Model Costs
Current pricing for all supported AI models per 1 million tokens. Some models include a separate long-context tier when prompt tokens meet or exceed the listed threshold.
note
Prices are subject to change by the model providers. This page reflects our current rate cards and may not include the most recent provider updates.
OpenAI
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Long Context Threshold | Long Context Input Cost (per 1M tokens) | Long Context Output Cost (per 1M tokens) |
|---|---|---|---|---|---|
| gpt-3.5-turbo | $0.5000 | $1.5000 | - | - | - |
| gpt-3.5-turbo-0613 | $1.5000 | $2.0000 | - | - | - |
| gpt-3.5-turbo-instruct | $1.5000 | $2.0000 | - | - | - |
| gpt-4 | $30.0000 | $60.0000 | - | - | - |
| gpt-4-0613 | $30.0000 | $60.0000 | - | - | - |
| gpt-4o-mini, gpt-4o-mini-2024-07-18 | $0.1500 | $0.6000 | - | - | - |
| gpt-4-32k | $60.0000 | $120.0000 | - | - | - |
| gpt-4-vision-preview, gpt-4-turbo-preview | $10.0000 | $30.0000 | - | - | - |
| gpt-4-turbo | $10.0000 | $30.0000 | - | - | - |
| gpt-4o-2024-05-13 | $5.0000 | $15.0000 | - | - | - |
| gpt-4o-2024-08-06, gpt-4o | $2.5000 | $10.0000 | - | - | - |
| o1, o1-2024-12-17 | $15.0000 | $60.0000 | - | - | - |
| o1-mini, o1-mini-2024-09-12 | $1.1000 | $4.4000 | - | - | - |
| o3-mini, o3-mini-2025-01-31, o3-mini-low, o3-mini-medium, o3-mini-high | $1.1000 | $4.4000 | - | - | - |
| o3 | $2.0000 | $8.0000 | - | - | - |
| o4-mini, o4-mini-low, o4-mini-medium, o4-mini-high | $1.1000 | $4.4000 | - | - | - |
| gpt-4.5-preview | $75.0000 | $150.0000 | - | - | - |
| gpt-4.1, gpt-4.1-2025-04-14 | $2.0000 | $8.0000 | - | - | - |
| gpt-4.1-mini, gpt-4.1-mini-2025-04-14 | $0.4000 | $1.6000 | - | - | - |
| gpt-4.1-nano, gpt-4.1-nano-2025-04-14 | $0.1000 | $0.4000 | - | - | - |
| gpt-5, gpt-5-2025-08-07, gpt-5-minimal, gpt-5-low, gpt-5-medium, gpt-5-high | $1.2500 | $10.0000 | - | - | - |
| gpt-5-pro | $15.0000 | $120.0000 | - | - | - |
| gpt-5.1-none, gpt-5.1-low, gpt-5.1-medium, gpt-5.1-high | $1.2500 | $10.0000 | - | - | - |
| gpt-5.2-none, gpt-5.2-low, gpt-5.2-medium, gpt-5.2-high | $1.7500 | $14.0000 | - | - | - |
| gpt-5.6-sol-none, gpt-5.6-sol-low, gpt-5.6-sol-medium, gpt-5.6-sol-high, gpt-5.6-sol-xhigh, gpt-5.6-sol-max | $5.0000 | $30.0000 | 272,001 tokens | $10.0000 | $45.0000 |
| gpt-5.6-terra-none, gpt-5.6-terra-low, gpt-5.6-terra-medium, gpt-5.6-terra-high, gpt-5.6-terra-xhigh, gpt-5.6-terra-max | $2.5000 | $15.0000 | 272,001 tokens | $5.0000 | $22.5000 |
| gpt-5.6-luna-none, gpt-5.6-luna-low, gpt-5.6-luna-medium, gpt-5.6-luna-high, gpt-5.6-luna-xhigh, gpt-5.6-luna-max | $1.0000 | $6.0000 | 272,001 tokens | $2.0000 | $9.0000 |
| gpt-5.5-none, gpt-5.5-low, gpt-5.5-medium, gpt-5.5-high, gpt-5.5-xhigh | $5.0000 | $30.0000 | - | - | - |
