AI model pricing.
See what your tokens cost. Compare input, output and cache prices across AI providers to find the right rate for your next project.
Collected · API list prices
Find your model.
One offer per provider. Every rate stays separate.
Model offers
8,037 matching offers · Showing 1–200
Featured providers first: Anthropic, OpenAI, Google, xAI, DeepSeek and Mistral. Expand a row for its full price breakdown.
Claude Sonnet 5.5Anthropic
Input / 1M$2
Output / 1M$10
Context tokens1,000,000
Model ID: claude-sonnet-5-5
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $10
- Cache read
- $0.2
- Cache write
- $2.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Opus 5.5Anthropic
Input / 1M$4
Output / 1M$20
Context tokens1,000,000
Model ID: claude-opus-5-5
Base prices USD per 1 million tokens
- Input
- $4
- Output
- $20
- Cache read
- $0.2
- Cache write
- $5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $8
- Output
- $40
- Cache read
- $0.4
- Cache write
- $10
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Fable 5.1Anthropic
Input / 1M$10
Output / 1M$50
Context tokens1,000,000
Model ID: claude-fable-5-1
Base prices USD per 1 million tokens
- Input
- $10
- Output
- $50
- Cache read
- $0.25
- Cache write
- $12.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Opus 5Anthropic
Input / 1M$5
Output / 1M$25
Context tokens1,000,000
Model ID: claude-opus-5
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $25
- Cache read
- $0.5
- Cache write
- $6.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $10
- Output
- $50
- Cache read
- $1
- Cache write
- $12.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Sonnet 5Anthropic
Input / 1M$2
Output / 1M$10
Context tokens1,000,000
Model ID: claude-sonnet-5
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $10
- Cache read
- $0.2
- Cache write
- $2.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Fable 5Anthropic
Input / 1M$10
Output / 1M$50
Context tokens1,000,000
Model ID: claude-fable-5
Base prices USD per 1 million tokens
- Input
- $10
- Output
- $50
- Cache read
- $1
- Cache write
- $12.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Opus 4.8Anthropic
Input / 1M$5
Output / 1M$25
Context tokens1,000,000
Model ID: claude-opus-4-8
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $25
- Cache read
- $0.5
- Cache write
- $6.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $10
- Output
- $50
- Cache read
- $1
- Cache write
- $12.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Opus 4.7Anthropic
Input / 1M$5
Output / 1M$25
Context tokens1,000,000
Model ID: claude-opus-4-7
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $25
- Cache read
- $0.5
- Cache write
- $6.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Sonnet 4.6Anthropic
Input / 1M$3
Output / 1M$15
Context tokens1,000,000
Model ID: claude-sonnet-4-6
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $15
- Cache read
- $0.3
- Cache write
- $3.75
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Opus 4.6Anthropic
Input / 1M$5
Output / 1M$25
Context tokens1,000,000
Model ID: claude-opus-4-6
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $25
- Cache read
- $0.5
- Cache write
- $6.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Claude Opus 4.5Anthropic
Input / 1M$5
Output / 1M$25
Context tokens200,000
Model ID: claude-opus-4-5-20251101
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $25
- Cache read
- $0.5
- Cache write
- $6.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Claude Opus 4.5 (latest)Anthropic
Input / 1M$5
Output / 1M$25
Context tokens200,000
Model ID: claude-opus-4-5
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $25
- Cache read
- $0.5
- Cache write
- $6.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Claude Haiku 4.5Anthropic
Input / 1M$1
Output / 1M$5
Context tokens200,000
Model ID: claude-haiku-4-5-20251001
Base prices USD per 1 million tokens
- Input
- $1
- Output
- $5
- Cache read
- $0.1
- Cache write
- $1.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Claude Haiku 4.5 (latest)Anthropic
Input / 1M$1
Output / 1M$5
Context tokens200,000
Model ID: claude-haiku-4-5
Base prices USD per 1 million tokens
- Input
- $1
- Output
- $5
- Cache read
- $0.1
- Cache write
- $1.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Claude Sonnet 4.5Anthropic
Input / 1M$3
Output / 1M$15
Context tokens1,000,000
Model ID: claude-sonnet-4-5-20250929
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $15
- Cache read
- $0.3
- Cache write
- $3.75
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Claude Sonnet 4.5 (latest)Anthropic
Input / 1M$3
Output / 1M$15
Context tokens1,000,000
Model ID: claude-sonnet-4-5
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $15
- Cache read
- $0.3
- Cache write
- $3.75
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
GPT-6 LunaOpenAI · Tiered pricing
Input / 1M$0.1
Output / 1M$0.5
Context tokens1,050,000
Model ID: gpt-6-luna
Base prices USD per 1 million tokens
- Input
- $0.1
- Output
- $0.5
- Cache read
- $0.01
- Cache write
- $0.125
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $0.2
- Output
- $0.75
- Cache read
- $0.02
- Cache write
- $0.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $0.2
- Output
- $1
- Cache read
- $0.02
- Cache write
- $0.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-6 SolOpenAI · Tiered pricing
Input / 1M$2
Output / 1M$10
Context tokens1,050,000
Model ID: gpt-6-sol
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $10
- Cache read
- $0.2
- Cache write
- $2.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $4
- Output
- $15
- Cache read
- $0.4
- Cache write
- $5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $4
- Output
- $20
- Cache read
- $0.4
- Cache write
- $5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-6 AstraOpenAI · Tiered pricing
Input / 1M$10
Output / 1M$50
Context tokens1,050,000
Model ID: gpt-6-astra
Base prices USD per 1 million tokens
- Input
- $10
- Output
- $50
- Cache read
- $1
- Cache write
- $12.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $20
- Output
- $75
- Cache read
- $2
- Cache write
- $25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $20
- Output
- $100
- Cache read
- $2
- Cache write
- $25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Daybreak BlueOpenAI · Tiered pricing
Input / 1M$4
Output / 1M$20
Context tokens1,050,000
Model ID: gpt-daybreak-blue-latest
Base prices USD per 1 million tokens
- Input
- $4
- Output
- $20
- Cache read
- $0.4
- Cache write
- $5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $8
- Output
- $30
- Cache read
- $0.8
- Cache write
- $10
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Daybreak RedOpenAI
Input / 1M$12.5
Output / 1M$75
Context tokens400,000
Model ID: gpt-daybreak-red-latest
Base prices USD per 1 million tokens
- Input
- $12.5
- Output
- $75
- Cache read
- $1.25
- Cache write
- $15.625
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
