APINEED

Models

Anthropic logo

Anthropic: claude-fable-5

Usage-based

claude-fable-5 by Anthropic. Input: text. Output: text. See the current prices and supported requests on its detail page.

by anthropicNot publishedContext not publishedText -> TextInput: $5 – $10.5 / 1M · Output: $25 – $52.5 / 1M · Cache read: $0.5 – $1.05 / 1M · Cache write: $6.25 – $13.125 / 1M · Cache write · 1 hour: $10 – $21 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: claude-fable-5-1

Usage-based

claude-fable-5-1 by Anthropic. Input: text. Output: text. See the current prices and supported requests on its detail page.

by anthropicNot publishedContext not publishedText -> TextInput: $5 – $10.5 / 1M · Output: $25 – $52.5 / 1M · Cache read: $0.125 – $0.2625 / 1M · Cache write: $6.25 – $13.125 / 1M · Cache write · 1 hour: $10 – $21 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: Claude Fable 5 (thinking-high alias)

Usage-based

Claude Fable 5 (thinking-high alias) by Anthropic. Input: text. Output: text. See the current prices and supported requests on its detail page.

by anthropicNot publishedContext not publishedText -> TextInput: $7.5 – $10.5 / 1M · Output: $37.5 – $52.5 / 1M · Cache read: $0.75 – $1.05 / 1M · Cache write: $9.375 – $13.125 / 1M · Cache write · 1 hour: $15 – $21 / 1M · Web search: $7.5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: claude-haiku-4-5

Usage-based

claude-haiku-4-5 by Anthropic. Input: text. Output: text. See the current prices and supported requests on its detail page.

by anthropicNot publishedContext not publishedText -> TextInput: $0.5 – $1.05 / 1M · Output: $2.5 – $5.25 / 1M · Cache read: $0.05 – $0.105 / 1M · Cache write: $0.625 – $1.3125 / 1M · Cache write · 1 hour: $1 – $2.1 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: Claude Opus 4.6

Usage-based

Claude Opus 4.6 by Anthropic. Input: text. Output: text. See the current prices and supported requests on its detail page.

by anthropicNot publishedContext not publishedText -> TextInput: $3.75 – $5.25 / 1M · Output: $18.75 – $26.25 / 1M · Cache read: $0.375 – $0.525 / 1M · Cache write: $4.6875 – $6.5625 / 1M · Cache write · 1 hour: $7.5 – $10.5 / 1M · Web search: $7.5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: Claude Opus 4.7

Usage-based

Claude Opus 4.7 by Anthropic. Input: text. Output: text. See the current prices and supported requests on its detail page.

by anthropicNot publishedContext not publishedText -> TextInput: $3.75 – $5.25 / 1M · Output: $18.75 – $26.25 / 1M · Cache read: $0.375 – $0.525 / 1M · Cache write: $4.6875 – $6.5625 / 1M · Cache write · 1 hour: $7.5 – $10.5 / 1M · Web search: $7.5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: claude-opus-4-8

Usage-based

claude-opus-4-8 by Anthropic. Input: text. Output: text. See the current prices and supported requests on its detail page.

by anthropicNot publishedContext not publishedText -> TextInput: $2.5 – $5.25 / 1M · Output: $12.5 – $26.25 / 1M · Cache read: $0.25 – $0.525 / 1M · Cache write: $3.125 – $6.5625 / 1M · Cache write · 1 hour: $5 – $10.5 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: claude-opus-5

Usage-based

claude-opus-5 API ranks #26 in the LLM2014 logic benchmark with a 24.58 median score, routed through APINEED for stable access and prepaid pricing.

by anthropicNot publishedContext not publishedText -> TextInput: $2.5 – $5.25 / 1M · Output: $12.5 – $26.25 / 1M · Cache read: $0.25 – $0.525 / 1M · Cache write: $3.125 – $6.5625 / 1M · Cache write · 1 hour: $5 – $10.5 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: Claude Sonnet 4.6

Usage-based

Claude Sonnet 4.6 by Anthropic. Input: text. Output: text. See the current prices and supported requests on its detail page.

by anthropicNot publishedContext not publishedText -> TextInput: $2.25 – $3.15 / 1M · Output: $11.25 – $15.75 / 1M · Cache read: $0.225 – $0.315 / 1M · Cache write: $2.8125 – $3.9375 / 1M · Cache write · 1 hour: $4.5 – $6.3 / 1M · Web search: $7.5 – $10.5 / 1K calls
Live pricing
Anthropic logo

Anthropic: claude-sonnet-5

Usage-based

claude-sonnet-5 API ranks #41 in the LLM2014 logic benchmark with a 9.67 median score, routed through APINEED for stable access and prepaid pricing.

by anthropicNot publishedContext not publishedText -> TextInput: $1 – $2.1 / 1M · Output: $5 – $10.5 / 1M · Cache read: $0.1 – $0.21 / 1M · Cache write: $1.25 – $2.625 / 1M · Cache write · 1 hour: $2 – $4.2 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
ByteDance logo

