Data source: models.dev. Providers may change prices and availability; check the provider's information before use. models.dev
Perplexity: Sonar Pro Search · Kilo Gateway
Model ID: kilo/perplexity/sonar-pro-search. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
Sonar Pro Search · OpenRouter
Model ID: openrouter/perplexity/sonar-pro-search. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
GPT OSS Safeguard 20B · NanoGPT
Model ID: nano-gpt/openai/gpt-oss-safeguard-20b. Context window: 128000 tokens. Input / output per million tokens: $0.075 / $0.3.
Safety GPT OSS 20B · Groq
Model ID: groq/openai/gpt-oss-safeguard-20b. Context window: 131072 tokens. Input / output per million tokens: $0.075 / $0.3.
gpt-oss-safeguard-20b · Vercel AI Gateway
Model ID: vercel/openai/gpt-oss-safeguard-20b. Context window: 128000 tokens. Input / output per million tokens: $0.07 / $0.2.
GPT OSS Safeguard 120B · Vercel AI Gateway
Model ID: vercel/openai/gpt-oss-safeguard-120b. Context window: 128000 tokens. Input / output per million tokens: $0.15 / $0.6.
GPT OSS Safeguard 20B · Kilo Gateway
Model ID: kilo/openai/gpt-oss-safeguard-20b. Context window: 131072 tokens. Input / output per million tokens: $0.075 / $0.3.
GPT OSS Safeguard 20B · Amazon Bedrock
Model ID: amazon-bedrock/openai.gpt-oss-safeguard-20b. Context window: 128000 tokens. Input / output per million tokens: $0.07 / $0.2.
GPT OSS Safeguard 120B · Amazon Bedrock
Model ID: amazon-bedrock/openai.gpt-oss-safeguard-120b. Context window: 128000 tokens. Input / output per million tokens: $0.15 / $0.6.
GPT OSS Safeguard 20B · Merge Gateway
Model ID: merge-gateway/openai/gpt-oss-safeguard-20b. Context window: 4096 tokens. Input / output per million tokens: $0.07 / $0.2.
GPT OSS Safeguard 120B · Merge Gateway
Model ID: merge-gateway/openai/gpt-oss-safeguard-120b. Context window: 4096 tokens. Input / output per million tokens: $0.15 / $0.6.
GPT OSS Safeguard 20B · OpenRouter
Model ID: openrouter/openai/gpt-oss-safeguard-20b. Context window: 131072 tokens. Input / output per million tokens: $0.075 / $0.3.
GPT OSS Safeguard 120B · Cortecs
Model ID: cortecs/gpt-oss-safeguard-120b. Context window: 128000 tokens. Input / output per million tokens: $0.179 / $0.697.
gpt-oss-safeguard-120b · Tinfoil
Model ID: tinfoil/gpt-oss-safeguard-120b. Context window: 131072 tokens. Input / output per million tokens: $0.15 / $0.6.
GPT OSS Safeguard 20B (Groq) · Eden AI
Model ID: edenai/groq/openai/gpt-oss-safeguard-20b. Context window: 131072 tokens. Input / output per million tokens: $0.075 / $0.3.
GPT OSS Safeguard 20B (Amazon Bedrock) · Eden AI
Model ID: edenai/amazon/openai.gpt-oss-safeguard-20b. Context window: 128000 tokens. Input / output per million tokens: $0.07 / $0.2.
GPT OSS Safeguard 20B (Amazon Bedrock, US) · Eden AI
Model ID: edenai/amazon/openai.gpt-oss-safeguard-20b@us. Context window: 128000 tokens. Input / output per million tokens: $0.07 / $0.2.
Minimax/Minimax-M2 · Qiniu
Model ID: qiniu-ai/minimax/minimax-m2. Context window: 200000 tokens. Input / output per million tokens: — / —.
