 Fast Non-Reasoning
Input$0.20
Output$0.50
Context2.0M
Max Output2.0M
Tool CallVision
2025-09-19
Qiniu
OpenAI/GPT-5
Input—
Output—
Context400K
Max Output128K
Tool Call
2025-09-19
SiliconFlow (China)
inclusionAI/Ling-flash-2.0
Input$0.14
Output$0.57
Context131K
Max Output131K
Tool Call
2025-09-18
Amazon Bedrock
Magistral Small 1.2
Input$0.50
Output$1.50
Context128K
Max Output40K
ReasoningTool CallVisionOpen Weights
2025-09-18
SiliconFlow
inclusionAI/Ling-flash-2.0
Input$0.14
Output$0.57
Context131K
Max Output131K
Tool Call
2025-09-18
Poe
Grok-4-Fast-Non-Reasoning
Input$0.20
Output$0.50
Context2.0M
Max Output128K
Tool CallVision
2025-09-16
Poe
Grok-4-Fast-Reasoning
Input$0.20
Output$0.50
Context2.0M
Max Output128K
ReasoningTool CallVision
2025-09-16
Impossibl
GPT-5-Codex
Input$1.25
Output$10.00
Context400K
Max Output128K
ReasoningTool CallVision
2025-09-15
Abacus
GPT-5-Codex
Input$1.25
Output$10.00
Context400K
Max Output128K
ReasoningTool CallVision
2025-09-15
Azure
GPT-5-Codex
Input$1.25
Output$10.00
Context400K
Max Output128K
ReasoningTool CallVision
2025-09-15
Alibaba (China)
Qwen3-Omni Flash
Input$0.06
Output$0.23
Context66K
Max Output16K
ReasoningTool CallVision
2025-09-15
Alibaba (China)
Qwen3-Omni Flash Realtime
Input$0.23
Output$0.92
Context66K
Max Output16K
Tool CallVision
2025-09-15
LLM Gateway
Seed 1.6 (250915) (ByteDance)
Input$0.25
Output$2.00
Context256K
Max Output256K
ReasoningTool CallVision
2025-09-15
Vercel AI Gateway
GPT-5-Codex
Input$1.25
Output$10.00
Context400K
Max Output128K
ReasoningTool CallVision
2025-09-15
Azure Cognitive Services
GPT-5-Codex
Input$1.25
Output$10.00
Context400K
Max Output128K
ReasoningTool CallVision
2025-09-15
OpenCode
GPT-5 Codex
Input$1.07
Output$8.50
Context400K
Max Output128K
ReasoningTool CallVision
2025-09-15
DevPass (LLM Gateway)
Qwen3 VL 235B A22B Thinking
Input$0.98
Output$3.95
Context131K
Max Output8K
ReasoningTool CallVisionOpen Weights
2025-09-15
DevPass (LLM Gateway)
Qwen3 VL 235B A22B Instruct
Input$0.20
Output$0.88
Context262K
Max Output8K
Tool CallVisionOpen Weights
2025-09-15
DevPass (LLM Gateway)
Seed 1.6 (250915)
Input$0.25
Output$2.00
Context256K
Max Output8K
ReasoningTool CallVisionOpen Weights
2025-09-15
QiHang
GPT-5-Mini
Input$0.04
Output$0.29
Context200K
Max Output64K
ReasoningTool CallVision
2025-09-15
Alibaba
Qwen3-Omni Flash
Input$0.43
Output$1.66
Context66K
Max Output16K
ReasoningTool CallVision
2025-09-15
Alibaba
Qwen3-Omni Flash Realtime
Input$0.52
Output$1.99
Context66K
Max Output16K
Tool CallVision
2025-09-15
Qiniu
Qwen3 Next 80B A3B Instruct
Input—
Output—
Context131K
Max Output33K
Tool Call
2025-09-12
Qiniu
Qwen3 Next 80B A3B Thinking
Input—
Output—
Context131K
Max Output33K
ReasoningTool Call
2025-09-12
Hugging Face
Qwen3-Next-80B-A3B-Instruct
Input$0.25
Output$1.00
Context262K
