Data source: models.dev. Providers may change prices and availability; check the provider's information before use. models.dev
gemini-2.0-flash-lite · 302.AI
Model ID: 302ai/gemini-2.0-flash-lite. Context window: 2000000 tokens. Input / output per million tokens: $0.075 / $0.3.
MiniMax-M1 · 302.AI
Model ID: 302ai/MiniMax-M1. Context window: 1000000 tokens. Input / output per million tokens: $0.132 / $1.254.
DeepSeek V3.2 · Abacus
Model ID: abacus/deepseek-ai/DeepSeek-V3.2. Context window: 128000 tokens. Input / output per million tokens: $0.27 / $0.4.
cosmos-transfer1-7b · Nvidia
Model ID: nvidia/nvidia/cosmos-transfer1-7b. Context window: 0 tokens. Input / output per million tokens: $0 / $0.
Gemma 3n E2b It · Nvidia
Model ID: nvidia/google/gemma-3n-e2b-it. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
mistral-nemotron · Nvidia
Model ID: nvidia/mistralai/mistral-nemotron. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Seedance v1.0 Pro · Vercel AI Gateway
Model ID: vercel/bytedance/seedance-v1.0-pro. Context window: 0 tokens. Input / output per million tokens: — / —.
o3-pro · Poe
Model ID: poe/openai/o3-pro. Context window: 200000 tokens. Input / output per million tokens: $18 / $72.
Magistral Small · Pioneer
Model ID: pioneer/mistralai/Magistral-Small-2506. Context window: 128000 tokens. Input / output per million tokens: $0.5 / $1.5.
o3 Pro · Vercel AI Gateway
Model ID: vercel/openai/o3-pro. Context window: 200000 tokens. Input / output per million tokens: $20 / $80.
o3-pro · Kilo Gateway
Model ID: kilo/openai/o3-pro. Context window: 200000 tokens. Input / output per million tokens: $20 / $80.
o3-pro · Abacus
Model ID: abacus/o3-pro. Context window: 200000 tokens. Input / output per million tokens: $20 / $40.
o3-pro · OpenRouter
Model ID: openrouter/openai/o3-pro. Context window: 200000 tokens. Input / output per million tokens: $20 / $80.
o3-pro · OpenAI
Model ID: openai/o3-pro. Context window: 200000 tokens. Input / output per million tokens: $20 / $80.
o3-pro · Eden AI
Model ID: edenai/openai/o3-pro. Context window: 200000 tokens. Input / output per million tokens: $20 / $80.
v0-1.5-lg · v0
Model ID: v0/v0-1.5-lg. Context window: 512000 tokens. Input / output per million tokens: $15 / $75.
v0-1.5-md · v0
Model ID: v0/v0-1.5-md. Context window: 128000 tokens. Input / output per million tokens: $3 / $15.
Qwen3-Embedding 4B · Privatemode AI
Model ID: privatemode-ai/qwen3-embedding-4b. Context window: 32000 tokens. Input / output per million tokens: $0.1502 / $0.
Gemini 2.5 Pro Preview 0605 · NanoGPT
Model ID: nano-gpt/gemini-2.5-pro-preview-06-05. Context window: 1048576 tokens. Input / output per million tokens: $2.5 / $10.
Gemini 2.5 Flash (No Thinking) · NanoGPT
Model ID: nano-gpt/gemini-2.5-flash-nothinking. Context window: 1048576 tokens. Input / output per million tokens: $0.3 / $2.5.
Qwen3 Embedding 8B · Scaleway
Model ID: scaleway/qwen3-embedding-8b. Context window: 32768 tokens. Input / output per million tokens: $0.1 / $0.
ElevenLabs-v3 · Poe
Model ID: poe/elevenlabs/elevenlabs-v3. Context window: 128000 tokens. Input / output per million tokens: — / —.
Qwen3 Embedding 4B · Vercel AI Gateway
Model ID: vercel/alibaba/qwen3-embedding-4b. Context window: 32768 tokens. Input / output per million tokens: — / —.
Qwen3 Embedding 8B · Vercel AI Gateway
Model ID: vercel/alibaba/qwen3-embedding-8b. Context window: 32768 tokens. Input / output per million tokens: — / —.
Qwen3-Embedding-8B · InferX
Model ID: inferx/Qwen3-Embedding-8B. Context window: 32768 tokens. Input / output per million tokens: $0 / $0.
Google: Gemini 2.5 Pro Preview 06-05 · Kilo Gateway
Model ID: kilo/google/gemini-2.5-pro-preview. Context window: 1048576 tokens. Input / output per million tokens: $1.25 / $10.