| gpt-5.4-none, gpt-5.4-low, gpt-5.4-medium, gpt-5.4-high, gpt-5.4-xhigh | $2.5000 | $15.0000 | 272,000 tokens | $5.0000 | $22.5000 |
| gpt-5.4-mini, gpt-5.4-mini-2026-03-17, gpt-5.4-mini-none, gpt-5.4-mini-low, gpt-5.4-mini-medium, gpt-5.4-mini-high, gpt-5.4-mini-xhigh | $0.7500 | $4.5000 | - | - | - |
| gpt-5.4-nano, gpt-5.4-nano-2026-03-17, gpt-5.4-nano-none, gpt-5.4-nano-low, gpt-5.4-nano-medium, gpt-5.4-nano-high, gpt-5.4-nano-xhigh | $0.2000 | $1.2500 | - | - | - |
| gpt-5.3-codex-low, gpt-5.3-codex-medium, gpt-5.3-codex-high, gpt-5.3-codex-xhigh, gpt-5.2-codex-low, gpt-5.2-codex-medium, gpt-5.2-codex-high, gpt-5.2-codex-xhigh | $1.7500 | $14.0000 | - | - | - |
| gpt-5.2-pro | $21.0000 | $168.0000 | - | - | - |
| gpt-5-mini, gpt-5-mini-2025-08-07 | $0.2500 | $2.0000 | - | - | - |
| gpt-5.1-codex-max, gpt-5.1-codex, gpt-5-codex | $1.2500 | $10.0000 | - | - | - |
| gpt-5.1-codex-mini | $0.2500 | $2.0000 | - | - | - |
| gpt-5-nano, gpt-5-nano-2025-08-07 | $0.0500 | $0.4000 | - | - | - |
| computer-use-preview, computer-use-preview-2025-03-11 | $3.0000 | $12.0000 | - | - | - |
Embedding Models
| Model | Cost (per 1M tokens) |
|---|---|
| text-embedding-3-large | $0.1300 |
| text-embedding-3-small | $0.0200 |
| text-embedding-ada-002 | $0.1000 |
Anthropic
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Long Context Threshold | Long Context Input Cost (per 1M tokens) | Long Context Output Cost (per 1M tokens) |
|---|---|---|---|---|---|
| claude-fable-5 | $10.0000 | $50.0000 | - | - | - |
| claude-opus-4-8 | $5.0000 | $25.0000 | - | - | - |
| claude-opus-4-7 | $5.0000 | $25.0000 | 200,000 tokens | $10.0000 | $37.5000 |
| claude-opus-4-6 | $5.0000 | $25.0000 | 200,000 tokens | $10.0000 | $37.5000 |
| claude-opus-4-5-20251101 | $5.0000 | $25.0000 | - | - | - |
| claude-opus-4-1-20250805 | $15.0000 | $75.0000 | - | - | - |
| claude-opus-4-20250514 | $15.0000 | $75.0000 | - | - | - |
| claude-sonnet-4-6 | $3.0000 | $15.0000 | 200,000 tokens | $6.0000 | $22.5000 |
| claude-sonnet-4-20250514 | $3.0000 | $15.0000 | 200,000 tokens | $6.0000 | $22.5000 |
| claude-sonnet-4-5-20250929 | $3.0000 | $15.0000 | 200,000 tokens | $6.0000 | $22.5000 |
| claude-haiku-4-5 | $1.0000 | $5.0000 | - | - | - |
| claude-3-5-haiku-20241022 | $0.8000 | $4.0000 | - | - | - |
| claude-3-haiku-20240307 | $0.2500 | $1.2500 | - | - | - |
| claude-3-sonnet-20240229 | $3.0000 | $15.0000 | - | - | - |
| claude-3-5-sonnet-20240620, claude-3-5-sonnet-20241022 | $3.0000 | $15.0000 | - | - | - |
| claude-3-7-sonnet-20250219, claude-3-7-sonnet-latest | $3.0000 | $15.0000 | - | - | - |
| claude-3-opus-20240229 | $15.0000 | $75.0000 | - | - | - |
| claude-haiku-4-5-20251001 | $1.0000 | $5.0000 | - | - | - |
Google Gemini