GPT-5.6OpenAI · Tiered pricing
Input / 1M$4
Output / 1M$20
Context tokens1,050,000
Model ID: gpt-5.6
Base prices USD per 1 million tokens
- Input
- $4
- Output
- $20
- Cache read
- $0.4
- Cache write
- $5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $8
- Output
- $30
- Cache read
- $0.8
- Cache write
- $10
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $8
- Output
- $40
- Cache read
- $0.8
- Cache write
- $10
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-5.6 LunaOpenAI · Tiered pricing
Input / 1M$0.2
Output / 1M$1.2
Context tokens1,050,000
Model ID: gpt-5.6-luna
Base prices USD per 1 million tokens
- Input
- $0.2
- Output
- $1.2
- Cache read
- $0.02
- Cache write
- $0.25
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $0.4
- Output
- $1.8
- Cache read
- $0.04
- Cache write
- $0.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $0.4
- Output
- $2.4
- Cache read
- $0.04
- Cache write
- $0.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-5.6 SolOpenAI · Tiered pricing
Input / 1M$4
Output / 1M$20
Context tokens1,050,000
Model ID: gpt-5.6-sol
Base prices USD per 1 million tokens
- Input
- $4
- Output
- $20
- Cache read
- $0.4
- Cache write
- $5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $8
- Output
- $30
- Cache read
- $0.8
- Cache write
- $10
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $8
- Output
- $40
- Cache read
- $0.8
- Cache write
- $10
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-5.6 TerraOpenAI · Tiered pricing
Input / 1M$2
Output / 1M$12
Context tokens1,050,000
Model ID: gpt-5.6-terra
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $12
- Cache read
- $0.2
- Cache write
- $2.5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $4
- Output
- $18
- Cache read
- $0.4
- Cache write
- $5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $4
- Output
- $24
- Cache read
- $0.4
- Cache write
- $5
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-Realtime-2.1OpenAI
Input / 1M$4
Output / 1M$24
Context tokens128,000
Model ID: gpt-realtime-2.1
Base prices USD per 1 million tokens
- Input
- $4
- Output
- $24
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $32
- Audio output
- $64
Input: text, audio, image
Output: text, audio
Maximum output: 32,000 tokens
GPT-5.5OpenAI · Tiered pricing
Input / 1M$5
Output / 1M$30
Context tokens1,050,000
Model ID: gpt-5.5
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $30
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $10
- Output
- $45
- Cache read
- $1
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $12.5
- Output
- $75
- Cache read
- $1.25
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-5.5 ProOpenAI · Tiered pricing
Input / 1M$30
Output / 1M$180
Context tokens1,050,000
Model ID: gpt-5.5-pro
Base prices USD per 1 million tokens
- Input
- $30
- Output
- $180
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $60
- Output
- $270
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
gpt-image-2OpenAI
Input / 1M$5
Output / 1M$30
Context tokens0
Model ID: gpt-image-2
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $30
- Cache read
- $1.25
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: image
Maximum output: 0 tokens
GPT-5.4 miniOpenAI
Input / 1M$0.75
Output / 1M$4.5
Context tokens400,000
Model ID: gpt-5.4-mini
Base prices USD per 1 million tokens
- Input
- $0.75
- Output
- $4.5
- Cache read
- $0.075
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $1.5
- Output
- $9
- Cache read
- $0.15
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
GPT-5.4 nanoOpenAI
Input / 1M$0.2
Output / 1M$1.25
Context tokens400,000
Model ID: gpt-5.4-nano
Base prices USD per 1 million tokens
- Input
- $0.2
- Output
- $1.25
- Cache read
- $0.02
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
GPT-5.4OpenAI · Tiered pricing
Input / 1M$2.5
Output / 1M$15
Context tokens1,050,000
Model ID: gpt-5.4
Base prices USD per 1 million tokens
- Input
- $2.5
- Output
- $15
- Cache read
- $0.25
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $5
- Output
- $22.5
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
fast mode · Experimental
- Input
- $5
- Output
- $30
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-5.4 ProOpenAI · Tiered pricing
Input / 1M$30
Output / 1M$180
Context tokens1,050,000
Model ID: gpt-5.4-pro
Base prices USD per 1 million tokens
- Input
- $30
- Output
- $180
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 272,000 context tokens
- Input
- $60
- Output
- $270
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
GPT-5.3 CodexOpenAI
Input / 1M$1.75
Output / 1M$14
Context tokens400,000
Model ID: gpt-5.3-codex
Base prices USD per 1 million tokens
- Input
- $1.75
- Output
- $14
- Cache read
- $0.175
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
GPT-5.3 Codex SparkOpenAI
Input / 1M$1.75
Output / 1M$14
Context tokens128,000
Model ID: gpt-5.3-codex-spark
Base prices USD per 1 million tokens
- Input
- $1.75
- Output
- $14
- Cache read
- $0.175
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 32,000 tokens
chatgpt-image-latestOpenAI
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens0
Model ID: chatgpt-image-latest
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image
Output: text, image
Maximum output: 0 tokens
GPT-5.2OpenAI
Input / 1M$1.75
Output / 1M$14
Context tokens400,000
Model ID: gpt-5.2
Base prices USD per 1 million tokens
- Input
- $1.75
- Output
- $14
- Cache read
- $0.175
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
GPT-5.2 ProOpenAI
Input / 1M$21
Output / 1M$168
Context tokens400,000
Model ID: gpt-5.2-pro
Base prices USD per 1 million tokens
- Input
- $21
- Output
- $168
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
gpt-image-1.5OpenAI
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens0
Model ID: gpt-image-1.5
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image
Output: text, image
Maximum output: 0 tokens
GPT-5.1OpenAI
Input / 1M$1.25
Output / 1M$10
Context tokens400,000
Model ID: gpt-5.1
Base prices USD per 1 million tokens
- Input
- $1.25
- Output
- $10
- Cache read
- $0.125
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
GPT-5 ProOpenAI
Input / 1M$15
Output / 1M$120
Context tokens400,000
Model ID: gpt-5-pro
Base prices USD per 1 million tokens
- Input
- $15
- Output
- $120
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 272,000 tokens
gpt-image-1-miniOpenAI
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens0
Model ID: gpt-image-1-mini
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image
Output: text, image
Maximum output: 0 tokens
GPT-5OpenAI
Input / 1M$1.25
Output / 1M$10
Context tokens400,000
Model ID: gpt-5
Base prices USD per 1 million tokens
- Input
- $1.25
- Output
- $10
- Cache read
- $0.125
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
GPT-5 MiniOpenAI
Input / 1M$0.25
Output / 1M$2
Context tokens400,000
Model ID: gpt-5-mini
Base prices USD per 1 million tokens
