Data source: models.dev. Providers may change prices and availability; check the provider's information before use. models.dev
Perplexity Sonar Reasoning Pro · Helicone
Model ID: helicone/sonar-reasoning-pro. Context window: 127000 tokens. Input / output per million tokens: $2 / $8.
Perplexity Sonar Pro · Helicone
Model ID: helicone/sonar-pro. Context window: 200000 tokens. Input / output per million tokens: $3 / $15.
Perplexity Sonar Deep Research · Helicone
Model ID: helicone/sonar-deep-research. Context window: 127000 tokens. Input / output per million tokens: $2 / $8.
Perplexity: Sonar · Kilo Gateway
Model ID: kilo/perplexity/sonar. Context window: 127072 tokens. Input / output per million tokens: $1 / $1.
Sonar · OpenRouter
Model ID: openrouter/perplexity/sonar. Context window: 127072 tokens. Input / output per million tokens: $1 / $1.
qwen2.5-vl-72b-instruct · Cortecs
Model ID: cortecs/qwen2.5-vl-72b-instruct. Context window: 32000 tokens. Input / output per million tokens: $1.014 / $1.014.
Qwen Long · Alibaba (China)
Model ID: alibaba-cn/qwen-long. Context window: 10000000 tokens. Input / output per million tokens: $0.072 / $0.287.
Qwen Plus Latest · DevPass (LLM Gateway)
Model ID: llmgateway/qwen-plus-latest. Context window: 1000000 tokens. Input / output per million tokens: $0.4 / $1.2.
ALLaM-2-7b · Groq
Model ID: groq/allam-2-7b. Context window: 4096 tokens. Input / output per million tokens: $0 / $0.
DeepSeek R1 Distill Llama 70B · FastRouter
Model ID: fastrouter/deepseek-ai/deepseek-r1-distill-llama-70b. Context window: 131072 tokens. Input / output per million tokens: $0.03 / $0.14.
DeepSeek: R1 Distill Llama 70B (retires Sep 28) · Kilo Gateway
Model ID: kilo/deepseek/deepseek-r1-distill-llama-70b. Context window: 8192 tokens. Input / output per million tokens: $0.8 / $0.8.
R1 Distill Llama 70B · OpenRouter
Model ID: openrouter/deepseek/deepseek-r1-distill-llama-70b. Context window: 8192 tokens. Input / output per million tokens: $0.8 / $0.8.
DeepSeek R1 · NanoGPT
Model ID: nano-gpt/deepseek-r1. Context window: 128000 tokens. Input / output per million tokens: $0.4 / $1.7.
DeepSeek-R1 · iFlow
Model ID: iflowcn/deepseek-r1. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
DeepSeek R1 Distill Qwen 32B · NovitaAI
Model ID: novita-ai/deepseek/deepseek-r1-distill-qwen-32b. Context window: 64000 tokens. Input / output per million tokens: $0.3 / $0.3.
DeepSeek R1 Distill Qwen 14B · NovitaAI
Model ID: novita-ai/deepseek/deepseek-r1-distill-qwen-14b. Context window: 32768 tokens. Input / output per million tokens: $0.15 / $0.15.
DeepSeek Reasoner · Helicone
Model ID: helicone/deepseek-reasoner. Context window: 128000 tokens. Input / output per million tokens: $0.56 / $1.68.
DeepSeek R1 Distill Llama 70B · Helicone
Model ID: helicone/deepseek-r1-distill-llama-70b. Context window: 128000 tokens. Input / output per million tokens: $0.03 / $0.13.
DeepSeek-R1 · Hugging Face
Model ID: huggingface/deepseek-ai/DeepSeek-R1. Context window: 64000 tokens. Input / output per million tokens: $0.7 / $2.5.
Z.AI GLM-5.1 · FrogBot
Model ID: frogbot/zai-glm-5-1. Context window: 198000 tokens. Input / output per million tokens: $1.4 / $4.4.
DeepSeek-R1 · Vercel AI Gateway
Model ID: vercel/deepseek/deepseek-r1. Context window: 128000 tokens. Input / output per million tokens: $1.35 / $5.4.
DeepSeek R1 · IO.NET
Model ID: io-net/deepseek-ai/DeepSeek-R1-0528. Context window: 128000 tokens. Input / output per million tokens: $2 / $8.75.
DeepSeek-R1 · Kilo Gateway
Model ID: kilo/deepseek/deepseek-r1. Context window: 64000 tokens. Input / output per million tokens: $0.7 / $2.5.