Max Output67K
Tool CallOpen Weights
2025-09-11
Hugging Face
Qwen3-Next-80B-A3B-Thinking
Input$0.30
Output$2.00
Context262K
Max Output131K
Tool CallOpen Weights
2025-09-11
Amazon Bedrock
Qwen3-Next 80B-A3B Instruct
Input$0.15
Output$1.20
Context262K
Max Output262K
Tool CallOpen Weights
2025-09-11
Qiniu
Claude 3.5 Sonnet
Input—
Output—
Context200K
Max Output8K
ReasoningTool CallVision
2025-09-09
Vercel AI Gateway
Seedream 4.0
Input—
Output—
Context0
Max Output0
2025-09-09
Qiniu
Kimi K2 0905
Input—
Output—
Context256K
Max Output100K
Tool Call
2025-09-08
Alibaba (China)
Qwen3-ASR Flash
Input$0.03
Output$0.03
Context53K
Max Output4K
2025-09-08
Alibaba
Qwen3-ASR Flash
Input$0.04
Output$0.04
Context53K
Max Output4K
2025-09-08
Qiniu
Qwen3 Max Preview
Input—
Output—
Context256K
Max Output64K
Tool Call
2025-09-06
Novita AI
Kimi K2 Instruct 0905
Input$0.60
Output$2.50
Context262K
Max Output98K
Tool CallOpen Weights
2025-09-05
OpenRouter
Kimi K2 Instruct 0905
Input$0.60
Output$2.50
Context262K
Max Output98K
Tool CallOpen Weights
2025-09-05
AI/ML API
Kimi K2 0905
Input$1.38
Output$4.13
Context262K
Max Output98K
Tool CallOpen Weights
2025-09-05
iFlow
Kimi-K2-0905
InputFree
OutputFree
Context256K
Max Output64K
Tool Call
2025-09-05
Merge Gateway
Qwen3 Max Preview
Input$1.08
Output$4.80
Context256K
Max Output66K
Tool Call
2025-09-05
Helicone
Kimi K2 (09/05)
Input$0.50
Output$2.00
Context262K
Max Output16K
Tool Call
2025-09-05
Prime Inference
Kimi K2 0905
Input$0.60
Output$2.50
Context262K
Max Output98K
Tool CallOpen Weights
2025-09-05
Kilo Gateway
Kimi K2 Instruct 0905
Input$0.60
Output$2.50
Context262K
Max Output98K
Tool CallOpen Weights
2025-09-05
302.AI
kimi-k2-thinking
Input$0.57
Output$2.30
Context262K
Max Output262K
ReasoningTool Call
2025-09-05
302.AI
kimi-k2-0905-preview
Input$0.63
Output$2.53
Context262K
Max Output262K
Tool Call
2025-09-05
NanoGPT
Llama 4 Scout
Input$0.09
Output$0.46
Context328K
Max Output66K
Tool CallVisionOpen Weights
2025-09-05
NanoGPT
Llama 4 Maverick
Input$0.19
Output$0.65
Context1.0M
Max Output66K
Tool CallVisionOpen Weights
2025-09-05
Hugging Face
Kimi-K2-Instruct-0905
Input$1.00
Output$3.00
Context262K
Max Output16K
Tool CallOpen Weights
2025-09-04
SiliconFlow (China)
ByteDance-Seed/Seed-OSS-36B-Instruct
Input$0.21
Output$0.57
Context262K
Max Output262K
Tool Call
2025-09-04
Groq
Compound Mini
Input—
Output—
Context131K
Max Output8K
2025-09-04
Groq
Compound
Input—
Output—
Context131K
Max Output8K
2025-09-04
| Model | Provider | Input | Output | Context | Max Output | Capabilities | Released |
|---|---|---|---|---|---|---|---|
| DeepSeek V3.1 Terminus | OpenRouter | $0.27 | $1.00 | 164K | 147K | ReasoningTool CallOpen Weights | 2025-09-22 |
| DeepSeek V3.1 Terminus | Helicone | $0.27 | $1.00 | 128K | 16K | ReasoningTool Call | 2025-09-22 |