- Input
- $0.25
- Output
- $2
- Cache read
- $0.025
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
GPT-5 NanoOpenAI
Input / 1M$0.05
Output / 1M$0.4
Context tokens400,000
Model ID: gpt-5-nano
Base prices USD per 1 million tokens
- Input
- $0.05
- Output
- $0.4
- Cache read
- $0.005
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
o3-proOpenAI
Input / 1M$20
Output / 1M$80
Context tokens200,000
Model ID: o3-pro
Base prices USD per 1 million tokens
- Input
- $20
- Output
- $80
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 100,000 tokens
o3OpenAI
Input / 1M$2
Output / 1M$8
Context tokens200,000
Model ID: o3
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $8
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 100,000 tokens
GPT-4.1OpenAI
Input / 1M$2
Output / 1M$8
Context tokens1,047,576
Model ID: gpt-4.1
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $8
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 32,768 tokens
GPT-4.1 miniOpenAI
Input / 1M$0.4
Output / 1M$1.6
Context tokens1,047,576
Model ID: gpt-4.1-mini
Base prices USD per 1 million tokens
- Input
- $0.4
- Output
- $1.6
- Cache read
- $0.1
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 32,768 tokens
GPT-4o (2024-11-20)OpenAI
Input / 1M$2.5
Output / 1M$10
Context tokens128,000
Model ID: gpt-4o-2024-11-20
Base prices USD per 1 million tokens
- Input
- $2.5
- Output
- $10
- Cache read
- $1.25
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 16,384 tokens
GPT-4o (2024-08-06)OpenAI
Input / 1M$2.5
Output / 1M$10
Context tokens128,000
Model ID: gpt-4o-2024-08-06
Base prices USD per 1 million tokens
- Input
- $2.5
- Output
- $10
- Cache read
- $1.25
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 16,384 tokens
GPT-4o miniOpenAI
Input / 1M$0.15
Output / 1M$0.6
Context tokens128,000
Model ID: gpt-4o-mini
Base prices USD per 1 million tokens
- Input
- $0.15
- Output
- $0.6
- Cache read
- $0.075
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 16,384 tokens
GPT-4oOpenAI
Input / 1M$2.5
Output / 1M$10
Context tokens128,000
Model ID: gpt-4o
Base prices USD per 1 million tokens
- Input
- $2.5
- Output
- $10
- Cache read
- $1.25
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 16,384 tokens
text-embedding-3-largeOpenAI
Input / 1M$0.13
Output / 1MFree (as declared)
Context tokens8,191
Model ID: text-embedding-3-large
Base prices USD per 1 million tokens
- Input
- $0.13
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 3,072 tokens
text-embedding-3-smallOpenAI
Input / 1M$0.02
Output / 1MFree (as declared)
Context tokens8,191
Model ID: text-embedding-3-small
Base prices USD per 1 million tokens
- Input
- $0.02
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 1,536 tokens
text-embedding-ada-002OpenAI
Input / 1M$0.1
Output / 1MFree (as declared)
Context tokens8,192
Model ID: text-embedding-ada-002
Base prices USD per 1 million tokens
- Input
- $0.1
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 1,536 tokens
Gemini 3.8 FlashGoogle
Input / 1M$0.75
Output / 1M$3.75
Context tokens1,048,576
Model ID: gemini-3.8-flash
Base prices USD per 1 million tokens
- Input
- $0.75
- Output
- $3.75
- Cache read
- $0.075
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $0.75
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini 3.7 FlashGoogle
Input / 1M$0.75
Output / 1M$3.75
Context tokens1,048,576
Model ID: gemini-3.7-flash
Base prices USD per 1 million tokens
- Input
- $0.75
- Output
- $3.75
- Cache read
- $0.075
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $0.75
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini Flash LatestGoogle
Input / 1M$0.75
Output / 1M$3.75
Context tokens1,048,576
Model ID: gemini-flash-latest
Base prices USD per 1 million tokens
- Input
- $0.75
- Output
- $3.75
- Cache read
- $0.075
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $0.75
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini 3.5 Flash LiteGoogle
Input / 1M$0.3
Output / 1M$2.5
Context tokens1,048,576
Model ID: gemini-3.5-flash-lite
Base prices USD per 1 million tokens
- Input
- $0.3
- Output
- $2.5
- Cache read
- $0.03
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini 3.6 FlashGoogle
Input / 1M$0.75
Output / 1M$3.75
Context tokens1,048,576
Model ID: gemini-3.6-flash
Base prices USD per 1 million tokens
- Input
- $0.75
- Output
- $3.75
- Cache read
- $0.075
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $0.75
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini Flash-Lite LatestGoogle
Input / 1M$0.3
Output / 1M$2.5
Context tokens1,048,576
Model ID: gemini-flash-lite-latest
Base prices USD per 1 million tokens
- Input
- $0.3
- Output
- $2.5
- Cache read
- $0.03
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini Omni Flash PreviewGoogle
Input / 1M$1.5
Output / 1M$17.5
Context tokens131,072
Model ID: gemini-omni-flash-preview
Base prices USD per 1 million tokens
- Input
- $1.5
- Output
- $17.5
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, video
Output: video
Maximum output: 65,536 tokens
Nano Banana 2 LiteGoogle
Input / 1M$0.25
Output / 1M$30
Context tokens65,536
Model ID: gemini-3.1-flash-lite-image
Base prices USD per 1 million tokens
- Input
- $0.25
- Output
- $30
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text, image
Maximum output: 4,096 tokens
Gemini 3.5 Live Translate PreviewGoogle
Input / 1M$3.5
Output / 1M$21
Context tokens16,384
Model ID: gemini-3.5-live-translate-preview
Base prices USD per 1 million tokens
- Input
- $3.5
- Output
- $21
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $3.5
- Audio output
- $21
Input: audio
Output: audio, text
Maximum output: 32,768 tokens
Nano Banana 2Google
Input / 1M$0.5
Output / 1M$60
Context tokens131,072
Model ID: gemini-3.1-flash-image
Base prices USD per 1 million tokens
- Input
- $0.5
- Output
- $60
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, video, pdf
Output: text, image
Maximum output: 32,768 tokens
Nano Banana ProGoogle
Input / 1M$2
Output / 1M$120
Context tokens65,536
Model ID: gemini-3-pro-image
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $120
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text, image
Maximum output: 32,768 tokens
Gemini 3.5 FlashGoogle
Input / 1M$1.5
Output / 1M$9
Context tokens1,048,576
Model ID: gemini-3.5-flash
Base prices USD per 1 million tokens
- Input
- $1.5
- Output
- $9
- Cache read
- $0.15
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $1.5
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini 3.1 Flash LiteGoogle
Input / 1M$0.25
Output / 1M$1.5
Context tokens1,048,576
Model ID: gemini-3.1-flash-lite
Base prices USD per 1 million tokens
- Input
- $0.25
- Output
- $1.5
- Cache read
- $0.025
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $0.5
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini Embedding 2Google
Input / 1M$0.2
Output / 1MFree (as declared)
Context tokens8,192
Model ID: gemini-embedding-2