DeepSeek-R1 · Amazon Bedrock
Model ID: amazon-bedrock/deepseek.r1-v1:0. Context window: 128000 tokens. Input / output per million tokens: $1.35 / $5.4.
DeepSeek-R1 (US) · Amazon Bedrock
Model ID: amazon-bedrock/us.deepseek.r1-v1:0. Context window: 128000 tokens. Input / output per million tokens: $1.35 / $5.4.
DeepSeek R1 · Merge Gateway
Model ID: merge-gateway/deepseek/deepseek-r1. Context window: 163840 tokens. Input / output per million tokens: $1.35 / $5.4.
DeepSeek R1 · Abacus
Model ID: abacus/deepseek-ai/DeepSeek-R1. Context window: 128000 tokens. Input / output per million tokens: $3 / $7.
DeepSeek V3.1 · Abacus
Model ID: abacus/deepseek/deepseek-v3.1. Context window: 128000 tokens. Input / output per million tokens: $0.55 / $1.66.
DeepSeek-R1 · OpenRouter
Model ID: openrouter/deepseek/deepseek-r1. Context window: 64000 tokens. Input / output per million tokens: $0.7 / $2.5.
DeepSeek-R1 · Snowflake Cortex
Model ID: snowflake-cortex/deepseek-r1. Context window: 128000 tokens. Input / output per million tokens: — / —.
DeepSeek-R1 · Melious
Model ID: melious/deepseek-r1-0528. Context window: 164000 tokens. Input / output per million tokens: $0.69552 / $2.78208.
Deepseek R1 Distill Qwen 32B · Cloudflare Workers AI
Model ID: cloudflare-workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b. Context window: 80000 tokens. Input / output per million tokens: $0.497 / $4.881.
DeepSeek R1 · D.Run (China)
Model ID: drun/public/deepseek-r1. Context window: 131072 tokens. Input / output per million tokens: $0.55 / $2.2.
DeepSeek-R1 (Deep Infra) · Eden AI
Model ID: edenai/deepinfra/deepseek-ai/DeepSeek-R1. Context window: 163840 tokens. Input / output per million tokens: $0.7 / $2.4.
Qwen Omni Turbo (Alibaba Cloud) · LLM Gateway
Model ID: llmgateway-providers/alibaba/qwen-omni-turbo. Context window: 32768 tokens. Input / output per million tokens: $0.2 / $0.8.
Qwen-Omni Turbo · Alibaba (China)
Model ID: alibaba-cn/qwen-omni-turbo. Context window: 32768 tokens. Input / output per million tokens: $0.058 / $0.23.
Qwen-Omni Turbo · Alibaba
Model ID: alibaba/qwen-omni-turbo. Context window: 32768 tokens. Input / output per million tokens: $0.07 / $0.27.
Qwen-Omni Turbo · DevPass (LLM Gateway)
Model ID: llmgateway/qwen-omni-turbo. Context window: 32768 tokens. Input / output per million tokens: $0.2 / $0.8.
MiniMax Text 01 (MiniMax) · LLM Gateway
Model ID: llmgateway-providers/minimax/minimax-text-01. Context window: 1000000 tokens. Input / output per million tokens: $0.2 / $1.1.
MiniMax-M2.5 · FrogBot
Model ID: frogbot/minimax-m2-5. Context window: 192000 tokens. Input / output per million tokens: $0.3 / $1.2.
Claude Sonnet 4.5 · Venice AI
Model ID: venice/claude-sonnet-4-5. Context window: 198000 tokens. Input / output per million tokens: $3.75 / $18.75.
Qwen 3 Coder 480B · IO.NET
Model ID: io-net/Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar. Context window: 106000 tokens. Input / output per million tokens: $0.22 / $0.95.
Llama 4 Maverick 17B 128E Instruct · IO.NET
Model ID: io-net/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8. Context window: 430000 tokens. Input / output per million tokens: $0.15 / $0.6.
MiniMax Text 01 · DevPass (LLM Gateway)
Model ID: llmgateway/minimax-text-01. Context window: 1000000 tokens. Input / output per million tokens: $0.2 / $1.1.
MiniMax: MiniMax-01 · Kilo Gateway
Model ID: kilo/minimax/minimax-01. Context window: 1000192 tokens. Input / output per million tokens: $0.2 / $1.1.
MiniMax-01 · OpenRouter
Model ID: openrouter/minimax/minimax-01. Context window: 1000192 tokens. Input / output per million tokens: $0.2 / $1.1.