Gemini 2.5 Pro Preview 06-05 · OpenRouter
Model ID: openrouter/google/gemini-2.5-pro-preview. Context window: 1048576 tokens. Input / output per million tokens: $1.25 / $10.
Lyria · Poe
Model ID: poe/google/lyria. Context window: 0 tokens. Input / output per million tokens: — / —.
Qwen3 Embedding 0.6B · DigitalOcean
Model ID: digitalocean/qwen3-embedding-0.6b. Context window: 8000 tokens. Input / output per million tokens: $0.04 / $0.
Gemma 3n E4b It · Nvidia
Model ID: nvidia/google/gemma-3n-e4b-it. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Qwen3 Embedding 0.6B · NEAR AI Cloud
Model ID: nearai/Qwen/Qwen3-Embedding-0.6B. Context window: 32768 tokens. Input / output per million tokens: $0.01 / $0.01.
Qwen3 Reranker 0.6B · NEAR AI Cloud
Model ID: nearai/Qwen/Qwen3-Reranker-0.6B. Context window: 40960 tokens. Input / output per million tokens: $0.01 / $0.01.
Qwen3 30B A3B · Helicone
Model ID: helicone/qwen3-30b-a3b. Context window: 41000 tokens. Input / output per million tokens: $0.08 / $0.29.
Magistral Small 2506 · IO.NET
Model ID: io-net/mistralai/Magistral-Small-2506. Context window: 128000 tokens. Input / output per million tokens: $0.5 / $1.5.
Lucid Realism · FastRouter
Model ID: fastrouter/leonardo-ai/lucid-realism. Context window: 4096 tokens. Input / output per million tokens: — / —.
Lucid Origin · FastRouter
Model ID: fastrouter/leonardo-ai/lucid-origin. Context window: 4096 tokens. Input / output per million tokens: — / —.
GPT Realtime 1.5 · FastRouter
Model ID: fastrouter/openai/gpt-realtime-1.5. Context window: 32000 tokens. Input / output per million tokens: $4 / $16.
DeepSeek V3.1 Terminus · Abacus
Model ID: abacus/deepseek-ai/DeepSeek-V3.1-Terminus. Context window: 128000 tokens. Input / output per million tokens: $0.27 / $1.
MM Poly 8B · Clarifai
Model ID: clarifai/clarifai/main/models/mm-poly-8b. Context window: 32768 tokens. Input / output per million tokens: $0.658 / $1.11.
Prompt Guard 2 86M · Groq
Model ID: groq/meta-llama/llama-prompt-guard-2-86m. Context window: 512 tokens. Input / output per million tokens: $0.04 / $0.04.
Llama Prompt Guard 2 22M · Groq
Model ID: groq/meta-llama/llama-prompt-guard-2-22m. Context window: 512 tokens. Input / output per million tokens: $0.03 / $0.03.
DeepSeek R1 0528 Qwen3 8B · NovitaAI
Model ID: novita-ai/deepseek/deepseek-r1-0528-qwen3-8b. Context window: 128000 tokens. Input / output per million tokens: $0.06 / $0.09.
FLUX.1 Kontext Max · Vercel AI Gateway
Model ID: vercel/bfl/flux-kontext-max. Context window: 512 tokens. Input / output per million tokens: — / —.
FLUX.1 Kontext Pro · Vercel AI Gateway
Model ID: vercel/bfl/flux-kontext-pro. Context window: 512 tokens. Input / output per million tokens: — / —.
DeepSeek R1 0528 · NanoGPT
Model ID: nano-gpt/deepseek-ai/DeepSeek-R1-0528. Context window: 163840 tokens. Input / output per million tokens: $0.4 / $1.7.
deepseek-ai/DeepSeek-R1 · SiliconFlow (China)
Model ID: siliconflow-cn/deepseek-ai/DeepSeek-R1. Context window: 164000 tokens. Input / output per million tokens: $0.5 / $2.18.
Pro/deepseek-ai/DeepSeek-R1 · SiliconFlow (China)
Model ID: siliconflow-cn/Pro/deepseek-ai/DeepSeek-R1. Context window: 164000 tokens. Input / output per million tokens: $0.5 / $2.18.
DeepSeek R1 0528 · Alibaba (China)
Model ID: alibaba-cn/deepseek-r1-0528. Context window: 131072 tokens. Input / output per million tokens: $0.574 / $2.294.
siliconflow/deepseek-r1-0528 · Alibaba (China)
Model ID: alibaba-cn/siliconflow/deepseek-r1-0528. Context window: 163840 tokens. Input / output per million tokens: $0.5 / $2.18.