Base prices USD per 1 million tokens
- Input
- $0.2
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $6.5
- Audio output
- Not listed
Input: text, image, audio, video, pdf
Output: text
Maximum output: 1 tokens
Deep Research Max Preview (Apr-21-2026)Google · Tiered pricing
Input / 1M$2
Output / 1M$12
Context tokens131,072
Model ID: deep-research-max-preview-04-2026
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $12
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $4
- Output
- $18
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text, image
Maximum output: 65,536 tokens
Deep Research Preview (Apr-21-2026)Google · Tiered pricing
Input / 1M$2
Output / 1M$12
Context tokens131,072
Model ID: deep-research-preview-04-2026
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $12
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $4
- Output
- $18
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text, image
Maximum output: 65,536 tokens
Gemini 3.1 Flash TTS PreviewGoogle
Input / 1M$1
Output / 1M$20
Context tokens8,192
Model ID: gemini-3.1-flash-tts-preview
Base prices USD per 1 million tokens
- Input
- $1
- Output
- $20
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: audio
Maximum output: 16,384 tokens
Gemma 4 26B A4B ITGoogle
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens262,144
Model ID: gemma-4-26b-a4b-it
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image
Output: text
Maximum output: 32,768 tokens
Gemma 4 31B ITGoogle
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens262,144
Model ID: gemma-4-31b-it
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image
Output: text
Maximum output: 32,768 tokens
Veo 3.1 liteGoogle
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens480
Model ID: veo-3.1-lite-generate-preview
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image
Output: video
Maximum output: 8,192 tokens
Gemini 3.1 Flash Live PreviewGoogle
Input / 1M$0.75
Output / 1M$4.5
Context tokens131,072
Model ID: gemini-3.1-flash-live-preview
Base prices USD per 1 million tokens
- Input
- $0.75
- Output
- $4.5
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $3
- Audio output
- $12
Input: text, image, video, audio
Output: text, audio
Maximum output: 65,536 tokens
Lyria 3 Clip PreviewGoogle
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,048,576
Model ID: lyria-3-clip-preview
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text, audio
Maximum output: 65,536 tokens
Lyria 3 Pro PreviewGoogle
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,048,576
Model ID: lyria-3-pro-preview
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text, audio
Maximum output: 65,536 tokens
Nano Banana 2Google
Input / 1M$0.5
Output / 1M$60
Context tokens65,536
Model ID: gemini-3.1-flash-image-preview
Base prices USD per 1 million tokens
- Input
- $0.5
- Output
- $60
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text, image
Maximum output: 65,536 tokens
Gemini 3.1 Pro PreviewGoogle · Tiered pricing
Input / 1M$2
Output / 1M$12
Context tokens1,048,576
Model ID: gemini-3.1-pro-preview
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $12
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $4
- Output
- $18
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini 3.1 Pro Preview Custom ToolsGoogle · Tiered pricing
Input / 1M$2
Output / 1M$12
Context tokens1,048,576
Model ID: gemini-3.1-pro-preview-customtools
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $12
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $4
- Output
- $18
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Gemini 3 Flash PreviewGoogle
Input / 1M$0.5
Output / 1M$3
Context tokens1,048,576
Model ID: gemini-3-flash-preview
Base prices USD per 1 million tokens
- Input
- $0.5
- Output
- $3
- Cache read
- $0.05
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $1
- Audio output
- Not listed
Input: text, image, video, audio, pdf
Output: text
Maximum output: 65,536 tokens
Nano Banana ProGoogle
Input / 1M$2
Output / 1M$120
Context tokens131,072
Model ID: gemini-3-pro-image-preview
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $120
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text, image
Maximum output: 32,768 tokens
Veo 3.1Google · beta
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens480
Model ID: veo-3.1-generate-preview
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image
Output: video
Maximum output: 8,192 tokens
Veo 3.1 fastGoogle
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens480
Model ID: veo-3.1-fast-generate-preview
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image, video
Output: video
Maximum output: 8,192 tokens
Gemini 2.5 Computer Use Preview 10-2025Google · Tiered pricing
Input / 1M$1.25
Output / 1M$10
Context tokens128,000
Model ID: gemini-2.5-computer-use-preview-10-2025
Base prices USD per 1 million tokens
- Input
- $1.25
- Output
- $10
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $2.5
- Output
- $15
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 64,000 tokens
Nano BananaGoogle
Input / 1M$0.3
Output / 1M$30
Context tokens32,768
Model ID: gemini-2.5-flash-image
Base prices USD per 1 million tokens
- Input
- $0.3
- Output
- $30
- Cache read
- $0.075
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text, image
Maximum output: 32,768 tokens
Gemini 2.5 FlashGoogle
Input / 1M$0.3
Output / 1M$2.5
Context tokens1,048,576
Model ID: gemini-2.5-flash
Base prices USD per 1 million tokens
- Input
- $0.3
- Output
- $2.5
- Cache read
- $0.03
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $1
- Audio output
- Not listed
Input: text, image, audio, video, pdf
Output: text
Maximum output: 65,536 tokens
Gemini 2.5 Flash-LiteGoogle
Input / 1M$0.1
Output / 1M$0.4
Context tokens1,048,576
Model ID: gemini-2.5-flash-lite
Base prices USD per 1 million tokens
- Input
- $0.1
- Output
- $0.4
- Cache read
- $0.01
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- $0.3
- Audio output
- Not listed
Input: text, image, audio, video, pdf
Output: text
Maximum output: 65,536 tokens
Gemini 2.5 ProGoogle · Tiered pricing
Input / 1M$1.25
Output / 1M$10
Context tokens1,048,576
Model ID: gemini-2.5-pro
Base prices USD per 1 million tokens
- Input
- $1.25
- Output
- $10
- Cache read
- $0.125
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $2.5
- Output
- $15
- Cache read
- $0.25
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, audio, video, pdf
Output: text
Maximum output: 65,536 tokens
Gemini Embedding 001Google
Input / 1M$0.15
Output / 1MFree (as declared)
Context tokens2,048
Model ID: gemini-embedding-001
Base prices USD per 1 million tokens
- Input
- $0.15
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 1 tokens
Gemini 2.5 Flash Preview TTSGoogle
Input / 1M$0.5
Output / 1M$10
Context tokens8,192
Model ID: gemini-2.5-flash-preview-tts
Base prices USD per 1 million tokens
- Input
- $0.5
- Output
- $10