GLM 4 Air 0111 · NanoGPT
Model ID: nano-gpt/glm-4-air-0111. Context window: 128000 tokens. Input / output per million tokens: $0.1394 / $0.1394.
Qwen 3 Next 80B Instruct · IO.NET
Model ID: io-net/Qwen/Qwen3-Next-80B-A3B-Instruct. Context window: 262144 tokens. Input / output per million tokens: $0.1 / $0.8.
Microsoft: Phi 4 · Kilo Gateway
Model ID: kilo/microsoft/phi-4. Context window: 16384 tokens. Input / output per million tokens: $0.07 / $0.14.
Phi 4 · OpenRouter
Model ID: openrouter/microsoft/phi-4. Context window: 16384 tokens. Input / output per million tokens: $0.07 / $0.14.
MiniMax M1 · NanoGPT
Model ID: nano-gpt/MiniMax-M1. Context window: 1000000 tokens. Input / output per million tokens: $0.1394 / $1.3328.
MiniMax M1 80K · NanoGPT
Model ID: nano-gpt/MiniMaxAI/MiniMax-M1-80k. Context window: 1000000 tokens. Input / output per million tokens: $0.6052 / $2.4225.
voyage-3-large · Vercel AI Gateway
Model ID: vercel/voyage/voyage-3-large. Context window: 8192 tokens. Input / output per million tokens: — / —.
Qwen 2.5 32B Abliterated · NanoGPT
Model ID: nano-gpt/huihui-ai/Qwen2.5-32B-Instruct-abliterated. Context window: 32768 tokens. Input / output per million tokens: $0.7 / $0.7.
Qwen3-VL-Plus · iFlow
Model ID: iflowcn/qwen3-vl-plus. Context window: 256000 tokens. Input / output per million tokens: $0 / $0.
Qwen3-Max-Preview · iFlow
Model ID: iflowcn/qwen3-max-preview. Context window: 256000 tokens. Input / output per million tokens: $0 / $0.
DeepSeek-V3.2-Exp · iFlow
Model ID: iflowcn/deepseek-v3.2. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Qwen3-Max · iFlow
Model ID: iflowcn/qwen3-max. Context window: 256000 tokens. Input / output per million tokens: $0 / $0.
OrcaRouter Auto · OrcaRouter
Model ID: orcarouter/orcarouter/auto. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Codestral 25.01 · Azure Cognitive Services
Model ID: azure-cognitive-services/codestral-2501. Context window: 256000 tokens. Input / output per million tokens: $0.3 / $0.9.
Step 1 (32K) · StepFun (Global)
Model ID: stepfun-ai/step-1-32k. Context window: 32768 tokens. Input / output per million tokens: $2.05 / $9.59.
Step 2 (16K) · StepFun (Global)
Model ID: stepfun-ai/step-2-16k. Context window: 16384 tokens. Input / output per million tokens: $5.21 / $16.44.
DeepSeek R1 Distill Qwen 7B · Alibaba (China)
Model ID: alibaba-cn/deepseek-r1-distill-qwen-7b. Context window: 32768 tokens. Input / output per million tokens: $0.072 / $0.144.
DeepSeek V3.1 · Alibaba (China)
Model ID: alibaba-cn/deepseek-v3-1. Context window: 131072 tokens. Input / output per million tokens: $0.574 / $1.721.
Moonshot Kimi K2 Instruct · Alibaba (China)
Model ID: alibaba-cn/moonshot-kimi-k2-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.574 / $2.294.
DeepSeek V3.2 Exp · Alibaba (China)
Model ID: alibaba-cn/deepseek-v3-2-exp. Context window: 131072 tokens. Input / output per million tokens: $0.287 / $0.431.
DeepSeek R1 · Alibaba (China)
Model ID: alibaba-cn/deepseek-r1. Context window: 131072 tokens. Input / output per million tokens: $0.574 / $2.294.
DeepSeek R1 Distill Qwen 1.5B · Alibaba (China)
Model ID: alibaba-cn/deepseek-r1-distill-qwen-1-5b. Context window: 32768 tokens. Input / output per million tokens: $0 / $0.
DeepSeek R1 Distill Qwen 32B · Alibaba (China)
Model ID: alibaba-cn/deepseek-r1-distill-qwen-32b. Context window: 32768 tokens. Input / output per million tokens: $0.287 / $0.861.
DeepSeek R1 Distill Llama 70B · Alibaba (China)
Model ID: alibaba-cn/deepseek-r1-distill-llama-70b. Context window: 32768 tokens. Input / output per million tokens: $0.287 / $0.861.