DeepSeek R1 0528 · NovitaAI
Model ID: novita-ai/deepseek/deepseek-r1-0528. Context window: 163840 tokens. Input / output per million tokens: $0.7 / $2.5.
DeepSeek-R1-0528 · Hugging Face
Model ID: huggingface/deepseek-ai/DeepSeek-R1-0528. Context window: 163840 tokens. Input / output per million tokens: $3 / $5.
Codestral Embed · Vercel AI Gateway
Model ID: vercel/mistral/codestral-embed. Context window: 8192 tokens. Input / output per million tokens: — / —.
DeepSeek R1-0528 · TensorX
Model ID: tensorx/deepseek/deepseek-r1-0528. Context window: 164000 tokens. Input / output per million tokens: $0.66 / $2.6.
DeepSeek-R1-0528 · Deep Infra
Model ID: deepinfra/deepseek-ai/DeepSeek-R1-0528. Context window: 163840 tokens. Input / output per million tokens: $0.5 / $2.15.
DeepSeek: R1 0528 · Kilo Gateway
Model ID: kilo/deepseek/deepseek-r1-0528. Context window: 163840 tokens. Input / output per million tokens: $0.7 / $2.5.
Qwen3 Max · Abacus
Model ID: abacus/qwen3-max. Context window: 131072 tokens. Input / output per million tokens: $1.2 / $6.
R1 0528 · OpenRouter
Model ID: openrouter/deepseek/deepseek-r1-0528. Context window: 163840 tokens. Input / output per million tokens: $0.5 / $2.15.
deepseek-ai/DeepSeek-R1 · SiliconFlow
Model ID: siliconflow/deepseek-ai/DeepSeek-R1. Context window: 164000 tokens. Input / output per million tokens: $0.5 / $2.18.
DeepSeek R1 0528 · Meganova
Model ID: meganova/deepseek-ai/DeepSeek-R1-0528. Context window: 163840 tokens. Input / output per million tokens: $0.5 / $2.15.
DeepSeek R1 0528 · Cortecs
Model ID: cortecs/deepseek-r1-0528. Context window: 164000 tokens. Input / output per million tokens: $0.652 / $2.57.
claude-opus-4-1-20250805-thinking · 302.AI
Model ID: 302ai/claude-opus-4-1-20250805-thinking. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
mistral-7b-instruct-v0.2 · Cortecs
Model ID: cortecs/mistral-7b-instruct-v0.2. Context window: 32000 tokens. Input / output per million tokens: $0.159 / $0.219.
mistral-large-2402 · Cortecs
Model ID: cortecs/mistral-large-2402. Context window: 32000 tokens. Input / output per million tokens: $4.284 / $12.952.
mistral-small-3.2-24b-instruct-2506 · Cortecs
Model ID: cortecs/mistral-small-3.2-24b-instruct-2506. Context window: 131000 tokens. Input / output per million tokens: $0.1 / $0.312.
mistral-7b-instruct-v0.3 · Cortecs
Model ID: cortecs/mistral-7b-instruct-v0.3. Context window: 127000 tokens. Input / output per million tokens: $0.111 / $0.111.
Imagen-4-Ultra · Poe
Model ID: poe/google/imagen-4-ultra. Context window: 480 tokens. Input / output per million tokens: — / —.
Amoral Gemma3 27B v2 · NanoGPT
Model ID: nano-gpt/soob3123/amoral-gemma3-27B-v2. Context window: 32768 tokens. Input / output per million tokens: $0.3 / $0.3.
Claude Opus 4 · DigitalOcean
Model ID: digitalocean/anthropic-claude-opus-4. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
Claude Sonnet 4 · DigitalOcean
Model ID: digitalocean/anthropic-claude-sonnet-4. Context window: 1000000 tokens. Input / output per million tokens: $3 / $15.
anthropic--claude-4-sonnet · SAP AI Core
Model ID: sap-ai-core/anthropic--claude-4-sonnet. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
Imagen-4 · Poe
Model ID: poe/google/imagen-4. Context window: 480 tokens. Input / output per million tokens: — / —.
Claude Sonnet 4 (latest) (EU) · Requesty
Model ID: requesty/claude-sonnet-4@eu. Context window: 1000000 tokens. Input / output per million tokens: $3 / $15.
magpie-tts-zeroshot · Nvidia
Model ID: nvidia/nvidia/magpie-tts-zeroshot. Context window: 0 tokens. Input / output per million tokens: $0 / $0.