Nemotron-nano 12b v2-vl · DigitalOcean
Model ID: digitalocean/nemotron-nano-12b-v2-vl. Context window: 128000 tokens. Input / output per million tokens: $0.2 / $0.6.
Nemotron Nano 12B v2 VL · Nvidia
Model ID: nvidia/nvidia/nemotron-nano-12b-v2-vl. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
llama-3.1-nemotron-safety-guard-8b-v3 · Nvidia
Model ID: nvidia/nvidia/llama-3.1-nemotron-safety-guard-8b-v3. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Qwen3-Coder-30B-A3B-Instruct · OVHcloud AI Endpoints
Model ID: ovhcloud/qwen3-coder-30b-a3b-instruct. Context window: 262144 tokens. Input / output per million tokens: $0.07 / $0.26.
Nvidia Nemotron Nano 12B V2 VL · Vercel AI Gateway
Model ID: vercel/nvidia/nemotron-nano-12b-v2-vl. Context window: 131072 tokens. Input / output per million tokens: $0.2 / $0.6.
NVIDIA Nemotron Nano 12B v2 VL BF16 · Amazon Bedrock
Model ID: amazon-bedrock/nvidia.nemotron-nano-12b-v2. Context window: 128000 tokens. Input / output per million tokens: $0.2 / $0.6.
MiniMax M2 · NanoGPT
Model ID: nano-gpt/minimax/minimax-m2. Context window: 200000 tokens. Input / output per million tokens: $0.17 / $1.53.
MiniMax M2 (MiniMax) · LLM Gateway
Model ID: llmgateway-providers/minimax/minimax-m2. Context window: 196608 tokens. Input / output per million tokens: $0.2 / $1.
MiniMax-M2 · NovitaAI
Model ID: novita-ai/minimax/minimax-m2. Context window: 204800 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax-M2 · MiniMax Token Plan (minimax.cn)
Model ID: minimax-cn-coding-plan/MiniMax-M2. Context window: 204800 tokens. Input / output per million tokens: $0 / $0.
MiniMax-M2 · Hugging Face
Model ID: huggingface/MiniMaxAI/MiniMax-M2. Context window: 204800 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax-M2 · MiniMax (minimax.io)
Model ID: minimax/MiniMax-M2. Context window: 204800 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax M2 · Vercel AI Gateway
Model ID: vercel/minimax/minimax-m2. Context window: 205000 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax-M2 · DevPass (LLM Gateway)
Model ID: llmgateway/minimax-m2. Context window: 196608 tokens. Input / output per million tokens: $0.2 / $1.
MiniMax-M2 · MiniMax Token Plan (minimax.io)
Model ID: minimax-coding-plan/MiniMax-M2. Context window: 204800 tokens. Input / output per million tokens: $0 / $0.
MiniMax-M2 · Kilo Gateway
Model ID: kilo/minimax/minimax-m2. Context window: 204800 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax-M2 · Amazon Bedrock
Model ID: amazon-bedrock/minimax.minimax-m2. Context window: 204608 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax M2 · Merge Gateway
Model ID: merge-gateway/minimax/minimax-m2. Context window: 204800 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax-M2 · OpenRouter
Model ID: openrouter/minimax/minimax-m2. Context window: 204800 tokens. Input / output per million tokens: $0.255 / $1.02.
MiniMax-M2 · Ofox
Model ID: ofox/minimax/minimax-m2. Context window: 204800 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax M2 · ZenMux
Model ID: zenmux/minimax/minimax-m2. Context window: 204000 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax-M2 · MiniMax (minimax.cn)
Model ID: minimax-cn/MiniMax-M2. Context window: 204800 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax-M2 · Cortecs
Model ID: cortecs/minimax-m2. Context window: 400000 tokens. Input / output per million tokens: $0.349 / $1.405.
MiniMax-M2 · Eden AI
Model ID: edenai/minimax/MiniMax-M2. Context window: 204800 tokens. Input / output per million tokens: $0.3 / $1.2.