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Long Context Threshold | Long Context Input Cost (per 1M tokens) | Long Context Output Cost (per 1M tokens) |
|---|---|---|---|---|---|
| gemini-pro | $1.2500 | $3.7500 | - | - | - |
| gemini-2.0-flash-exp | $0.0000 | $0.0000 | - | - | - |
| gemini-2.0-flash-001 | $0.3750 | $1.5000 | - | - | - |
| gemini-3.5-flash, gemini-3.5-flash-high, gemini-3.5-flash-low, gemini-3.5-flash-minimal | $1.5000 | $9.0000 | - | - | - |
| gemini-3.1-pro-preview, gemini-3.1-pro-preview-low, gemini-3.1-pro-preview-customtools, gemini-3-pro-preview, gemini-3-pro-preview-low | $2.0000 | $12.0000 | 200,000 tokens | $4.0000 | $18.0000 |
| gemini-2.5-pro-preview-03-25 | $1.2500 | $10.0000 | 200,000 tokens | $2.5000 | $15.0000 |
| gemini-3-flash-preview, gemini-3-flash-preview-medium, gemini-3-flash-preview-low, gemini-3-flash-preview-minimal | $0.5000 | $3.0000 | - | - | - |
| gemini-3.1-flash-lite, gemini-3.1-flash-lite-medium, gemini-3.1-flash-lite-low, gemini-3.1-flash-lite-minimal | $0.2500 | $1.5000 | - | - | - |
| gemini-2.5-pro, gemini-2.5-pro-thinking | $1.2500 | $10.0000 | 200,000 tokens | $2.5000 | $15.0000 |
| gemini-2.5-computer-use-preview-10-2025 | $1.2500 | $10.0000 | 200,000 tokens | $2.5000 | $15.0000 |
| gemini-2.5-flash-preview-04-17 | $0.3000 | $2.5000 | - | - | - |
| gemini-2.5-flash-preview-09-2025-non-thinking, gemini-2.5-flash-preview-09-2025-thinking | $0.3000 | $2.5000 | - | - | - |
| gemini-2.5-flash, gemini-2.5-flash-non-thinking, gemini-2.5-flash-thinking | $0.3000 | $2.5000 | - | - | - |
| gemini-2.5-flash-lite, gemini-2.5-flash-lite-thinking | $0.1000 | $0.4000 | - | - | - |
| gemini-2.5-flash-lite-preview-09-2025-non-thinking, gemini-2.5-flash-lite-preview-09-2025-thinking | $0.1000 | $0.4000 | - | - | - |
Replicate
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) |
|---|---|---|
| meta/llama-2-70b, meta/llama-2-70b-chat | $0.6500 | $2.7500 |
| meta/llama-2-13b, meta/llama-2-13b-chat | $0.1000 | $0.5000 |
| meta/llama-2-7b, meta/llama-2-7b-chat | $0.0500 | $0.2500 |
| mistralai/mistral-7b-v0.1, mistralai/mistral-7b-instruct-v0.2 | $0.0500 | $0.2500 |
| mistralai/mixtral-8x7b-instruct-v0.1 | $0.3000 | $1.0000 |
Groq
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) |
|---|---|---|
| openai/gpt-oss-20b | $0.1000 | $0.5000 |
| openai/gpt-oss-120b | $0.1500 | $0.7500 |
| moonshotai/kimi-k2-instruct | $1.0000 | $3.0000 |
| meta-llama/llama-4-maverick-17b-128e-instruct | $0.5000 | $0.7700 |
| meta-llama/llama-4-scout-17b-16e-instruct | $0.1100 | $0.3400 |
| deepseek-r1-distill-llama-70b, deepseek-r1-distill-llama-70b-specdec | $8.0000 | $8.0000 |
| llama-3.1-405b-reasoning | $0.5900 | $0.7900 |