Claude Opus 4 · Vercel AI Gateway
Model ID: vercel/anthropic/claude-opus-4. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
Claude Sonnet 4 · Vercel AI Gateway
Model ID: vercel/anthropic/claude-sonnet-4. Context window: 1000000 tokens. Input / output per million tokens: $3 / $15.
Claude Sonnet 4 · FastRouter
Model ID: fastrouter/anthropic/claude-sonnet-4. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
Anthropic: Claude Opus 4 ($$$$) · Kilo Gateway
Model ID: kilo/anthropic/claude-opus-4. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
Anthropic: Claude Sonnet 4 · Kilo Gateway
Model ID: kilo/anthropic/claude-sonnet-4. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
Claude Opus 4 (20250514) · Merge Gateway
Model ID: merge-gateway/anthropic/claude-opus-4-20250514. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
Claude Sonnet 4 · Merge Gateway
Model ID: merge-gateway/anthropic/claude-sonnet-4-20250514. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
Claude Sonnet 4 · OpenCode Zen
Model ID: opencode/claude-sonnet-4. Context window: 1000000 tokens. Input / output per million tokens: $3 / $15.
Claude Opus 4 · OpenRouter
Model ID: openrouter/anthropic/claude-opus-4. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
Claude Sonnet 4 · OpenRouter
Model ID: openrouter/anthropic/claude-sonnet-4. Context window: 1000000 tokens. Input / output per million tokens: $3 / $15.
Claude Opus 4 · ZenMux
Model ID: zenmux/anthropic/claude-opus-4. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
Claude Sonnet 4 · ZenMux
Model ID: zenmux/anthropic/claude-sonnet-4. Context window: 1000000 tokens. Input / output per million tokens: $3 / $15.
Claude Sonnet 4 (latest) · Cortecs
Model ID: cortecs/claude-sonnet-4. Context window: 200000 tokens. Input / output per million tokens: $2.898 / $14.493.
v0-1.0-md · v0
Model ID: v0/v0-1.0-md. Context window: 128000 tokens. Input / output per million tokens: $3 / $15.
Claude-Opus-4 · Poe
Model ID: poe/anthropic/claude-opus-4. Context window: 192512 tokens. Input / output per million tokens: $13 / $64.
Claude-Sonnet-4 · Poe
Model ID: poe/anthropic/claude-sonnet-4. Context window: 983040 tokens. Input / output per million tokens: $2.6 / $13.
Veo-3 · Poe
Model ID: poe/google/veo-3. Context window: 480 tokens. Input / output per million tokens: — / —.
Gemini 2.5 Flash 0520 · NanoGPT
Model ID: nano-gpt/gemini-2.5-flash-preview-05-20. Context window: 1048000 tokens. Input / output per million tokens: $0.15 / $0.6.
Gemini 2.5 Flash 0520 Thinking · NanoGPT
Model ID: nano-gpt/gemini-2.5-flash-preview-05-20:thinking. Context window: 1048000 tokens. Input / output per million tokens: $0.15 / $3.5.
Gemini Embedding 001 · SAP AI Core
Model ID: sap-ai-core/gemini-embedding. Context window: 2048 tokens. Input / output per million tokens: — / —.
Gemini Embedding 001 · Vertex
Model ID: google-vertex/gemini-embedding-001. Context window: 2048 tokens. Input / output per million tokens: $0.15 / $0.
Solar Pro 2 · LLMTR
Model ID: llmtr/upstage/solar-pro2. Context window: 65536 tokens. Input / output per million tokens: $0.15 / $0.6.
Gemini Embedding 001 · Google
Model ID: google/gemini-embedding-001. Context window: 2048 tokens. Input / output per million tokens: $0.15 / $0.
voyage-3.5 · Vercel AI Gateway
Model ID: vercel/voyage/voyage-3.5. Context window: 8192 tokens. Input / output per million tokens: — / —.
voyage-3.5-lite · Vercel AI Gateway
Model ID: vercel/voyage/voyage-3.5-lite. Context window: 8192 tokens. Input / output per million tokens: — / —.
Gemini Embedding 001 · Vercel AI Gateway
Model ID: vercel/google/gemini-embedding-001. Context window: 8192 tokens. Input / output per million tokens: — / —.
Veo 3.0 · Vercel AI Gateway
Model ID: vercel/google/veo-3.0-generate-001. Context window: 0 tokens. Input / output per million tokens: — / —.