MiniMax-M2 · 302.AI
Model ID: 302ai/MiniMax-M2. Context window: 1000000 tokens. Input / output per million tokens: $0.33 / $1.32.
DeepSeek-OCR · NovitaAI
Model ID: novita-ai/deepseek/deepseek-ocr. Context window: 8192 tokens. Input / output per million tokens: $0.03 / $0.03.
Seedance v1.0 Pro Fast · Vercel AI Gateway
Model ID: vercel/bytedance/seedance-v1.0-pro-fast. Context window: 0 tokens. Input / output per million tokens: — / —.
Qwen: Qwen3 VL 32B Instruct · Kilo Gateway
Model ID: kilo/qwen/qwen3-vl-32b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.104 / $0.416.
Qwen3 VL 32B Instruct · OpenRouter
Model ID: openrouter/qwen/qwen3-vl-32b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.104 / $0.416.
Gemini 2.5 Flash Image · Qiniu
Model ID: qiniu-ai/gemini-2.5-flash-image. Context window: 32768 tokens. Input / output per million tokens: — / —.
PaddleOCR-VL · NovitaAI
Model ID: novita-ai/paddlepaddle/paddleocr-vl. Context window: 16384 tokens. Input / output per million tokens: $0.02 / $0.02.
Qwen/Qwen3-VL-32B-Instruct · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-VL-32B-Instruct. Context window: 262000 tokens. Input / output per million tokens: $0.2 / $0.6.
Qwen/Qwen3-VL-32B-Thinking · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-VL-32B-Thinking. Context window: 262000 tokens. Input / output per million tokens: $0.2 / $1.5.
Qwen/Qwen3-VL-32B-Thinking · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-VL-32B-Thinking. Context window: 262000 tokens. Input / output per million tokens: $0.2 / $1.5.
Qwen/Qwen3-VL-32B-Instruct · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-VL-32B-Instruct. Context window: 262000 tokens. Input / output per million tokens: $0.2 / $0.6.
deepseek-ai/DeepSeek-OCR · SiliconFlow (China)
Model ID: siliconflow-cn/deepseek-ai/DeepSeek-OCR. Context window: 8192 tokens. Input / output per million tokens: $0 / $0.
DeepSeek OCR · Clarifai
Model ID: clarifai/deepseek-ai/deepseek-ocr/models/DeepSeek-OCR. Context window: 8192 tokens. Input / output per million tokens: $0.2 / $0.7.
S1 · Vercel AI Gateway
Model ID: vercel/fish-audio/s1. Context window: 0 tokens. Input / output per million tokens: — / —.
IBM: Granite 4.0 Micro · Kilo Gateway
Model ID: kilo/ibm-granite/granite-4.0-h-micro. Context window: 131000 tokens. Input / output per million tokens: $0.017 / $0.112.
Granite 4.0 Micro · OpenRouter
Model ID: openrouter/ibm-granite/granite-4.0-h-micro. Context window: 131000 tokens. Input / output per million tokens: $0.017 / $0.112.
qwen/qwen3-vl-8b-instruct · NovitaAI
Model ID: novita-ai/qwen/qwen3-vl-8b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.08 / $0.5.
Big Pickle · OpenCode Zen
Model ID: opencode/big-pickle. Context window: 200000 tokens. Input / output per million tokens: $0 / $0.
Claude 4.5 Haiku · Qiniu
Model ID: qiniu-ai/claude-4.5-haiku. Context window: 200000 tokens. Input / output per million tokens: — / —.
OpenAI: GPT-5 Image Mini · Kilo Gateway
Model ID: kilo/openai/gpt-5-image-mini. Context window: 400000 tokens. Input / output per million tokens: $2.5 / $2.