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: audio
Maximum output: 16,384 tokens
Gemini 2.5 Pro Preview TTSGoogle
Input / 1M$1
Output / 1M$20
Context tokens8,192
Model ID: gemini-2.5-pro-preview-tts
Base prices USD per 1 million tokens
- Input
- $1
- Output
- $20
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: audio
Maximum output: 16,384 tokens
Grok 4.7xAI · Tiered pricing
Input / 1M$2
Output / 1M$6
Context tokens500,000
Model ID: grok-4.7
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $6
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $4
- Output
- $12
- Cache read
- $1
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 500,000 tokens
Grok 4.6xAI · Tiered pricing
Input / 1M$2
Output / 1M$6
Context tokens500,000
Model ID: grok-4.6
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $6
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $4
- Output
- $12
- Cache read
- $1
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 500,000 tokens
Grok 4.5xAI · Tiered pricing
Input / 1M$2
Output / 1M$6
Context tokens500,000
Model ID: grok-4.5
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $6
- Cache read
- $0.3
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $4
- Output
- $12
- Cache read
- $0.6
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 500,000 tokens
Grok Imagine Video 1.5xAI
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens1,024
Model ID: grok-imagine-video-1.5
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image, audio, pdf
Output: video
Maximum output: 0 tokens
Grok 4.3xAI · Tiered pricing
Input / 1M$1.25
Output / 1M$2.5
Context tokens1,000,000
Model ID: grok-4.3
Base prices USD per 1 million tokens
- Input
- $1.25
- Output
- $2.5
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $2.5
- Output
- $5
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 30,000 tokens
Grok Build 0.1xAI · Tiered pricing
Input / 1M$1
Output / 1M$2
Context tokens256,000
Model ID: grok-build-0.1
Base prices USD per 1 million tokens
- Input
- $1
- Output
- $2
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $2
- Output
- $4
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 256,000 tokens
Grok Imagine Image QualityxAI
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens16,000
Model ID: grok-imagine-image-quality
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image, pdf
Output: image, pdf
Maximum output: 0 tokens
Grok 4.20 (Non-Reasoning)xAI · Tiered pricing
Input / 1M$1.25
Output / 1M$2.5
Context tokens1,000,000
Model ID: grok-4.20-0309-non-reasoning
Base prices USD per 1 million tokens
- Input
- $1.25
- Output
- $2.5
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $2.5
- Output
- $5
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 30,000 tokens
Grok 4.20 (Reasoning)xAI · Tiered pricing
Input / 1M$1.25
Output / 1M$2.5
Context tokens1,000,000
Model ID: grok-4.20-0309-reasoning
Base prices USD per 1 million tokens
- Input
- $1.25
- Output
- $2.5
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $2.5
- Output
- $5
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 30,000 tokens
Grok 4.20 Multi-AgentxAI · Tiered pricing
Input / 1M$1.25
Output / 1M$2.5
Context tokens1,000,000
Model ID: grok-4.20-multi-agent-0309
Base prices USD per 1 million tokens
- Input
- $1.25
- Output
- $2.5
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Above 200,000 context tokens
- Input
- $2.5
- Output
- $5
- Cache read
- $0.4
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 30,000 tokens
Grok Imagine ImagexAI
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens16,000
Model ID: grok-imagine-image
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image, pdf
Output: image, pdf
Maximum output: 0 tokens
Grok Imagine VideoxAI
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens1,024
Model ID: grok-imagine-video
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image, video, pdf
Output: video
Maximum output: 0 tokens
DeepSeek V4.1 FlashDeepSeek
Input / 1M$0.15
Output / 1M$0.6
Context tokens1,000,000
Model ID: deepseek-flash
Base prices USD per 1 million tokens
- Input
- $0.15
- Output
- $0.6
- Cache read
- $0.003
- Cache write
- Not listed
- Reasoning
- $0.6
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 393,216 tokens
DeepSeek V4 ProDeepSeek
Input / 1M$0.435
Output / 1M$0.87
Context tokens1,000,000
Model ID: deepseek-v4-pro
Base prices USD per 1 million tokens
- Input
- $0.435
- Output
- $0.87
- Cache read
- $0.003625
- Cache write
- Not listed
- Reasoning
- $0.87
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 393,216 tokens
GLM-5.3Mistral
Input / 1M$1.4
Output / 1M$4.4
Context tokens1,000,000
Model ID: zai-glm-5-3
Base prices USD per 1 million tokens
- Input
- $1.4
- Output
- $4.4
- Cache read
- $0.14
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 131,072 tokens
GLM-5.2Mistral · beta
Input / 1M$1.4
Output / 1M$4.4
Context tokens1,000,000
Model ID: zai-glm-5-2
Base prices USD per 1 million tokens
- Input
- $1.4
- Output
- $4.4
- Cache read
- $0.14
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 131,072 tokens
Mistral Medium (latest)Mistral
Input / 1M$1.5
Output / 1M$7.5
Context tokens262,144
Model ID: mistral-medium-latest
Base prices USD per 1 million tokens
- Input
- $1.5
- Output
- $7.5
- Cache read
- $0.15
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 262,144 tokens
Mistral Medium 3.5Mistral
Input / 1M$1.5
Output / 1M$7.5
Context tokens262,144
Model ID: mistral-medium-2604
Base prices USD per 1 million tokens
- Input
- $1.5
- Output
- $7.5
- Cache read
- $0.15
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 262,144 tokens
Mistral Small (latest)Mistral
Input / 1M$0.15
Output / 1M$0.6
Context tokens256,000
Model ID: mistral-small-latest
Base prices USD per 1 million tokens
- Input
- $0.15
- Output
- $0.6
- Cache read
- $0.015
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 256,000 tokens
Mistral Small 4Mistral
Input / 1M$0.15
Output / 1M$0.6
Context tokens256,000
Model ID: mistral-small-2603
Base prices USD per 1 million tokens
- Input
- $0.15
- Output
- $0.6
- Cache read
- $0.015
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 256,000 tokens
Voxtral Mini TTS (latest)Mistral
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens0
Model ID: voxtral-mini-tts-latest
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text
Output: audio
Maximum output: 0 tokens
Voxtral Mini (latest)Mistral
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens0
Model ID: voxtral-mini-latest
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: audio
Output: text
Maximum output: 0 tokens
Mistral Medium 3.1Mistral
Input / 1M$0.4
Output / 1M$2
Context tokens262,144
Model ID: mistral-medium-2508
Base prices USD per 1 million tokens
- Input
- $0.4
- Output
- $2
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 262,144 tokens
Voxtral Small (latest)Mistral
Input / 1M$0.1
Output / 1M$0.3
Context tokens32,000
Model ID: voxtral-small-latest