Imagen 4 Ultra · FastRouter
Model ID: fastrouter/google/imagen-4.0-ultra. Context window: 480 tokens. Input / output per million tokens: — / —.
Imagen 4 Fast · FastRouter
Model ID: fastrouter/google/imagen-4.0-fast. Context window: 480 tokens. Input / output per million tokens: — / —.
Gemini Embedding 001 · Merge Gateway
Model ID: merge-gateway/google/gemini-embedding-001. Context window: 2048 tokens. Input / output per million tokens: $0.15 / $0.
solar-pro2 · Upstage
Model ID: upstage/solar-pro2. Context window: 65536 tokens. Input / output per million tokens: $0.25 / $0.25.
Gemma 3N E4B Instruct · Together AI
Model ID: togetherai/google/gemma-3n-E4B-it. Context window: 32768 tokens. Input / output per million tokens: $0.06 / $0.12.
Model Router · Azure Cognitive Services
Model ID: azure-cognitive-services/model-router. Context window: 200000 tokens. Input / output per million tokens: $0.14 / $0.
Model Router · Azure
Model ID: azure/model-router. Context window: 200000 tokens. Input / output per million tokens: $0.14 / $0.
Gemma 3 27B · STACKIT
Model ID: stackit/google/gemma-3-27b-it. Context window: 37000 tokens. Input / output per million tokens: $0.53 / $0.76.
Anthropic: Claude Opus 4 · Helicone
Model ID: helicone/claude-opus-4. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
Anthropic: Claude Sonnet 4 · Helicone
Model ID: helicone/claude-sonnet-4. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
Claude Opus 4 · Abacus
Model ID: abacus/claude-opus-4-20250514. Context window: 200000 tokens. Input / output per million tokens: $15 / $75.
Claude Sonnet 4 · Abacus
Model ID: abacus/claude-sonnet-4-20250514. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
Llama-3.1-8B-CS · Poe
Model ID: poe/cerebras/llama-3.1-8b-cs. Context window: 128000 tokens. Input / output per million tokens: $0.1 / $0.1.
Cogito v1 Preview Qwen 32B · NanoGPT
Model ID: nano-gpt/deepcogito/cogito-v1-preview-qwen-32B. Context window: 128000 tokens. Input / output per million tokens: $1.8 / $1.8.
Runway-Gen-4-Turbo · Poe
Model ID: poe/runwayml/runway-gen-4-turbo. Context window: 256 tokens. Input / output per million tokens: — / —.
Qwen-Omni Turbo Realtime · Alibaba (China)
Model ID: alibaba-cn/qwen-omni-turbo-realtime. Context window: 32768 tokens. Input / output per million tokens: $0.23 / $0.918.
Qwen-Omni Turbo Realtime · Alibaba
Model ID: alibaba/qwen-omni-turbo-realtime. Context window: 32768 tokens. Input / output per million tokens: $0.27 / $1.07.
mistralai--mistral-medium-instruct · SAP AI Core
Model ID: sap-ai-core/mistralai--mistral-medium-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.36 / $1.22.
Mistral Medium 3 · Azure Cognitive Services
Model ID: azure-cognitive-services/mistral-medium-2505. Context window: 128000 tokens. Input / output per million tokens: $0.4 / $2.
Mistral Medium 3 · Pioneer
Model ID: pioneer/mistral-medium. Context window: 128000 tokens. Input / output per million tokens: $0.4 / $2.
Mistral: Mistral Medium 3 · Kilo Gateway
Model ID: kilo/mistralai/mistral-medium-3. Context window: 131072 tokens. Input / output per million tokens: $0.4 / $2.
Mistral Medium 3 · Azure
Model ID: azure/mistral-medium-2505. Context window: 128000 tokens. Input / output per million tokens: $0.4 / $2.
Mistral Medium 3 · Merge Gateway
Model ID: merge-gateway/mistral/mistral-medium-2505. Context window: 128000 tokens. Input / output per million tokens: $0.4 / $2.
Mistral Medium 3 · OpenRouter
Model ID: openrouter/mistralai/mistral-medium-3. Context window: 131072 tokens. Input / output per million tokens: $0.4 / $2.
Mistral Medium 3 · Mistral
Model ID: mistral/mistral-medium-2505. Context window: 131072 tokens. Input / output per million tokens: $0.4 / $2.
Mistral Medium 3 · Eden AI
Model ID: edenai/mistral/mistral-medium-2505. Context window: 131072 tokens. Input / output per million tokens: $0.4 / $2.