GPT-5 Image Mini · OpenRouter
Model ID: openrouter/openai/gpt-5-image-mini. Context window: 400000 tokens. Input / output per million tokens: $2.5 / $2.
claude-haiku-4-5-20251001 · 302.AI
Model ID: 302ai/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
claude-haiku-4-5 · 302.AI
Model ID: 302ai/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 Thinking · NanoGPT
Model ID: nano-gpt/anthropic/claude-haiku-4.5:thinking. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · NanoGPT
Model ID: nano-gpt/anthropic/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · DigitalOcean
Model ID: digitalocean/anthropic-claude-4.5-haiku. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Anthropic Claude Haiku 4.5 · DigitalOcean
Model ID: digitalocean/anthropic-claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Qwen/Qwen3-VL-8B-Instruct · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-VL-8B-Instruct. Context window: 262000 tokens. Input / output per million tokens: $0.18 / $0.68.
Claude Haiku 4.5 · FreeModel
Model ID: freemodel/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Impossibl
Model ID: impossibl/anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (Vertex AI (Anthropic)) · LLM Gateway
Model ID: llmgateway-providers/vertex-anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Qwen3 VL Flash (Alibaba Cloud) · LLM Gateway
Model ID: llmgateway-providers/alibaba/qwen3-vl-flash. Context window: 262144 tokens. Input / output per million tokens: $0.05 / $0.4.
Claude Haiku 4.5 (2025-10-01) (AWS Bedrock) · LLM Gateway
Model ID: llmgateway-providers/aws-bedrock/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (AWS Bedrock) · LLM Gateway
Model ID: llmgateway-providers/aws-bedrock/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (2025-10-01) (Anthropic) · LLM Gateway
Model ID: llmgateway-providers/anthropic/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (Anthropic) · LLM Gateway
Model ID: llmgateway-providers/anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Seed 1.6 · Volcengine Ark
Model ID: volcengine/doubao-seed-1-6-251015. Context window: 256000 tokens. Input / output per million tokens: $0.11875 / $1.18747.
Claude Haiku 4.5 (latest) · OrcaRouter
Model ID: orcarouter/anthropic/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
anthropic--claude-4.5-haiku · SAP AI Core
Model ID: sap-ai-core/anthropic--claude-4.5-haiku. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · Vertex
Model ID: google-vertex/claude-haiku-4-5@20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude-Haiku-4.5 · Poe
Model ID: poe/anthropic/claude-haiku-4.5. Context window: 192000 tokens. Input / output per million tokens: $0.85 / $4.3.
Veo-3.1-Fast · Poe
Model ID: poe/google/veo-3.1-fast. Context window: 480 tokens. Input / output per million tokens: — / —.
Veo-3.1 · Poe
Model ID: poe/google/veo-3.1. Context window: 480 tokens. Input / output per million tokens: — / —.
Claude Haiku 4.5 (latest) · Pioneer
Model ID: pioneer/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · UnoRouter
Model ID: unorouter/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1.2 / $6.
Claude Haiku 4.5 (latest) (EU) · Requesty
Model ID: requesty/claude-haiku-4-5@eu. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $5.5.
Claude Haiku 4.5 (latest) · Requesty
Model ID: requesty/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · DaoXE
Model ID: daoxe/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · CrossModel
Model ID: crossmodel/anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · FrogBot
Model ID: frogbot/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Xpersona
Model ID: xpersona/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $0.6 / $3.7.
Claude Haiku 4.5 · Anthropic
Model ID: anthropic/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Anthropic
Model ID: anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Veo 3.1 · Google
Model ID: google/veo-3.1-generate-preview. Context window: 480 tokens. Input / output per million tokens: — / —.
Veo 3.1 fast · Google
Model ID: google/veo-3.1-fast-generate-preview. Context window: 480 tokens. Input / output per million tokens: — / —.
Claude Haiku 4.5 · Vercel AI Gateway
Model ID: vercel/anthropic/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Veo 3.1 Fast Generate · Vercel AI Gateway
Model ID: vercel/google/veo-3.1-fast-generate-001. Context window: 0 tokens. Input / output per million tokens: — / —.