DeepSeek R1 Distill Llama 8B · Alibaba (China)
Model ID: alibaba-cn/deepseek-r1-distill-llama-8b. Context window: 32768 tokens. Input / output per million tokens: $0 / $0.
DeepSeek R1 Distill Qwen 14B · Alibaba (China)
Model ID: alibaba-cn/deepseek-r1-distill-qwen-14b. Context window: 32768 tokens. Input / output per million tokens: $0.144 / $0.431.
OpenAI GPT-5 Nano · Helicone
Model ID: helicone/gpt-5-nano. Context window: 400000 tokens. Input / output per million tokens: $0.049999999999999996 / $0.39999999999999997.
OpenAI: GPT-5 Codex · Helicone
Model ID: helicone/gpt-5-codex. Context window: 400000 tokens. Input / output per million tokens: $1.25 / $10.
OpenAI: GPT-5 Pro · Helicone
Model ID: helicone/gpt-5-pro. Context window: 128000 tokens. Input / output per million tokens: $15 / $120.
Qwen3 Next 80B A3B Instruct · Helicone
Model ID: helicone/qwen3-next-80b-a3b-instruct. Context window: 262000 tokens. Input / output per million tokens: $0.14 / $1.4.
OpenAI: GPT-5.1 Codex Mini · Helicone
Model ID: helicone/gpt-5.1-codex-mini. Context window: 400000 tokens. Input / output per million tokens: $0.25 / $2.
OpenAI: GPT-5.1 Codex · Helicone
Model ID: helicone/gpt-5.1-codex. Context window: 400000 tokens. Input / output per million tokens: $1.25 / $10.
OpenAI GPT-5.1 · Helicone
Model ID: helicone/gpt-5.1. Context window: 400000 tokens. Input / output per million tokens: $1.25 / $10.
OpenAI GPT-5.1 Chat · Helicone
Model ID: helicone/gpt-5.1-chat-latest. Context window: 128000 tokens. Input / output per million tokens: $1.25 / $10.
OpenAI: o1-mini · Helicone
Model ID: helicone/o1-mini. Context window: 128000 tokens. Input / output per million tokens: $1.1 / $4.4.
Meta Llama 4 Maverick 17B 128E · Helicone
Model ID: helicone/llama-4-maverick. Context window: 131072 tokens. Input / output per million tokens: $0.15 / $0.6.
OpenAI: o1 · Helicone
Model ID: helicone/o1. Context window: 200000 tokens. Input / output per million tokens: $15 / $60.
Meta Llama Guard 4 12B · Helicone
Model ID: helicone/llama-guard-4. Context window: 131072 tokens. Input / output per million tokens: $0.21 / $0.21.
Kimi K2 (07/11) · Helicone
Model ID: helicone/kimi-k2-0711. Context window: 131072 tokens. Input / output per million tokens: $0.5700000000000001 / $2.3.
Meta Llama 4 Scout 17B 16E · Helicone
Model ID: helicone/llama-4-scout. Context window: 131072 tokens. Input / output per million tokens: $0.08 / $0.3.
OpenAI GPT-5 Mini · Helicone
Model ID: helicone/gpt-5-mini. Context window: 400000 tokens. Input / output per million tokens: $0.25 / $2.
OpenAI GPT-5 · Helicone
Model ID: helicone/gpt-5. Context window: 400000 tokens. Input / output per million tokens: $1.25 / $10.
Step 2 (16K) · StepFun (China)
Model ID: stepfun/step-2-16k. Context window: 16384 tokens. Input / output per million tokens: $5.21 / $16.44.
Step 1 (32K) · StepFun (China)
Model ID: stepfun/step-1-32k. Context window: 32768 tokens. Input / output per million tokens: $2.05 / $9.59.
Qwen 3 Embedding 8B · Hugging Face
Model ID: huggingface/Qwen/Qwen3-Embedding-8B. Context window: 32000 tokens. Input / output per million tokens: $0.01 / $0.
Qwen 3 Embedding 4B · Hugging Face
Model ID: huggingface/Qwen/Qwen3-Embedding-4B. Context window: 32000 tokens. Input / output per million tokens: $0.01 / $0.
Llama 3.1 8B Instruct · Nvidia
Model ID: nvidia/meta/llama-3.1-8b-instruct. Context window: 16000 tokens. Input / output per million tokens: $0 / $0.
Codestral 25.01 · Azure
Model ID: azure/codestral-2501. Context window: 256000 tokens. Input / output per million tokens: $0.3 / $0.9.