| llama-3.3-70b-versatile, llama-3.1-70b-versatile, llama3-groq-70b-8192-tool-use-preview | $0.5900 | $0.7900 |
| llama-3.1-8b-instant, llama3-groq-8b-8192-tool-use-preview | $0.0500 | $0.1000 |
| llama3-70b-8192 | $0.5900 | $0.7900 |
| llama3-8b-8192 | $0.0500 | $0.1000 |
| llama2-70b-4096 | $0.6400 | $0.8000 |
| mixtral-8x7b-32768 | $0.2700 | $0.2700 |
| gemma-7b-it | $0.1000 | $0.1000 |
Perplexity
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) |
|---|---|---|
| sonar | $1.0000 | $1.0000 |
| sonar-pro | $3.0000 | $15.0000 |
| sonar-reasoning | $1.0000 | $5.0000 |
| sonar-deep-research | $2.0000 | $8.0000 |
| llama-3.1-sonar-small-128k-online | $0.2000 | $0.2000 |
| llama-3.1-sonar-large-128k-online | $1.0000 | $1.0000 |
| llama-3.1-sonar-huge-128k-online | $5.0000 | $5.0000 |
xAI
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Long Context Threshold | Long Context Input Cost (per 1M tokens) | Long Context Output Cost (per 1M tokens) |
|---|---|---|---|---|---|
| grok-4.5, grok-4.5-low, grok-4.5-medium, grok-4.5-high | $2.0000 | $6.0000 | 200,000 tokens | $4.0000 | $12.0000 |
| grok-4.3 | $1.2500 | $2.5000 | - | - | - |
| grok-4.20-0309-reasoning | $2.0000 | $6.0000 | - | - | - |
| grok-4.20-0309-non-reasoning | $2.0000 | $6.0000 | - | - | - |
| grok-4.20-multi-agent-0309 | $2.0000 | $6.0000 | - | - | - |
| grok-4-0709 | $3.0000 | $15.0000 | 128,000 tokens | $6.0000 | $30.0000 |
| grok-4-fast-reasoning | $0.2000 | $0.5000 | 128,000 tokens | $0.4000 | $1.0000 |
| grok-4-fast-non-reasoning | $0.2000 | $0.5000 | 128,000 tokens | $0.4000 | $1.0000 |
| grok-4-1-fast-reasoning | $0.2000 | $0.5000 | 128,000 tokens | $0.4000 | $1.0000 |
| grok-4-1-fast-non-reasoning | $0.2000 | $0.5000 | 128,000 tokens | $0.4000 | $1.0000 |
| grok-3, grok-3-latest | $3.0000 | $15.0000 | - | - | - |
| grok-3-fast, grok-3-fast-latest | $5.0000 | $25.0000 | - | - | - |
| grok-3-mini, grok-3-mini-latest | $0.3000 | $0.5000 | - | - | - |
| grok-3-mini-fast, grok-3-mini-fast-latest | $0.6000 | $4.0000 | - | - | - |
| grok-beta | $5.0000 | $15.0000 | - | - | - |
| grok-vision-beta | $5.0000 | $15.0000 | - | - | - |
AWS Bedrock
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Long Context Threshold | Long Context Input Cost (per 1M tokens) | Long Context Output Cost (per 1M tokens) |
|---|---|---|---|---|---|
| anthropic.claude-opus-4-8, anthropic.claude-opus-4-7-v1:0, anthropic.claude-opus-4-6-v1:0 | $5.0000 | $25.0000 | - | - | - |
| anthropic.claude-opus-4-1-20250805-v1:0, anthropic.claude-opus-4-20250514-v1:0 | $15.0000 | $75.0000 | - | - | - |
| anthropic.claude-sonnet-4-6, anthropic.claude-sonnet-4-5-20250929-v1:0, anthropic.claude-sonnet-4-20250514-v1:0, anthropic.claude-3-7-sonnet-20250219-v1:0, anthropic.claude-3-5-sonnet-20240620-v1:0, anthropic.claude-3-5-sonnet-20241022-v2:0, anthropic.claude-3-sonnet-20240229-v1:0 | $3.0000 | $15.0000 | 200,000 tokens | $6.0000 | $22.5000 |