| DeepSeek V3.2 | Helicone | $0.27 | $0.41 | 164K | 66K | Tool Call | 2025-09-22 |
| DeepSeek/DeepSeek-V3.1-Terminus-Thinking | Qiniu | — | — | 128K | 32K | Reasoning | 2025-09-22 |
| DeepSeek/DeepSeek-V3.1-Terminus | Qiniu | — | — | 128K | 32K | Tool Call | 2025-09-22 |
| DeepSeek: DeepSeek V3.1 Terminus | Kilo Gateway | $0.27 | $1.00 | 164K | 147K | ReasoningTool Call | 2025-09-22 |
| Qwen3-LiveTranslate Flash Realtime | Alibaba | $10.00 | $10.00 | 53K | 4K | Vision | 2025-09-22 |
| x-AI/Grok-4-Fast | Qiniu | — | — | 2.0M | 2.0M | ReasoningTool CallVision | 2025-09-20 |
| Manta Pro 1.0 | NanoGPT | $0.06 | $0.50 | 66K | 33K | 2025-09-20 | |
| Manta Flash 1.0 | NanoGPT | $0.02 | $0.16 | 16K | 16K | 2025-09-20 | |
| Manta Mini 1.0 | NanoGPT | $0.02 | $0.16 | 8K | 8K | 2025-09-20 | |
| xAI Grok 4 Fast Non-Reasoning | Helicone | $0.20 | $0.50 | 2.0M | 2.0M | Tool CallVision | 2025-09-19 |
| OpenAI/GPT-5 | Qiniu | — | — | 400K | 128K | Tool Call | 2025-09-19 |
| inclusionAI/Ling-flash-2.0 | SiliconFlow (China) | $0.14 | $0.57 | 131K | 131K | Tool Call | 2025-09-18 |
| Magistral Small 1.2 | Amazon Bedrock | $0.50 | $1.50 | 128K | 40K | ReasoningTool CallVisionOpen Weights | 2025-09-18 |
| inclusionAI/Ling-flash-2.0 | SiliconFlow | $0.14 | $0.57 | 131K | 131K | Tool Call | 2025-09-18 |
| Grok-4-Fast-Non-Reasoning | Poe | $0.20 | $0.50 | 2.0M | 128K | Tool CallVision | 2025-09-16 |
| Grok-4-Fast-Reasoning | Poe | $0.20 | $0.50 | 2.0M | 128K | ReasoningTool CallVision | 2025-09-16 |
| GPT-5-Codex | Impossibl | $1.25 | $10.00 | 400K | 128K | ReasoningTool CallVision | 2025-09-15 |
| GPT-5-Codex | Abacus | $1.25 | $10.00 | 400K | 128K | ReasoningTool CallVision | 2025-09-15 |
| GPT-5-Codex | Azure | $1.25 | $10.00 | 400K | 128K | ReasoningTool CallVision | 2025-09-15 |
| Qwen3-Omni Flash | Alibaba (China) | $0.06 | $0.23 | 66K | 16K | ReasoningTool CallVision | 2025-09-15 |
| Qwen3-Omni Flash Realtime | Alibaba (China) | $0.23 | $0.92 | 66K | 16K | Tool CallVision | 2025-09-15 |
| Seed 1.6 (250915) (ByteDance) | LLM Gateway | $0.25 | $2.00 | 256K | 256K | ReasoningTool CallVision | 2025-09-15 |
| GPT-5-Codex | Vercel AI Gateway | $1.25 | $10.00 | 400K | 128K | ReasoningTool CallVision | 2025-09-15 |
| GPT-5-Codex | Azure Cognitive Services | $1.25 | $10.00 | 400K | 128K | ReasoningTool CallVision | 2025-09-15 |
| GPT-5 Codex | OpenCode | $1.07 | $8.50 | 400K | 128K | ReasoningTool CallVision | 2025-09-15 |
| Qwen3 VL 235B A22B Thinking | DevPass (LLM Gateway) | $0.98 | $3.95 | 131K | 8K | ReasoningTool CallVisionOpen Weights | 2025-09-15 |
| Qwen3 VL 235B A22B Instruct | DevPass (LLM Gateway) | $0.20 | $0.88 | 262K | 8K | Tool CallVisionOpen Weights | 2025-09-15 |
| Seed 1.6 (250915) | DevPass (LLM Gateway) | $0.25 | $2.00 | 256K | 8K | ReasoningTool CallVisionOpen Weights | 2025-09-15 |