Base prices USD per 1 million tokens
- Input
- $0.1
- Output
- $0.3
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, audio
Output: text
Maximum output: 32,000 tokens
Mistral Small 3.2Mistral
Input / 1M$0.1
Output / 1M$0.3
Context tokens128,000
Model ID: mistral-small-2506
Base prices USD per 1 million tokens
- Input
- $0.1
- Output
- $0.3
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 16,384 tokens
Mistral Medium 3Mistral
Input / 1M$0.4
Output / 1M$2
Context tokens131,072
Model ID: mistral-medium-2505
Base prices USD per 1 million tokens
- Input
- $0.4
- Output
- $2
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 131,072 tokens
Magistral Medium (latest)Mistral
Input / 1M$2
Output / 1M$5
Context tokens128,000
Model ID: magistral-medium-latest
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $5
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 16,384 tokens
Mistral Large 2.1Mistral
Input / 1M$2
Output / 1M$6
Context tokens131,072
Model ID: mistral-large-2411
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $6
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 16,384 tokens
Mistral Large (latest)Mistral
Input / 1M$0.5
Output / 1M$1.5
Context tokens262,144
Model ID: mistral-large-latest
Base prices USD per 1 million tokens
- Input
- $0.5
- Output
- $1.5
- Cache read
- $0.05
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 262,144 tokens
Mistral Large 3Mistral
Input / 1M$0.5
Output / 1M$1.5
Context tokens262,144
Model ID: mistral-large-2512
Base prices USD per 1 million tokens
- Input
- $0.5
- Output
- $1.5
- Cache read
- $0.05
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 262,144 tokens
Pixtral Large (latest)Mistral
Input / 1M$2
Output / 1M$6
Context tokens128,000
Model ID: pixtral-large-latest
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $6
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
Ministral 3B (latest)Mistral
Input / 1M$0.04
Output / 1M$0.04
Context tokens128,000
Model ID: ministral-3b-latest
Base prices USD per 1 million tokens
- Input
- $0.04
- Output
- $0.04
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 128,000 tokens
Ministral 8B (latest)Mistral
Input / 1M$0.1
Output / 1M$0.1
Context tokens128,000
Model ID: ministral-8b-latest
Base prices USD per 1 million tokens
- Input
- $0.1
- Output
- $0.1
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 128,000 tokens
Pixtral 12BMistral
Input / 1M$0.15
Output / 1M$0.15
Context tokens128,000
Model ID: pixtral-12b
Base prices USD per 1 million tokens
- Input
- $0.15
- Output
- $0.15
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
Mistral NemoMistral
Input / 1M$0.15
Output / 1M$0.15
Context tokens128,000
Model ID: mistral-nemo
Base prices USD per 1 million tokens
- Input
- $0.15
- Output
- $0.15
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 128,000 tokens
Codestral (latest)Mistral
Input / 1M$0.3
Output / 1M$0.9
Context tokens256,000
Model ID: codestral-latest
Base prices USD per 1 million tokens
- Input
- $0.3
- Output
- $0.9
- Cache read
- $0.03
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 4,096 tokens
Mixtral 8x22BMistral
Input / 1M$2
Output / 1M$6
Context tokens64,000
Model ID: open-mixtral-8x22b
Base prices USD per 1 million tokens
- Input
- $2
- Output
- $6
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 64,000 tokens
Mistral EmbedMistral
Input / 1M$0.1
Output / 1MFree (as declared)
Context tokens8,000
Model ID: mistral-embed
Base prices USD per 1 million tokens
- Input
- $0.1
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 3,072 tokens
Mixtral 8x7BMistral
Input / 1M$0.7
Output / 1M$0.7
Context tokens32,000
Model ID: open-mixtral-8x7b
Base prices USD per 1 million tokens
- Input
- $0.7
- Output
- $0.7
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,000 tokens
Mistral 7BMistral
Input / 1M$0.25
Output / 1M$0.25
Context tokens8,000
Model ID: open-mistral-7b
Base prices USD per 1 million tokens
- Input
- $0.25
- Output
- $0.25
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 8,000 tokens
Abliterated Modelabliteration.ai
Input / 1M$3
Output / 1M$3
Context tokens150,000
Model ID: abliterated-model
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $3
- Cache read
- $0.3
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 8,192 tokens
Abliterated ModelNanoGPT
Input / 1M$1
Output / 1M$3
Context tokens262,144
Model ID: abliteration-ai/abliterated-model
Base prices USD per 1 million tokens
- Input
- $1
- Output
- $3
- Cache read
- $0.1
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 262,134 tokens
Abliterated Model Largeabliteration.ai
Input / 1M$5
Output / 1M$5
Context tokens1,000,000
Model ID: abliterated-model-large
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $5
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 999,990 tokens
Abliterated Model LargeNanoGPT
Input / 1M$3
Output / 1M$5
Context tokens1,000,000
Model ID: abliteration-ai/abliterated-model-large
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $5
- Cache read
- $0.3
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 999,990 tokens
Abliterated Model Large V2abliteration.ai
Input / 1M$5
Output / 1M$5
Context tokens1,000,000
Model ID: abliterated-model-large-v2
Base prices USD per 1 million tokens
- Input
- $5
- Output
- $5
- Cache read
- $0.5
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 999,990 tokens
Abliterated Model Large V2NanoGPT
Input / 1M$3
Output / 1M$5
Context tokens1,000,000
Model ID: abliteration-ai/abliterated-model-large-v2
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $5
- Cache read
- $0.3
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 999,990 tokens
Active Speaker DetectionNvidia
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens0
Model ID: nvidia/active-speaker-detection
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: video
Output: text
Maximum output: 4,096 tokens
Agent MaxThe Grid AI · beta
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens1,000,000
Model ID: agent-max
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text, image
Output: text
Maximum output: 128,000 tokens
Agent PrimeThe Grid AI · beta
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens196,608
Model ID: agent-prime
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text
Output: text
Maximum output: 30,000 tokens
Agent StandardThe Grid AI · beta
Input / 1MNo price declared
Output / 1MNo price declared
Context tokens128,000
Model ID: agent-standard
Base prices USD per 1 million tokens
- Input
- No price declared
- Output
- No price declared
- Cache read
- No price declared
- Cache write
- No price declared
- Reasoning
- No price declared
- Audio input
- No price declared
- Audio output
- No price declared
Input: text
Output: text
Maximum output: 16,000 tokens
Agentic Chat (Claude Fable 5.1)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-fable-5-1