| anthropic.claude-3-5-haiku-20241022-v1:0 | $0.8000 | $4.0000 | - | - | - |
| anthropic.claude-3-haiku-20240307-v1:0 | $0.2500 | $1.2500 | - | - | - |
| anthropic.claude-3-opus-20240229-v1:0 | $15.0000 | $75.0000 | - | - | - |
| openai.gpt-oss-20b-1:0 | $0.0700 | $0.3000 | - | - | - |
| openai.gpt-oss-120b-1:0 | $0.1500 | $0.6000 | - | - | - |
| openai.gpt-5.4 | $2.5000 | $15.0000 | - | - | - |
| openai.gpt-5.5 | $5.0000 | $30.0000 | - | - | - |
Embedding Models
| Model | Cost (per 1M tokens) |
|---|---|
| cohere.embed-english-v3.0, cohere.embed-multilingual-v3.0 | $0.1000 |
| amazon.titan-embed-text-v1, amazon.titan-embed-text-v2:0 | $0.1000 |
Azure
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Long Context Threshold | Long Context Input Cost (per 1M tokens) | Long Context Output Cost (per 1M tokens) |
|---|---|---|---|---|---|
| gpt-4o-mini | $0.1500 | $0.6000 | - | - | - |
| gpt-4o | $5.0000 | $15.0000 | - | - | - |
| gpt-4 | $30.0000 | $60.0000 | - | - | - |
| gpt-35-turbo | $0.5000 | $1.5000 | - | - | - |
| gpt-4.1 | $2.0000 | $8.0000 | - | - | - |
| gpt-4.1-mini | $0.4000 | $1.6000 | - | - | - |
| gpt-4.1-nano | $0.1000 | $0.4000 | - | - | - |
| gpt-5.5, gpt-5.5-none, gpt-5.5-low, gpt-5.5-medium, gpt-5.5-high, gpt-5.5-xhigh | $5.0000 | $30.0000 | - | - | - |
| gpt-5.4, gpt-5.4-none, gpt-5.4-low, gpt-5.4-medium, gpt-5.4-high, gpt-5.4-xhigh | $2.5000 | $15.0000 | 272,000 tokens | $5.0000 | $22.5000 |
| gpt-5.4-mini, gpt-5.4-mini-none, gpt-5.4-mini-low, gpt-5.4-mini-medium, gpt-5.4-mini-high, gpt-5.4-mini-xhigh | $0.7500 | $4.5000 | - | - | - |
| gpt-5.4-nano, gpt-5.4-nano-none, gpt-5.4-nano-low, gpt-5.4-nano-medium, gpt-5.4-nano-high, gpt-5.4-nano-xhigh | $0.2000 | $1.2500 | - | - | - |
Embedding Models
| Model | Cost (per 1M tokens) |
|---|---|
| text-embedding-3-large | $0.1300 |
| text-embedding-3-small | $0.0200 |
Fireworks
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) |
|---|---|---|
| accounts/fireworks/models/minimax-m3, accounts/fireworks/models/minimax-m3-non-thinking, accounts/fireworks/models/minimax-m2p5, accounts/fireworks/models/minimax-m2p7 | $0.3000 | $1.2000 |
| accounts/fireworks/models/deepseek-v3p2 | $1.2000 | $1.2000 |
| accounts/fireworks/models/deepseek-v4-pro | $1.7400 | $3.4800 |
| accounts/fireworks/models/deepseek-v4-flash | $0.1400 | $0.2800 |
| accounts/fireworks/models/glm-5 | $1.0000 | $3.2000 |
| accounts/fireworks/models/kimi-k2-thinking | $0.6000 | $2.5000 |
| accounts/fireworks/models/kimi-k2p5 | $0.6000 | $3.0000 |
| accounts/fireworks/models/kimi-k2p6, accounts/fireworks/models/kimi-k2p7-code | $0.9500 | $4.0000 |