Gemini 2.5 Pro Preview 0506 · NanoGPT
Model ID: nano-gpt/gemini-2.5-pro-preview-05-06. Context window: 1048576 tokens. Input / output per million tokens: $2.5 / $10.
Gemini 2.5 Pro Preview TTS · Google
Model ID: google/gemini-2.5-pro-preview-tts. Context window: 8192 tokens. Input / output per million tokens: $1 / $20.
Gemini 2.5 Flash Preview TTS · Google
Model ID: google/gemini-2.5-flash-preview-tts. Context window: 8192 tokens. Input / output per million tokens: $0.5 / $10.
Devstral Small 2505 · IO.NET
Model ID: io-net/mistralai/Devstral-Small-2505. Context window: 128000 tokens. Input / output per million tokens: $0.05 / $0.22.
Qwen3 32B · DigitalOcean
Model ID: digitalocean/alibaba-qwen3-32b. Context window: 32768 tokens. Input / output per million tokens: $0.25 / $0.55.
Qwen/Qwen3-8B · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-8B. Context window: 131000 tokens. Input / output per million tokens: $0.06 / $0.06.
Qwen/Qwen3-14B · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-14B. Context window: 131000 tokens. Input / output per million tokens: $0.07 / $0.28.
Qwen/Qwen3-32B · SiliconFlow (China)
Model ID: siliconflow-cn/Qwen/Qwen3-32B. Context window: 131000 tokens. Input / output per million tokens: $0.14 / $0.57.
Deepseek Prover V2 671B · NovitaAI
Model ID: novita-ai/deepseek/deepseek-prover-v2-671b. Context window: 160000 tokens. Input / output per million tokens: $0.7 / $2.5.
Meta: Llama Guard 4 12B · Kilo Gateway
Model ID: kilo/meta-llama/llama-guard-4-12b. Context window: 163840 tokens. Input / output per million tokens: $0.18 / $0.18.
Llama Guard 4 12B · OpenRouter
Model ID: openrouter/meta-llama/llama-guard-4-12b. Context window: 163840 tokens. Input / output per million tokens: $0.18 / $0.18.
Qwen/Qwen3-8B · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-8B. Context window: 131000 tokens. Input / output per million tokens: $0.06 / $0.06.
Qwen/Qwen3-14B · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-14B. Context window: 131000 tokens. Input / output per million tokens: $0.07 / $0.28.
Qwen/Qwen3-32B · SiliconFlow
Model ID: siliconflow/Qwen/Qwen3-32B. Context window: 131000 tokens. Input / output per million tokens: $0.14 / $0.57.
Llama 4 Maverick 17B 128E Instruct · Vertex
Model ID: google-vertex/meta/llama-4-maverick-17b-128e-instruct-maas. Context window: 524288 tokens. Input / output per million tokens: $0.35 / $1.15.
Qwen3 30B A3B · NovitaAI
Model ID: novita-ai/qwen/qwen3-30b-a3b-fp8. Context window: 40960 tokens. Input / output per million tokens: $0.09 / $0.45.
Qwen3 235B A22B · NovitaAI
Model ID: novita-ai/qwen/qwen3-235b-a22b-fp8. Context window: 40960 tokens. Input / output per million tokens: $0.2 / $0.8.
Qwen3 4B · NovitaAI
Model ID: novita-ai/qwen/qwen3-4b-fp8. Context window: 128000 tokens. Input / output per million tokens: $0.03 / $0.03.
Qwen3 8B · NovitaAI
Model ID: novita-ai/qwen/qwen3-8b-fp8. Context window: 128000 tokens. Input / output per million tokens: $0.035 / $0.138.
Qwen3 32B · NovitaAI
Model ID: novita-ai/qwen/qwen3-32b-fp8. Context window: 40960 tokens. Input / output per million tokens: $0.1 / $0.45.
Qwen3 14B Instruct · CoreWeave
Model ID: wandb/OpenPipe/Qwen3-14B-Instruct. Context window: 32768 tokens. Input / output per million tokens: $0.05 / $0.22.
Qwen 3 235B A22B Thinking 2507 · Venice AI
Model ID: venice/qwen3-235b-a22b-thinking-2507. Context window: 128000 tokens. Input / output per million tokens: $0.45 / $3.5.
Qwen 3 Next 80b · Venice AI
Model ID: venice/qwen3-next-80b. Context window: 256000 tokens. Input / output per million tokens: $0.35 / $1.9.
Qwen 3 235B A22B Instruct 2507 · Venice AI
Model ID: venice/qwen3-235b-a22b-instruct-2507. Context window: 128000 tokens. Input / output per million tokens: $0.15 / $0.75.