Qwen 2.5 7B Vision Instruct · Inference
Model ID: inference/qwen/qwen-2.5-7b-vision-instruct. Context window: 125000 tokens. Input / output per million tokens: $0.2 / $0.2.
Qwen 3 Embedding 4B · Inference
Model ID: inference/qwen/qwen3-embedding-4b. Context window: 32000 tokens. Input / output per million tokens: $0.01 / $0.
Google Gemma 3 · Inference
Model ID: inference/google/gemma-3. Context window: 125000 tokens. Input / output per million tokens: $0.15 / $0.3.
Llama 3.1 8B Instruct · Inference
Model ID: inference/meta/llama-3.1-8b-instruct. Context window: 16000 tokens. Input / output per million tokens: $0.025 / $0.025.
Llama 3.2 3B Instruct · Inference
Model ID: inference/meta/llama-3.2-3b-instruct. Context window: 16000 tokens. Input / output per million tokens: $0.02 / $0.02.
Llama 3.2 1B Instruct · Inference
Model ID: inference/meta/llama-3.2-1b-instruct. Context window: 16000 tokens. Input / output per million tokens: $0.01 / $0.01.
Llama 3.2 11B Vision Instruct · Inference
Model ID: inference/meta/llama-3.2-11b-vision-instruct. Context window: 16000 tokens. Input / output per million tokens: $0.055 / $0.055.
Osmosis Structure 0.6B · Inference
Model ID: inference/osmosis/osmosis-structure-0.6b. Context window: 4000 tokens. Input / output per million tokens: $0.1 / $0.5.
Mistral Nemo 12B Instruct · Inference
Model ID: inference/mistral/mistral-nemo-12b-instruct. Context window: 16000 tokens. Input / output per million tokens: $0.038 / $0.1.
Green S · GreenPT
Model ID: greenpt/green-s. Context window: 0 tokens. Input / output per million tokens: $0.00437 / $0.
Qwen-MT Turbo · Alibaba (China)
Model ID: alibaba-cn/qwen-mt-turbo. Context window: 16384 tokens. Input / output per million tokens: $0.101 / $0.28.
Qwen-MT Plus · Alibaba (China)
Model ID: alibaba-cn/qwen-mt-plus. Context window: 16384 tokens. Input / output per million tokens: $0.259 / $0.775.
Qwen-MT Turbo · Alibaba
Model ID: alibaba/qwen-mt-turbo. Context window: 16384 tokens. Input / output per million tokens: $0.16 / $0.49.
Qwen-MT Plus · Alibaba
Model ID: alibaba/qwen-mt-plus. Context window: 16384 tokens. Input / output per million tokens: $2.46 / $7.37.
LucidNova RF1 100B · LucidQuery
Model ID: lucidquery/lucidnova-rf1-100b. Context window: 120000 tokens. Input / output per million tokens: $2 / $5.
DeepSeek V3 · DigitalOcean
Model ID: digitalocean/deepseek-v3. Context window: 163840 tokens. Input / output per million tokens: — / —.
deepseek-ai/DeepSeek-V3 · SiliconFlow (China)
Model ID: siliconflow-cn/deepseek-ai/DeepSeek-V3. Context window: 164000 tokens. Input / output per million tokens: $0.25 / $1.
Pro/deepseek-ai/DeepSeek-V3 · SiliconFlow (China)
Model ID: siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3. Context window: 164000 tokens. Input / output per million tokens: $0.25 / $1.
DeepSeek-V3 · iFlow
Model ID: iflowcn/deepseek-v3. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
siliconflow/deepseek-v3-0324 · Alibaba (China)
Model ID: alibaba-cn/siliconflow/deepseek-v3-0324. Context window: 163840 tokens. Input / output per million tokens: $0.25 / $1.
DeepSeek-V3 · Pioneer
Model ID: pioneer/deepseek-ai/DeepSeek-V3. Context window: 163840 tokens. Input / output per million tokens: $0.27 / $1.12.
DeepSeek V3 · Helicone
Model ID: helicone/deepseek-v3. Context window: 128000 tokens. Input / output per million tokens: $0.56 / $1.68.
DeepSeek-V3 · Hugging Face
Model ID: huggingface/deepseek-ai/DeepSeek-V3. Context window: 64000 tokens. Input / output per million tokens: $0.4 / $1.3.
DeepSeek-V3 · Deep Infra
Model ID: deepinfra/deepseek-ai/DeepSeek-V3. Context window: 163840 tokens. Input / output per million tokens: $0.32 / $0.89.