Veo 3.1 · Vercel AI Gateway
Model ID: vercel/google/veo-3.1-generate-001. Context window: 0 tokens. Input / output per million tokens: — / —.
Qwen3 Coder Next · DevPass (LLM Gateway)
Model ID: llmgateway/qwen3-coder-next. Context window: 262144 tokens. Input / output per million tokens: $0.108 / $0.675.
Claude Haiku 4.5 · DevPass (LLM Gateway)
Model ID: llmgateway/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · DevPass (LLM Gateway)
Model ID: llmgateway/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Cloudflare AI Gateway
Model ID: cloudflare-ai-gateway/anthropic/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · GitHub Copilot
Model ID: github-copilot/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · Perplexity Agent
Model ID: perplexity-agent/anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Opper
Model ID: opper/anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Databricks
Model ID: databricks/databricks-claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Kilo Gateway
Model ID: kilo/anthropic/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (Global) · Amazon Bedrock
Model ID: amazon-bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (JP) · Amazon Bedrock
Model ID: amazon-bedrock/jp.anthropic.claude-haiku-4-5-20251001-v1:0. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $5.5.
Claude Haiku 4.5 · Amazon Bedrock
Model ID: amazon-bedrock/anthropic.claude-haiku-4-5-20251001-v1:0. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (AU) · Amazon Bedrock
Model ID: amazon-bedrock/au.anthropic.claude-haiku-4-5-20251001-v1:0. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $5.5.
Claude Haiku 4.5 (EU) · Amazon Bedrock
Model ID: amazon-bedrock/eu.anthropic.claude-haiku-4-5-20251001-v1:0. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $5.5.
Claude Haiku 4.5 (US) · Amazon Bedrock
Model ID: amazon-bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $5.5.
Claude Haiku 4.5 (20251001) · Merge Gateway
Model ID: merge-gateway/anthropic/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · Abacus
Model ID: abacus/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · OpenCode Zen
Model ID: opencode/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · NEAR AI Cloud
Model ID: nearai/anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · OpenRouter
Model ID: openrouter/anthropic/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Model Oracle AI
Model ID: model-oracle-ai/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: — / —.
Seed 1.6 · Ofox
Model ID: ofox/volcengine/doubao-seed-1-6. Context window: 256000 tokens. Input / output per million tokens: $0.12 / $0.29.
Claude Haiku 4.5 (latest) · Ofox
Model ID: ofox/anthropic/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Neon
Model ID: neon/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Qwen/Qwen3-VL-8B-Instruct · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-VL-8B-Instruct. Context window: 262000 tokens. Input / output per million tokens: $0.18 / $0.68.
Claude Haiku 4.5 (latest) · Snowflake Cortex
Model ID: snowflake-cortex/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: — / —.
Claude Haiku 4.5 · ZenMux
Model ID: zenmux/anthropic/claude-haiku-4.5. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · Cortecs
Model ID: cortecs/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: $0.996 / $4.982.
Claude Haiku 4.5 · Vertex (Anthropic)
Model ID: google-vertex-anthropic/claude-haiku-4-5@20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 (latest) · AnyAPI
Model ID: anyapi/anthropic/claude-haiku-4-5. Context window: 200000 tokens. Input / output per million tokens: — / —.
Qwen: Qwen3 VL 8B Thinking · Kilo Gateway
Model ID: kilo/qwen/qwen3-vl-8b-thinking. Context window: 131072 tokens. Input / output per million tokens: $0.18 / $2.1.
Qwen: Qwen3 VL 8B Instruct · Kilo Gateway
Model ID: kilo/qwen/qwen3-vl-8b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.117 / $0.455.
OpenAI: GPT-5 Image ($$$$) · Kilo Gateway
Model ID: kilo/openai/gpt-5-image. Context window: 400000 tokens. Input / output per million tokens: $10 / $10.