Qwen3-30B-A3B · 302.AI
Model ID: 302ai/qwen3-30b-a3b. Context window: 128000 tokens. Input / output per million tokens: $0.11 / $1.08.
Qwen3-235B-A22B · 302.AI
Model ID: 302ai/qwen3-235b-a22b. Context window: 128000 tokens. Input / output per million tokens: $0.29 / $2.86.
Qwen3 30B A3B · NanoGPT
Model ID: nano-gpt/qwen/qwen3-30b-a3b. Context window: 41000 tokens. Input / output per million tokens: $0.1 / $0.3.
Qwen3 235B A22B FP8 (NovitaAI) · LLM Gateway
Model ID: llmgateway-providers/novita/qwen3-235b-a22b-fp8. Context window: 40960 tokens. Input / output per million tokens: $0.2 / $0.8.
Llama 3.3 70B Instruct · Regolo AI
Model ID: regolo-ai/llama-3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.6 / $2.7.
Qwen3 235B A22B Instruct 2507 · ModelScope
Model ID: modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507. Context window: 262144 tokens. Input / output per million tokens: $0 / $0.
Qwen3 32B · Helicone
Model ID: helicone/qwen3-32b. Context window: 131072 tokens. Input / output per million tokens: $0.29 / $0.59.
Qwen3 30B A3B · Hugging Face
Model ID: huggingface/Qwen/Qwen3-30B-A3B. Context window: 40960 tokens. Input / output per million tokens: $0.12 / $0.5.
Qwen3 235B A22B Instruct 2507 · Vercel AI Gateway
Model ID: vercel/alibaba/qwen-3-235b. Context window: 262144 tokens. Input / output per million tokens: $0.22 / $0.88.
Qwen3-14B · Vercel AI Gateway
Model ID: vercel/alibaba/qwen-3-14b. Context window: 40960 tokens. Input / output per million tokens: $0.12 / $0.24.
Qwen3-30B-A3B · Vercel AI Gateway
Model ID: vercel/alibaba/qwen-3-30b. Context window: 40960 tokens. Input / output per million tokens: $0.12 / $0.5.
Qwen 3.32B · Vercel AI Gateway
Model ID: vercel/alibaba/qwen-3-32b. Context window: 128000 tokens. Input / output per million tokens: $0.16 / $0.64.
Qwen3 235B A22B FP8 · DevPass (LLM Gateway)
Model ID: llmgateway/qwen3-235b-a22b-fp8. Context window: 40960 tokens. Input / output per million tokens: $0.2 / $0.8.
Qwen3 30B A3B · Deep Infra
Model ID: deepinfra/Qwen/Qwen3-30B-A3B. Context window: 40960 tokens. Input / output per million tokens: $0.12 / $0.5.
Qwen: Qwen3 14B · Kilo Gateway
Model ID: kilo/qwen/qwen3-14b. Context window: 40960 tokens. Input / output per million tokens: $0.2275 / $0.91.
Qwen3 30B A3B · Kilo Gateway
Model ID: kilo/qwen/qwen3-30b-a3b. Context window: 40960 tokens. Input / output per million tokens: $0.13 / $0.52.
Qwen: Qwen3 8B · Kilo Gateway
Model ID: kilo/qwen/qwen3-8b. Context window: 131072 tokens. Input / output per million tokens: $0.117 / $0.455.
Palmyra X5 (US) · Amazon Bedrock
Model ID: amazon-bedrock/us.writer.palmyra-x5-v1:0. Context window: 1040000 tokens. Input / output per million tokens: $0.6 / $6.
Palmyra X5 · Amazon Bedrock
Model ID: amazon-bedrock/writer.palmyra-x5-v1:0. Context window: 1040000 tokens. Input / output per million tokens: $0.6 / $6.
Qwen3 30B A3B · Merge Gateway
Model ID: merge-gateway/qwen/qwen3-30b-a3b. Context window: 131072 tokens. Input / output per million tokens: $0.108 / $1.076.
Palmyra X5 · Merge Gateway
Model ID: merge-gateway/writer/palmyra-x5. Context window: 1000000 tokens. Input / output per million tokens: $0.6 / $6.
Qwen3 14B · OpenRouter
Model ID: openrouter/qwen/qwen3-14b. Context window: 131072 tokens. Input / output per million tokens: $0.12 / $0.24.
Qwen3 30B A3B · OpenRouter
Model ID: openrouter/qwen/qwen3-30b-a3b. Context window: 131072 tokens. Input / output per million tokens: $0.12 / $0.5.