| GPT-5-Mini | QiHang | $0.04 | $0.29 | 200K | 64K | ReasoningTool CallVision | 2025-09-15 |
| Qwen3-Omni Flash | Alibaba | $0.43 | $1.66 | 66K | 16K | ReasoningTool CallVision | 2025-09-15 |
| Qwen3-Omni Flash Realtime | Alibaba | $0.52 | $1.99 | 66K | 16K | Tool CallVision | 2025-09-15 |
| Qwen3 Next 80B A3B Instruct | Qiniu | — | — | 131K | 33K | Tool Call | 2025-09-12 |
| Qwen3 Next 80B A3B Thinking | Qiniu | — | — | 131K | 33K | ReasoningTool Call | 2025-09-12 |
| Qwen3-Next-80B-A3B-Instruct | Hugging Face | $0.25 | $1.00 | 262K | 67K | Tool CallOpen Weights | 2025-09-11 |
| Qwen3-Next-80B-A3B-Thinking | Hugging Face | $0.30 | $2.00 | 262K | 131K | Tool CallOpen Weights | 2025-09-11 |
| Qwen3-Next 80B-A3B Instruct | Amazon Bedrock | $0.15 | $1.20 | 262K | 262K | Tool CallOpen Weights | 2025-09-11 |
| Claude 3.5 Sonnet | Qiniu | — | — | 200K | 8K | ReasoningTool CallVision | 2025-09-09 |
| Seedream 4.0 | Vercel AI Gateway | — | — | 0 | 0 | 2025-09-09 | |
| Kimi K2 0905 | Qiniu | — | — | 256K | 100K | Tool Call | 2025-09-08 |
| Qwen3-ASR Flash | Alibaba (China) | $0.03 | $0.03 | 53K | 4K | 2025-09-08 | |
| Qwen3-ASR Flash | Alibaba | $0.04 | $0.04 | 53K | 4K | 2025-09-08 | |
| Qwen3 Max Preview | Qiniu | — | — | 256K | 64K | Tool Call | 2025-09-06 |
| Kimi K2 Instruct 0905 | Novita AI | $0.60 | $2.50 | 262K | 98K | Tool CallOpen Weights | 2025-09-05 |
| Kimi K2 Instruct 0905 | OpenRouter | $0.60 | $2.50 | 262K | 98K | Tool CallOpen Weights | 2025-09-05 |
| Kimi K2 0905 | AI/ML API | $1.38 | $4.13 | 262K | 98K | Tool CallOpen Weights | 2025-09-05 |
| Kimi-K2-0905 | iFlow | Free | Free | 256K | 64K | Tool Call | 2025-09-05 |
| Qwen3 Max Preview | Merge Gateway | $1.08 | $4.80 | 256K | 66K | Tool Call | 2025-09-05 |
| Kimi K2 (09/05) | Helicone | $0.50 | $2.00 | 262K | 16K | Tool Call | 2025-09-05 |
| Kimi K2 0905 | Prime Inference | $0.60 | $2.50 | 262K | 98K | Tool CallOpen Weights | 2025-09-05 |
| Kimi K2 Instruct 0905 | Kilo Gateway | $0.60 | $2.50 | 262K | 98K | Tool CallOpen Weights | 2025-09-05 |
| kimi-k2-thinking | 302.AI | $0.57 | $2.30 | 262K | 262K | ReasoningTool Call | 2025-09-05 |
| kimi-k2-0905-preview | 302.AI | $0.63 | $2.53 | 262K | 262K | Tool Call | 2025-09-05 |
| Llama 4 Scout | NanoGPT | $0.09 | $0.46 | 328K | 66K | Tool CallVisionOpen Weights | 2025-09-05 |
| Llama 4 Maverick | NanoGPT | $0.19 | $0.65 | 1.0M | 66K | Tool CallVisionOpen Weights | 2025-09-05 |
| Kimi-K2-Instruct-0905 | Hugging Face | $1.00 | $3.00 | 262K | 16K | Tool CallOpen Weights | 2025-09-04 |
| ByteDance-Seed/Seed-OSS-36B-Instruct | SiliconFlow (China) | $0.21 | $0.57 | 262K | 262K | Tool Call | 2025-09-04 |
| Compound Mini | Groq | — | — | 131K | 8K | 2025-09-04 | |
| Compound | Groq | — | — | 131K | 8K | 2025-09-04 |