DeepSeek V3 · Merge Gateway
Model ID: merge-gateway/deepseek/deepseek-v3. Context window: 163840 tokens. Input / output per million tokens: $0.58 / $1.68.
deepseek-ai/DeepSeek-V3 · SiliconFlow
Model ID: siliconflow/deepseek-ai/DeepSeek-V3. Context window: 164000 tokens. Input / output per million tokens: $0.25 / $1.
DeepSeek V3 · D.Run (China)
Model ID: drun/public/deepseek-v3. Context window: 131072 tokens. Input / output per million tokens: $0.28 / $1.1.
DeepSeek-V3 (Deep Infra) · Eden AI
Model ID: edenai/deepinfra/deepseek-ai/DeepSeek-V3. Context window: 163840 tokens. Input / output per million tokens: $0.32 / $0.89.
OpenAI o3-mini · NanoGPT
Model ID: nano-gpt/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
OpenAI o3 mini · DigitalOcean
Model ID: digitalocean/openai-o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3-mini · Impossibl
Model ID: impossibl/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3 Mini (Azure) · LLM Gateway
Model ID: llmgateway-providers/azure/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3 Mini (OpenAI) · LLM Gateway
Model ID: llmgateway-providers/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3-mini · DevPass (LLM Gateway)
Model ID: llmgateway/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3-mini · Cloudflare AI Gateway
Model ID: cloudflare-ai-gateway/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3-mini · Kilo Gateway
Model ID: kilo/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3 Mini · Merge Gateway
Model ID: merge-gateway/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3-mini · Abacus
Model ID: abacus/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3-mini · NEAR AI Cloud
Model ID: nearai/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3-mini · OpenRouter
Model ID: openrouter/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o3-mini · AnyAPI
Model ID: anyapi/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: — / —.
o3-mini · Eden AI
Model ID: edenai/openai/o3-mini. Context window: 200000 tokens. Input / output per million tokens: $1.1 / $4.4.
o1 · Poe
Model ID: poe/openai/o1. Context window: 200000 tokens. Input / output per million tokens: $14 / $54.
Sao10K: Llama 3.3 Euryale 70B · Kilo Gateway
Model ID: kilo/sao10k/l3.3-euryale-70b. Context window: 131072 tokens. Input / output per million tokens: $0.65 / $0.75.
Llama 3.3 Euryale 70B · OpenRouter
Model ID: openrouter/sao10k/l3.3-euryale-70b. Context window: 131072 tokens. Input / output per million tokens: $0.65 / $0.75.
Phi-4-reasoning · Azure Cognitive Services
Model ID: azure-cognitive-services/phi-4-reasoning. Context window: 32000 tokens. Input / output per million tokens: $0.125 / $0.5.
Phi-4-mini · Azure Cognitive Services
Model ID: azure-cognitive-services/phi-4-mini. Context window: 128000 tokens. Input / output per million tokens: $0.075 / $0.3.
Phi-4-multimodal · Azure Cognitive Services
Model ID: azure-cognitive-services/phi-4-multimodal. Context window: 128000 tokens. Input / output per million tokens: $0.08 / $0.32.
Phi-4 · Azure Cognitive Services
Model ID: azure-cognitive-services/phi-4. Context window: 128000 tokens. Input / output per million tokens: $0.125 / $0.5.
Phi-4-reasoning-plus · Azure Cognitive Services
Model ID: azure-cognitive-services/phi-4-reasoning-plus. Context window: 32000 tokens. Input / output per million tokens: $0.125 / $0.5.
Phi-4-mini-reasoning · Azure Cognitive Services
Model ID: azure-cognitive-services/phi-4-mini-reasoning. Context window: 128000 tokens. Input / output per million tokens: $0.075 / $0.3.
Gemini-2.0-Flash · Poe
Model ID: poe/google/gemini-2.0-flash. Context window: 990000 tokens. Input / output per million tokens: $0.1 / $0.42.
Phi-4-mini-reasoning · Azure
Model ID: azure/phi-4-mini-reasoning. Context window: 128000 tokens. Input / output per million tokens: $0.075 / $0.3.
Phi-4-reasoning-plus · Azure
Model ID: azure/phi-4-reasoning-plus. Context window: 32000 tokens. Input / output per million tokens: $0.125 / $0.5.
Phi-4 · Azure
Model ID: azure/phi-4. Context window: 128000 tokens. Input / output per million tokens: $0.125 / $0.5.
Phi-4-multimodal · Azure
Model ID: azure/phi-4-multimodal. Context window: 128000 tokens. Input / output per million tokens: $0.08 / $0.32.