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (Claude Fable 5)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-fable-5
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (Claude Haiku 4.5)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens200,000
Model ID: duo-chat-haiku-4-5
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Agentic Chat (Claude Opus 4.5)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens200,000
Model ID: duo-chat-opus-4-5
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Agentic Chat (Claude Opus 4.6)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-opus-4-6
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Agentic Chat (Claude Opus 4.7)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-opus-4-7
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Agentic Chat (Claude Opus 4.8)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-opus-4-8
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (Claude Opus 5.5)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-opus-5-5
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (Claude Opus 5)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-opus-5
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (Claude Sonnet 4.5)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens200,000
Model ID: duo-chat-sonnet-4-5
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Agentic Chat (Claude Sonnet 4.6)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-sonnet-4-6
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Agentic Chat (Claude Sonnet 5)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,000,000
Model ID: duo-chat-sonnet-5
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 64,000 tokens
Agentic Chat (GPT-5 Codex)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens400,000
Model ID: duo-chat-gpt-5-codex
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5 Mini)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens400,000
Model ID: duo-chat-gpt-5-mini
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.1)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens400,000
Model ID: duo-chat-gpt-5-1
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.2 Codex)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens400,000
Model ID: duo-chat-gpt-5-2-codex
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.2)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens400,000
Model ID: duo-chat-gpt-5-2
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.3 Codex)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens400,000
Model ID: duo-chat-gpt-5-3-codex
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.4 Mini)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens400,000
Model ID: duo-chat-gpt-5-4-mini
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.4 Nano)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens400,000
Model ID: duo-chat-gpt-5-4-nano
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.4)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,050,000
Model ID: duo-chat-gpt-5-4
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.5)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,050,000
Model ID: duo-chat-gpt-5-5
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.6 Luna)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,050,000
Model ID: duo-chat-gpt-5-6-luna
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.6 Sol)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,050,000
Model ID: duo-chat-gpt-5-6-sol
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-5.6 Terra)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,050,000
Model ID: duo-chat-gpt-5-6-terra
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-6 Astra)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,050,000
Model ID: duo-chat-gpt-6-astra
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-6 Luna)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,050,000
Model ID: duo-chat-gpt-6-luna
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agentic Chat (GPT-6 Sol)GitLab Duo
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens1,050,000
Model ID: duo-chat-gpt-6-sol
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Free (as declared)
- Cache write
- Free (as declared)
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image, pdf
Output: text
Maximum output: 128,000 tokens
Agents-A1InferX
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens262,000
Model ID: Agents-A1
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 100,000 tokens
AGI-01 FrontierLucidQuery
Input / 1M$4.5
Output / 1M$22
Context tokens300,000
Model ID: lucidquery-agi-01-frontier
Base prices USD per 1 million tokens
- Input
- $4.5
- Output
- $22
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 120,000 tokens
AGI-01 SwiftLucidQuery
Input / 1M$2.5
Output / 1M$15
Context tokens300,000
Model ID: lucidquery-agi-01-swift
Base prices USD per 1 million tokens
- Input
- $2.5
- Output
- $15
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 120,000 tokens
Agnes 1.5 LiteZenMux
Input / 1M$0.12
Output / 1M$0.6
Context tokens256,000
Model ID: sapiens-ai/agnes-1.5-lite
Base prices USD per 1 million tokens
- Input
- $0.12
- Output
- $0.6
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 256,000 tokens
Agnes 1.5 ProZenMux
Input / 1M$0.16
Output / 1M$0.8
Context tokens256,000
Model ID: sapiens-ai/agnes-1.5-pro
Base prices USD per 1 million tokens
- Input
- $0.16
- Output
- $0.8
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 256,000 tokens
Agnes 2.0 FlashAgnes AI
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens512,000
Model ID: agnes-2.0-flash
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 65,536 tokens
Agnes 2.5 FlashAgnes AI
Input / 1MFree (as declared)
Output / 1MFree (as declared)
Context tokens512,000
Model ID: agnes-2.5-flash
Base prices USD per 1 million tokens
- Input
- Free (as declared)
- Output
- Free (as declared)
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 65,536 tokens
Agnes 2.5 Pro AlphaAgnes AI
Input / 1M$0.45
Output / 1M$0.9
Context tokens1,000,000
Model ID: agnes-2.5-pro-alpha
Base prices USD per 1 million tokens
- Input
- $0.45
- Output
- $0.9
- Cache read
- $0.0038
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 65,536 tokens
Agnes 3.0 FlashNanoGPT
Input / 1M$0.05
Output / 1M$0.15
Context tokens524,288
Model ID: agnes-3.0-flash
Base prices USD per 1 million tokens
- Input
- $0.05
- Output
- $0.15
- Cache read
- $0.005
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text, image
Output: text
Maximum output: 65,536 tokens
Aion 3.0Venice AI
Input / 1M$3.75
Output / 1M$7.5
Context tokens128,000
Model ID: aion-labs-aion-3-0
Base prices USD per 1 million tokens
- Input
- $3.75
- Output
- $7.5
- Cache read
- $0.9375
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion 3.0 MiniVenice AI
Input / 1M$0.875
Output / 1M$1.75
Context tokens128,000
Model ID: aion-labs-aion-3-0-mini
Base prices USD per 1 million tokens