| accounts/fireworks/models/kimi-k3 | $3.0000 | $15.0000 |
| accounts/fireworks/models/gpt-oss-20b | $0.0700 | $0.3000 |
| accounts/fireworks/models/gpt-oss-120b | $0.1500 | $0.6000 |
| accounts/fireworks/models/llama4-maverick-instruct-basic | $0.2200 | $0.8800 |
| accounts/fireworks/models/qwen3-235b-a22b | $0.1000 | $0.1000 |
| accounts/fireworks/models/qwen3p6-plus | $0.5000 | $3.0000 |
| accounts/fireworks/models/qwen3p7-plus | $0.4000 | $1.6000 |
| accounts/fireworks/models/glm-5p1 | $1.4000 | $4.4000 |
| accounts/fireworks/models/glm-5p2 | $1.4000 | $4.4000 |
| accounts/fireworks/models/llama4-scout-instruct-basic | $0.1500 | $0.6000 |
| accounts/fireworks/models/deepseek-r1 | $3.0000 | $8.0000 |
| accounts/fireworks/models/deepseek-v3 | $0.9000 | $0.9000 |
| accounts/fireworks/models/deepseek-v3-0324 | $1.2000 | $1.2000 |
| accounts/fireworks/models/llama-v3p3-70b-instruct | $0.9000 | $0.9000 |
| accounts/fireworks/models/llama-v3p3-70b-instruct | $3.0000 | $3.0000 |
| accounts/fireworks/models/llama-v3p1-70b-instruct | $0.9000 | $0.9000 |
Together AI
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) |
|---|---|---|
| moonshotai/Kimi-K3 | $3.0000 | $15.0000 |
| moonshotai/Kimi-K2.6 | $1.2000 | $4.5000 |
| MiniMaxAI/MiniMax-M2.7, MiniMaxAI/MiniMax-M3 | $0.3000 | $1.2000 |
| deepseek-ai/DeepSeek-V4-Pro | $2.1000 | $4.4000 |
| zai-org/GLM-5.2 | $1.4000 | $4.4000 |
DeepInfra
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) |
|---|---|---|
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | $0.5000 | $2.5000 |
| nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning | $0.2000 | $0.8000 |
| deepseek-ai/DeepSeek-V4-Flash | $0.1000 | $0.2000 |
| deepseek-ai/DeepSeek-V4-Pro | $1.3000 | $2.6000 |
| zai-org/GLM-5.2 | $1.3950 | $4.5000 |
| moonshotai/Kimi-K2.6 | $0.7500 | $3.5000 |
| XiaomiMiMo/MiMo-V2.5 | $0.4000 | $2.0000 |
| XiaomiMiMo/MiMo-V2.5-Pro | $1.0000 | $3.0000 |
| Qwen/Qwen3.6-35B-A3B | $0.1500 | $0.9500 |
Meta
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) |
|---|---|---|
| muse-spark-1.1 | $1.2500 | $4.2500 |
BotDojo
Language Models
| Model | Input Cost (per 1M tokens) | Output Cost (per 1M tokens) | Long Context Threshold | Long Context Input Cost (per 1M tokens) | Long Context Output Cost (per 1M tokens) |
|---|---|---|---|---|---|
| kata-1.1-high | $3.4500 | $17.2500 | - | - | - |
| kata-1.0-fast, kata-1.0-low, kata-1.1-low | $0.3450 | $1.3800 | - | - | - |
| kata-1.0-medium | $1.0930 | $4.6000 | - | - | - |
| kata-1.1-medium | $1.6100 | $5.0600 | - | - | - |
| kata-1.0-high | $3.4500 | $17.2500 | 200,000 tokens | $6.9000 | $25.8750 |
Last Updated: 7/27/2026
tip
For the most up-to-date pricing and model availability, please check the individual provider's pricing pages.