Phi-4-mini · Azure
Model ID: azure/phi-4-mini. Context window: 128000 tokens. Input / output per million tokens: $0.075 / $0.3.
Phi-4-reasoning · Azure
Model ID: azure/phi-4-reasoning. Context window: 32000 tokens. Input / output per million tokens: $0.125 / $0.5.
Llama 3.3 70B Instruct · NovitaAI
Model ID: novita-ai/meta-llama/llama-3.3-70b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.135 / $0.4.
Llama-3.3-70B-Instruct · GreenPT
Model ID: greenpt/llama-3.3-70b-instruct. Context window: 100000 tokens. Input / output per million tokens: $1.254 / $1.254.
Gemini 2.0 Pro 1206 · NanoGPT
Model ID: nano-gpt/gemini-exp-1206. Context window: 2097152 tokens. Input / output per million tokens: $1.258 / $4.998.
Llama 3.3 70b Instruct · NanoGPT
Model ID: nano-gpt/meta-llama/llama-3.3-70b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.05 / $0.23.
Llama-3.3-70B-Instruct · watsonx.ai
Model ID: watsonx/meta-llama/llama-3-3-70b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.7526 / $0.7526.
Llama 3.3 Instruct (70B) · DigitalOcean
Model ID: digitalocean/llama3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.65 / $0.65.
Llama-3.3-70B-Instruct · evroc
Model ID: evroc/nvidia/Llama-3.3-70B-Instruct-FP8. Context window: 128000 tokens. Input / output per million tokens: $1.15 / $1.15.
Llama 3.3 70B Instruct (NovitaAI) · LLM Gateway
Model ID: llmgateway-providers/novita/llama-3.3-70b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.135 / $0.4.
Llama 3.3 70B Instruct (Cerebras) · LLM Gateway
Model ID: llmgateway-providers/cerebras/llama-3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.85 / $1.2.
Llama-3.3-70B-Instruct · Llama
Model ID: llama/llama-3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Llama-3.3-8B-Instruct · Llama
Model ID: llama/llama-3.3-8b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Llama 3.3 70B · Groq
Model ID: groq/llama-3.3-70b-versatile. Context window: 131072 tokens. Input / output per million tokens: $0.59 / $0.79.
Llama-3.3-70B-Instruct · Azure Cognitive Services
Model ID: azure-cognitive-services/llama-3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.71 / $0.71.
Llama-3.3-70B-Instruct · Pendra
Model ID: pendra/llama3.3:70b. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Llama-3.3-70B-Instruct · Scaleway
Model ID: scaleway/llama-3.3-70b-instruct. Context window: 100000 tokens. Input / output per million tokens: $0.9 / $0.9.
Llama-3.3-70B-Instruct · Pioneer
Model ID: pioneer/meta-llama/Llama-3.3-70B-Instruct. Context window: 16384 tokens. Input / output per million tokens: $0.9 / $0.9.
Meta Llama 3.3 70B Versatile · Helicone
Model ID: helicone/llama-3.3-70b-versatile. Context window: 131072 tokens. Input / output per million tokens: $0.59 / $0.7899999999999999.
Meta Llama 3.3 70B Instruct · Helicone
Model ID: helicone/llama-3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.13 / $0.39.
Llama 3.3 70B Instruct · CloudFerro Sherlock
Model ID: cloudferro-sherlock/meta-llama/Llama-3.3-70B-Instruct. Context window: 70000 tokens. Input / output per million tokens: $2.92 / $2.92.
Llama-3.3-70B-Instruct · Hugging Face
Model ID: huggingface/meta-llama/Llama-3.3-70B-Instruct. Context window: 131072 tokens. Input / output per million tokens: $0.59 / $0.79.
Llama-3.3-70B-Instruct · Vercel AI Gateway
Model ID: vercel/meta/llama-3.3-70b. Context window: 128000 tokens. Input / output per million tokens: $0 / $0.
Llama 3.3 70B Instruct · IO.NET
Model ID: io-net/meta-llama/Llama-3.3-70B-Instruct. Context window: 128000 tokens. Input / output per million tokens: $0.13 / $0.38.
Llama-3.3-70B-Instruct · DevPass (LLM Gateway)
Model ID: llmgateway/llama-3.3-70b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.135 / $0.4.
Llama-3.3-70B-Instruct · Crusoe
Model ID: crusoe/meta-llama/Llama-3.3-70B-Instruct. Context window: 128000 tokens. Input / output per million tokens: $0.25 / $0.75.