Qwen3 VL 8B Thinking · OpenRouter
Model ID: openrouter/qwen/qwen3-vl-8b-thinking. Context window: 131072 tokens. Input / output per million tokens: $0.18 / $2.1.
Qwen3 VL 8B Instruct · OpenRouter
Model ID: openrouter/qwen/qwen3-vl-8b-instruct. Context window: 262144 tokens. Input / output per million tokens: $0.117 / $0.455.
GPT-5 Image · OpenRouter
Model ID: openrouter/openai/gpt-5-image. Context window: 400000 tokens. Input / output per million tokens: $10 / $10.
Veo-3-Fast · Poe
Model ID: poe/google/veo-3-fast. Context window: 480 tokens. Input / output per million tokens: — / —.
GLM 4.5 Air · NovitaAI
Model ID: novita-ai/zai-org/glm-4.5-air. Context window: 131072 tokens. Input / output per million tokens: $0.13 / $0.85.
Z-AI/GLM 4.6 · Qiniu
Model ID: qiniu-ai/z-ai/glm-4.6. Context window: 200000 tokens. Input / output per million tokens: — / —.
Qwen/Qwen3-VL-30B-A3B-Thinking · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Thinking. Context window: 262000 tokens. Input / output per million tokens: $0.29 / $1.
qwen/qwen3-vl-30b-a3b-instruct · NovitaAI
Model ID: novita-ai/qwen/qwen3-vl-30b-a3b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.2 / $0.7.
qwen/qwen3-vl-30b-a3b-thinking · NovitaAI
Model ID: novita-ai/qwen/qwen3-vl-30b-a3b-thinking. Context window: 131072 tokens. Input / output per million tokens: $0.2 / $1.
Qwen/Qwen3-VL-30B-A3B-Thinking · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-VL-30B-A3B-Thinking. Context window: 262000 tokens. Input / output per million tokens: $0.29 / $1.
GPT-Realtime mini · Vercel AI Gateway
Model ID: vercel/openai/gpt-realtime-mini. Context window: 0 tokens. Input / output per million tokens: $0.6 / $2.4.
deepseek-ai/DeepSeek-V3.2-Exp · SiliconFlow
Model ID: siliconflow/deepseek-ai/DeepSeek-V3.2-Exp. Context window: 164000 tokens. Input / output per million tokens: $0.27 / $0.41.
DeepSeek V3.2 Exp · Meganova
Model ID: meganova/deepseek-ai/DeepSeek-V3.2-Exp. Context window: 164000 tokens. Input / output per million tokens: $0.27 / $0.4.
Qwen3 Coder 30b A3B Instruct · NovitaAI
Model ID: novita-ai/qwen/qwen3-coder-30b-a3b-instruct. Context window: 160000 tokens. Input / output per million tokens: $0.07 / $0.27.
Qwen3 VL Flash · DevPass (LLM Gateway)
Model ID: llmgateway/qwen3-vl-flash. Context window: 262144 tokens. Input / output per million tokens: $0.05 / $0.4.
Stable Audio 2.5 (Text-to-Audio) · DigitalOcean
Model ID: digitalocean/fal-ai/stable-audio-25/text-to-audio. Context window: 0 tokens. Input / output per million tokens: — / —.
gpt-5-pro · 302.AI
Model ID: 302ai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
gemini-2.5-flash-image · 302.AI
Model ID: 302ai/gemini-2.5-flash-image. Context window: 32768 tokens. Input / output per million tokens: $0.3 / $30.
Gemini-3-Flash · Poe
Model ID: poe/google/gemini-3-flash. Context window: 1048576 tokens. Input / output per million tokens: $0.4 / $2.4.
Gemini 2.5 Computer Use Preview 10-2025 · Google
Model ID: google/gemini-2.5-computer-use-preview-10-2025. Context window: 131072 tokens. Input / output per million tokens: $1.25 / $10.