- Input
- $0.875
- Output
- $1.75
- Cache read
- $0.225
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion 3.5OpenRouter
Input / 1M$3
Output / 1M$6
Context tokens262,144
Model ID: aion-labs/aion-3.5
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $6
- Cache read
- $0.75
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion 3.5Venice AI
Input / 1M$3.75
Output / 1M$7.5
Context tokens262,144
Model ID: aion-labs-aion-3-5
Base prices USD per 1 million tokens
- Input
- $3.75
- Output
- $7.5
- Cache read
- $0.9375
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion 3.5 MiniOpenRouter
Input / 1M$0.7
Output / 1M$1.4
Context tokens262,144
Model ID: aion-labs/aion-3.5-mini
Base prices USD per 1 million tokens
- Input
- $0.7
- Output
- $1.4
- Cache read
- $0.18
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion 3.5 MiniVenice AI
Input / 1M$0.875
Output / 1M$1.75
Context tokens262,144
Model ID: aion-labs-aion-3-5-mini
Base prices USD per 1 million tokens
- Input
- $0.875
- Output
- $1.75
- Cache read
- $0.225
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion-2.0OpenRouter
Input / 1M$0.8
Output / 1M$1.6
Context tokens131,072
Model ID: aion-labs/aion-2.0
Base prices USD per 1 million tokens
- Input
- $0.8
- Output
- $1.6
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion-3.0OpenRouter
Input / 1M$3
Output / 1M$6
Context tokens131,072
Model ID: aion-labs/aion-3.0
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $6
- Cache read
- $0.75
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion-3.0-MiniOpenRouter
Input / 1M$0.7
Output / 1M$1.4
Context tokens131,072
Model ID: aion-labs/aion-3.0-mini
Base prices USD per 1 million tokens
- Input
- $0.7
- Output
- $1.4
- Cache read
- $0.18
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
Aion-RP 1.0 (8B)OpenRouter
Input / 1M$0.8
Output / 1M$1.6
Context tokens32,768
Model ID: aion-labs/aion-rp-llama-3.1-8b
Base prices USD per 1 million tokens
- Input
- $0.8
- Output
- $1.6
- Cache read
- Not listed
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 29,491 tokens
AionLabs: Aion 3.0NanoGPT
Input / 1M$3
Output / 1M$6
Context tokens131,072
Model ID: aion-labs/aion-3.0
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $6
- Cache read
- $0.75
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
AionLabs: Aion 3.0 MiniNanoGPT
Input / 1M$0.7
Output / 1M$1.4
Context tokens131,072
Model ID: aion-labs/aion-3.0-mini
Base prices USD per 1 million tokens
- Input
- $0.7
- Output
- $1.4
- Cache read
- $0.18
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
AionLabs: Aion 3.5Kilo Gateway
Input / 1M$3
Output / 1M$6
Context tokens262,144
Model ID: aion-labs/aion-3.5
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $6
- Cache read
- $0.75
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
AionLabs: Aion 3.5NanoGPT
Input / 1M$3
Output / 1M$6
Context tokens262,144
Model ID: aion-labs/aion-3.5
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $6
- Cache read
- $0.75
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
AionLabs: Aion 3.5 MiniKilo Gateway
Input / 1M$0.7
Output / 1M$1.4
Context tokens262,144
Model ID: aion-labs/aion-3.5-mini
Base prices USD per 1 million tokens
- Input
- $0.7
- Output
- $1.4
- Cache read
- $0.18
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
AionLabs: Aion 3.5 MiniNanoGPT
Input / 1M$0.7
Output / 1M$1.4
Context tokens262,144
Model ID: aion-labs/aion-3.5-mini
Base prices USD per 1 million tokens
- Input
- $0.7
- Output
- $1.4
- Cache read
- $0.18
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
AionLabs: Aion-2.0Kilo Gateway
Input / 1M$0.8
Output / 1M$1.6
Context tokens131,072
Model ID: aion-labs/aion-2.0
Base prices USD per 1 million tokens
- Input
- $0.8
- Output
- $1.6
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
AionLabs: Aion-2.0NanoGPT
Input / 1M$0.8
Output / 1M$1.6
Context tokens131,072
Model ID: aion-labs/aion-2.0
Base prices USD per 1 million tokens
- Input
- $0.8
- Output
- $1.6
- Cache read
- $0.2
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
AionLabs: Aion-3.0Kilo Gateway
Input / 1M$3
Output / 1M$6
Context tokens131,072
Model ID: aion-labs/aion-3.0
Base prices USD per 1 million tokens
- Input
- $3
- Output
- $6
- Cache read
- $0.75
- Cache write
- Not listed
- Reasoning
- Not listed
- Audio input
- Not listed
- Audio output
- Not listed
Input: text
Output: text
Maximum output: 32,768 tokens
All prices in USD per 1M tokens. Not listed: component price unavailable. No price declared: no price table. Free (as declared): listed at $0 for that component.
READ THE PRICE, NOT JUST THE MODEL NAME
Two sides to
every request.
You pay for the tokens you send and the tokens the model generates. Compare both rates against the way you actually use a model.
Prompts, context, documents
input tokens ÷ 1M × input rateAnswers, generated code
output tokens ÷ 1M × output rateThis simplified calculation uses base rates for uncached text tokens. Cache usage, context tiers, audio, reasoning and special modes can change the bill. Listed prices are estimates of API costs, not invoices or subscription prices.
Know the rate.
Keep your usage in sight.
Bring your supported AI accounts, usage limits and costs together in tokenkarma.
AI model pricing, explained
How do I compare AI model prices?
Compare input and output prices separately for the same model at the provider you plan to use. All token prices here are in USD per one million tokens. Expand an offer to see cache prices, additional components and any listed context tiers or modes.
Does a ChatGPT or Claude subscription include API usage?
This catalogue compares API token prices. It does not describe what is included in a chat subscription. Check the terms of your plan separately, and use our usage limits comparison to explore chat limits.
Why can the same model have different prices?
Different providers can host or resell the same model with their own rates and conditions. Each model and provider combination has its own offer here. We do not combine those prices or silently select the cheapest provider.
What do “Free”, “Not listed” and “No price declared” mean?
“Free (as declared)” means that specific component has a listed price of zero. “Not listed” means its price is missing. “No price declared” means there is no price table for that offer. A zero token rate does not imply unlimited access or the absence of other charges.
Why does context length matter for pricing?
Some offers list different rates above a context threshold. Expand an offer to see those tiers separately from its base rates. A larger context window is a capacity, not a guarantee that every request has the same price.
How current are these prices?
This catalogue was collected on September 29, 2026. It is a dated snapshot, not a live quote. Rates, availability and billing conditions may change. The catalogue covers the offers listed here, not every model on the market.