Llama 3.3 70B Turbo · Deep Infra
Model ID: deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo. Context window: 131072 tokens. Input / output per million tokens: $0.1 / $0.32.
Llama-3.3-70B-Instruct · Kilo Gateway
Model ID: kilo/meta-llama/llama-3.3-70b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.1 / $0.32.
Llama-3.3-70B-Instruct · Azure
Model ID: azure/llama-3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.71 / $0.71.
Llama 3.3 70B Instruct · Amazon Bedrock
Model ID: amazon-bedrock/meta.llama3-3-70b-instruct-v1:0. Context window: 128000 tokens. Input / output per million tokens: $0.72 / $0.72.
Llama 3.3 70B Instruct (US) · Amazon Bedrock
Model ID: amazon-bedrock/us.meta.llama3-3-70b-instruct-v1:0. Context window: 128000 tokens. Input / output per million tokens: $0.72 / $0.72.
Llama 3.3 70B Instruct · Merge Gateway
Model ID: merge-gateway/meta/llama-3.3-70b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.22 / $0.5.
Llama 3.3 70B Versatile · Abacus
Model ID: abacus/llama-3.3-70b-versatile. Context window: 128000 tokens. Input / output per million tokens: $0.59 / $0.79.
Llama-3.3-70B-Instruct · Abacus
Model ID: abacus/meta-llama/Meta-Llama-3.3-70B-Instruct. Context window: 131072 tokens. Input / output per million tokens: $0.59 / $0.79.
Llama-3.3-70B-Instruct · OpenRouter
Model ID: openrouter/meta-llama/llama-3.3-70b-instruct. Context window: 131072 tokens. Input / output per million tokens: $0.1 / $0.32.
Llama-3.3-70B-Instruct · Neon
Model ID: neon/meta-llama-3-3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.5 / $1.5.
Llama-3.3-70B-Instruct · Snowflake Cortex
Model ID: snowflake-cortex/snowflake-llama3.3-70b. Context window: 128000 tokens. Input / output per million tokens: — / —.
Llama 3.3 70B Instruct · Meganova
Model ID: meganova/meta-llama/Llama-3.3-70B-Instruct. Context window: 131072 tokens. Input / output per million tokens: $0.1 / $0.3.
Llama 3.3 70B · Together AI
Model ID: togetherai/meta-llama/Llama-3.3-70B-Instruct-Turbo. Context window: 131072 tokens. Input / output per million tokens: $1.04 / $1.04.
Llama 3.3 70B Instruct fp8 Fast · Cloudflare Workers AI
Model ID: cloudflare-workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast. Context window: 24000 tokens. Input / output per million tokens: $0.293 / $2.253.
Llama-3.3-70B-Instruct · Cortecs
Model ID: cortecs/llama-3.3-70b-instruct. Context window: 131000 tokens. Input / output per million tokens: $0.724 / $0.724.
Llama-3.3-70B-Instruct · OCI Generative AI
Model ID: oci/meta.llama-3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $0.72 / $0.72.
Llama-3.3-70B-Instruct · Tinfoil
Model ID: tinfoil/llama3-3-70b. Context window: 131072 tokens. Input / output per million tokens: $1.75 / $2.75.
Llama-3.3-70B-Instruct (Scaleway) · Eden AI
Model ID: edenai/scaleway/llama-3.3-70b-instruct. Context window: 128000 tokens. Input / output per million tokens: $1.0314 / $1.0314.
Llama-3.3-70B-Instruct (Deep Infra) · Eden AI
Model ID: edenai/deepinfra/meta-llama/Llama-3.3-70B-Instruct. Context window: 131072 tokens. Input / output per million tokens: $0.1 / $0.32.
Llama-3.3-70B-Instruct (IONOS) · Eden AI
Model ID: edenai/ionos/meta-llama/Llama-3.3-70B-Instruct. Context window: 128000 tokens. Input / output per million tokens: $0.7449 / $0.7449.
OpenAI o1 · NanoGPT
Model ID: nano-gpt/openai/o1. Context window: 200000 tokens. Input / output per million tokens: $15 / $60.
OpenAI o1 · DigitalOcean
Model ID: digitalocean/openai-o1. Context window: 200000 tokens. Input / output per million tokens: $15 / $60.
o1 · Impossibl
Model ID: impossibl/openai/o1. Context window: 200000 tokens. Input / output per million tokens: $15 / $60.
o1 (Azure) · LLM Gateway
Model ID: llmgateway-providers/azure/o1. Context window: 200000 tokens. Input / output per million tokens: $15 / $60.