Interfaze Beta · Vercel AI Gateway
Model ID: vercel/interfaze/interfaze-beta. Context window: 1000000 tokens. Input / output per million tokens: $1.5 / $3.5.
Gemini 2.5 Computer Use Preview (10-2025) · Merge Gateway
Model ID: merge-gateway/google/gemini-2.5-computer-use-preview-10-2025. Context window: 128000 tokens. Input / output per million tokens: $1.25 / $10.
Granite 4.0 H Micro · Cloudflare Workers AI
Model ID: cloudflare-workers-ai/@cf/ibm-granite/granite-4.0-h-micro. Context window: 131000 tokens. Input / output per million tokens: $0.017 / $0.112.
GPT 5 Pro · NanoGPT
Model ID: nano-gpt/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT-5 Pro · Impossibl
Model ID: impossibl/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT-5 Pro (OpenAI) · LLM Gateway
Model ID: llmgateway-providers/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT-5 Pro · OrcaRouter
Model ID: orcarouter/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT-5 Pro · Azure Cognitive Services
Model ID: azure-cognitive-services/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT-5-Pro · Poe
Model ID: poe/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $14 / $110.
Sora-2 · Poe
Model ID: poe/openai/sora-2. Context window: 0 tokens. Input / output per million tokens: — / —.
Sora-2-Pro · Poe
Model ID: poe/openai/sora-2-pro. Context window: 0 tokens. Input / output per million tokens: — / —.
GPT-5 pro · Vercel AI Gateway
Model ID: vercel/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT Image 1 Mini · Vercel AI Gateway
Model ID: vercel/openai/gpt-image-1-mini. Context window: 0 tokens. Input / output per million tokens: $2 / $8.
GPT-5 Pro · DevPass (LLM Gateway)
Model ID: llmgateway/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
Qwen: Qwen3 VL 30B A3B Instruct · Kilo Gateway
Model ID: kilo/qwen/qwen3-vl-30b-a3b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.13 / $0.52.
Qwen: Qwen3 VL 30B A3B Thinking · Kilo Gateway
Model ID: kilo/qwen/qwen3-vl-30b-a3b-thinking. Context window: 131072 tokens. Input / output per million tokens: $0.2 / $2.4.
GPT-5 Pro · Kilo Gateway
Model ID: kilo/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT-5 Pro · Azure
Model ID: azure/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
Qwen3 VL 30B A3B Instruct · OpenRouter
Model ID: openrouter/qwen/qwen3-vl-30b-a3b-instruct. Context window: 262144 tokens. Input / output per million tokens: $0.13 / $0.52.
Qwen3 VL 30B A3B Thinking · OpenRouter
Model ID: openrouter/qwen/qwen3-vl-30b-a3b-thinking. Context window: 262144 tokens. Input / output per million tokens: $0.2 / $2.4.
GPT-5 Pro · OpenRouter
Model ID: openrouter/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT-5 Pro · OpenAI
Model ID: openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
GPT-5 Pro · Eden AI
Model ID: edenai/openai/gpt-5-pro. Context window: 400000 tokens. Input / output per million tokens: $15 / $120.
Qwen/Qwen3-VL-30B-A3B-Instruct · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Instruct. Context window: 262000 tokens. Input / output per million tokens: $0.29 / $1.
Qwen3 VL 30B A3B Instruct (NovitaAI) · LLM Gateway
Model ID: llmgateway-providers/novita/qwen3-vl-30b-a3b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.2 / $0.7.
Qwen3 VL 30B A3B Instruct (DeepInfra) · LLM Gateway
Model ID: llmgateway-providers/deepinfra/qwen3-vl-30b-a3b-instruct. Context window: 262144 tokens. Input / output per million tokens: $0.15 / $0.6.