Qwen3 8B · OpenRouter
Model ID: openrouter/qwen/qwen3-8b. Context window: 131072 tokens. Input / output per million tokens: $0.117 / $0.455.
Qwen3 30B A3b fp8 · Cloudflare Workers AI
Model ID: cloudflare-workers-ai/@cf/qwen/qwen3-30b-a3b-fp8. Context window: 32768 tokens. Input / output per million tokens: $0.0509 / $0.335.
Gemini-2.5-Flash · Poe
Model ID: poe/google/gemini-2.5-flash. Context window: 1065535 tokens. Input / output per million tokens: $0.21 / $1.8.
GPT Image 1 · DigitalOcean
Model ID: digitalocean/openai-gpt-image-1. Context window: 0 tokens. Input / output per million tokens: $5 / $40.
OpenAI GPT Image 2 · DigitalOcean
Model ID: digitalocean/openai-gpt-image-2. Context window: 0 tokens. Input / output per million tokens: $8 / $30.
GPT Image 1 · Vercel AI Gateway
Model ID: vercel/openai/gpt-image-1. Context window: 0 tokens. Input / output per million tokens: $5 / $40.
GPT-Image-1 · Azure
Model ID: azure/gpt-image-1. Context window: 0 tokens. Input / output per million tokens: $5 / $40.
Gemini 2.5 Flash Preview Thinking · NanoGPT
Model ID: nano-gpt/gemini-2.5-flash-preview-04-17:thinking. Context window: 1048576 tokens. Input / output per million tokens: $0.15 / $3.5.
Gemini 2.5 Flash Preview · NanoGPT
Model ID: nano-gpt/gemini-2.5-flash-preview-04-17. Context window: 1048576 tokens. Input / output per million tokens: $0.15 / $0.6.
gemini-2.5-flash · SAP AI Core
Model ID: sap-ai-core/gemini-2.5-flash. Context window: 1048576 tokens. Input / output per million tokens: $0.3 / $2.5.
Auto model (Premium) · NanoGPT
Model ID: nano-gpt/auto-model-premium. Context window: 1000000 tokens. Input / output per million tokens: $9.996 / $19.992.
Auto model (Standard) · NanoGPT
Model ID: nano-gpt/auto-model-standard. Context window: 1000000 tokens. Input / output per million tokens: $9.996 / $19.992.
Auto model · NanoGPT
Model ID: nano-gpt/auto-model. Context window: 1000000 tokens. Input / output per million tokens: $0 / $0.
Auto model (Basic) · NanoGPT
Model ID: nano-gpt/auto-model-basic. Context window: 1000000 tokens. Input / output per million tokens: $9.996 / $19.992.
OpenAI o4-mini · NanoGPT
Model ID: nano-gpt/openai/o4-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
OpenAI o3 · NanoGPT
Model ID: nano-gpt/openai/o3. Context window: 200000 tokens. Input / output per million tokens: $2 / $8.
OpenAI o3 · DigitalOcean
Model ID: digitalocean/openai-o3. Context window: 200000 tokens. Input / output per million tokens: $2 / $8.
o4-mini · Impossibl
Model ID: impossibl/openai/o4-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3 · Impossibl
Model ID: impossibl/openai/o3. Context window: 200000 tokens. Input / output per million tokens: $2 / $8.
o4 Mini (Azure) · LLM Gateway
Model ID: llmgateway-providers/azure/o4-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3 (Azure) · LLM Gateway
Model ID: llmgateway-providers/azure/o3. Context window: 200000 tokens. Input / output per million tokens: $2 / $8.
o4 Mini (OpenAI) · LLM Gateway
Model ID: llmgateway-providers/openai/o4-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3 (OpenAI) · LLM Gateway
Model ID: llmgateway-providers/openai/o3. Context window: 200000 tokens. Input / output per million tokens: $2 / $8.
o3 · Azure Cognitive Services
Model ID: azure-cognitive-services/o3. Context window: 200000 tokens. Input / output per million tokens: $2 / $8.
o4-mini · Poe
Model ID: poe/openai/o4-mini. Context window: 200000 tokens. Input / output per million tokens: $0.99 / $4.
o3 · Poe
Model ID: poe/openai/o3. Context window: 200000 tokens. Input / output per million tokens: $1.8 / $7.2.
Qwen2.5 7B Instruct · NovitaAI
Model ID: novita-ai/qwen/qwen2.5-7b-instruct. Context window: 32000 tokens. Input / output per million tokens: $0.07 / $0.07.