Qwen/Qwen3-VL-30B-A3B-Instruct · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-VL-30B-A3B-Instruct. Context window: 262000 tokens. Input / output per million tokens: $0.29 / $1.
Qwen/Qwen3-VL-235B-A22B-Thinking · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Thinking. Context window: 262000 tokens. Input / output per million tokens: $0.45 / $3.5.
Qwen/Qwen3-VL-235B-A22B-Instruct · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Instruct. Context window: 262000 tokens. Input / output per million tokens: $0.3 / $1.5.
Qwen/Qwen3-VL-235B-A22B-Instruct · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-VL-235B-A22B-Instruct. Context window: 262000 tokens. Input / output per million tokens: $0.3 / $1.5.
Qwen/Qwen3-VL-235B-A22B-Thinking · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-VL-235B-A22B-Thinking. Context window: 262000 tokens. Input / output per million tokens: $0.45 / $3.5.
GLM 4.6 Turbo · NanoGPT
Model ID: nano-gpt/z-ai/GLM-4.6-turbo. Context window: 204800 tokens. Input / output per million tokens: $1 / $3.
GLM 4.6 Turbo (Thinking) · NanoGPT
Model ID: nano-gpt/z-ai/GLM-4.6-turbo:thinking. Context window: 204800 tokens. Input / output per million tokens: $1 / $3.
Granite-4.0-H-Small · watsonx.ai
Model ID: watsonx/ibm/granite-4-h-small. Context window: 131072 tokens. Input / output per million tokens: $0.0636 / $0.265.
Qwen3 VL 30B A3B Instruct · DevPass (LLM Gateway)
Model ID: llmgateway/qwen3-vl-30b-a3b-instruct. Context window: 262144 tokens. Input / output per million tokens: $0.15 / $0.6.
Venice Uncensored · NanoGPT
Model ID: nano-gpt/venice-uncensored. Context window: 128000 tokens. Input / output per million tokens: $0.4 / $1.8.
Anthropic: Claude 4.5 Haiku (20251001) · Helicone
Model ID: helicone/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Anthropic: Claude 4.5 Haiku · Helicone
Model ID: helicone/claude-4.5-haiku. Context window: 200000 tokens. Input / output per million tokens: $1 / $5.
Claude Haiku 4.5 · QiHang
Model ID: qihang-ai/claude-haiku-4-5-20251001. Context window: 200000 tokens. Input / output per million tokens: $0.14 / $0.71.
Mistral Small 3.2 24B Instruct 2506 · Berget.AI
Model ID: berget/mistralai/Mistral-Small-3.2-24B-Instruct-2506. Context window: 32000 tokens. Input / output per million tokens: $0.33 / $0.33.
Ring-1T · Bailing
Model ID: bailing/Ring-1T. Context window: 128000 tokens. Input / output per million tokens: $0.57 / $2.29.
Ling-1T · Bailing
Model ID: bailing/Ling-1T. Context window: 128000 tokens. Input / output per million tokens: $0.57 / $2.29.
Claude 4.5 Sonnet · Qiniu
Model ID: qiniu-ai/claude-4.5-sonnet. Context window: 200000 tokens. Input / output per million tokens: — / —.
GLM 4.6 · NanoGPT
Model ID: nano-gpt/z-ai/glm-4.6. Context window: 200000 tokens. Input / output per million tokens: $0.35 / $1.4.
GLM 4.6 Thinking · NanoGPT
Model ID: nano-gpt/z-ai/glm-4.6:thinking. Context window: 200000 tokens. Input / output per million tokens: $0.35 / $1.4.
GLM-4.6 · Impossibl
Model ID: impossibl/zai/glm-4.6. Context window: 204800 tokens. Input / output per million tokens: $0.6 / $2.2.
GLM-4.6 (NovitaAI) · LLM Gateway
Model ID: llmgateway-providers/novita/glm-4.6. Context window: 204800 tokens. Input / output per million tokens: $0.55 / $2.2.