ByteDance: seed-2.1-pro

25% off

seed-2.1-pro API ranks #18 in the LLM2014 logic benchmark with a 45.78 median score, routed through APINEED for stable access and prepaid pricing.

by bytedanceNot publishedContext not publishedText -> TextInput: $0.667665692369 / 1M · Output: $3.338328461846 / 1M · Cache read: $0.133533138474 / 1M · image cache read: $0.133533138474 / 1M · 25% off
Live pricing
ByteDance logo

ByteDance: seed-2.1-turbo

Usage-based

seed-2.1-turbo by ByteDance. Input: text. Output: text. See the current prices and supported requests on its detail page.

by bytedanceNot publishedContext not publishedText -> TextInput: $0.375 – $0.525 / 1M · Output: $1.875 – $2.625 / 1M
Live pricing
Deepseek logo

Deepseek: deepseek-v4-flash

Usage-based

deepseek-v4-flash by Deepseek. Input: text. Output: text. See the current prices and supported requests on its detail page.

by deepseekNot publishedContext not publishedText -> TextInput: $0.098 – $0.2058 / 1M · Output: $0.196 – $0.4116 / 1M · Cache read: $0.0196 – $0.04116 / 1M
Live pricing
Deepseek logo

Deepseek: deepseek-v4-pro

Usage-based

deepseek-v4-pro by Deepseek. Input: text. Output: text. See the current prices and supported requests on its detail page.

by deepseekNot publishedContext not publishedText -> TextInput: $0.47763 – $1.003023 / 1M · Output: $0.95526 – $2.006046 / 1M · Cache read: $0.0398025 – $0.08358525 / 1M
Live pricing
Google logo

Google: gemini-2.5-flash

Usage-based

gemini-2.5-flash by Google. Input: text. Output: text. See the current prices and supported requests on its detail page.

by googleNot publishedContext not publishedText -> TextInput: $0.315 / 1M · Output: $2.625 / 1M · Cache read: $0.0315 / 1M · Audio input: $1.05 / 1M · audio cache read: $0.105 / 1M · cache write storage: $0.0875 / 1M · Web search: $14.7 per thousand requests
Live pricing
Google logo

Google: gemini-3-flash-preview

Usage-based

gemini-3-flash-preview by Google. Input: text. Output: text. See the current prices and supported requests on its detail page.

by googleNot publishedContext not publishedText -> TextInput: $0.25 – $0.525 / 1M · Output: $1.5 – $3.15 / 1M · Cache read: $0.025 – $0.0525 / 1M · Audio input: $0.5 – $1.05 / 1M · audio cache read: $0.05 – $0.105 / 1M · cache write storage: $0.041666666667 – $0.0875 / 1M · Web search: $7 – $14.7 per thousand queries
Live pricing
Google logo

Google: gemini-3.1-pro-preview

50% off

gemini-3.1-pro-preview API ranks #12 in the LLM2014 logic benchmark with a 55.84 median score, routed through APINEED for stable access and prepaid pricing.

by googleNot publishedContext not publishedText -> TextInput (Input context tokens ≤ 200000): $1 / 1M · Input (Input context tokens > 200000): $2 / 1M · Output (Input context tokens ≤ 200000): $6 / 1M · Output (Input context tokens > 200000): $9 / 1M · Cache read (Input context tokens ≤ 200000): $0.1 / 1M · Cache read (Input context tokens > 200000): $0.2 / 1M · Image input (Input context tokens ≤ 200000): $1 / 1M image tokens · Image input (Input context tokens > 200000): $1 / 1M image tokens · cache write storage (Input context tokens ≤ 200000): $0.1875 / 1M · cache write storage (Input context tokens > 200000): $0.1875 / 1M · reasoning output (Input context tokens ≤ 200000): $6 / 1M · reasoning output (Input context tokens > 200000): $6 / 1M · image cache read (Input context tokens ≤ 200000): $0.1 / 1M · image cache read (Input context tokens > 200000): $0.2 / 1M · Web search: $7 per thousand queries · 50% off
Live pricing
Google logo

Google: Gemini 3.5 Flash

Usage-based

Gemini 3.5 Flash by Google. Input: text. Output: text. See the current prices and supported requests on its detail page.

by googleNot publishedContext not publishedText -> TextInput: $1.125 – $1.575 / 1M · Output: $6.75 – $9.45 / 1M · Cache read: $0.1125 – $0.1575 / 1M · Audio input: $2.25 – $3.15 / 1M · audio cache read: $0.225 – $0.315 / 1M · cache write storage: $0.0625 – $0.0875 / 1M · Web search: $10.5 – $14.7 per thousand queries
Live pricing
Google logo

Google: Gemini 3.5 Flash Lite

Usage-based

Gemini 3.5 Flash Lite API ranks #27 in the LLM2014 logic benchmark with a 20.44 median score, routed through APINEED for stable access and prepaid pricing.

by googleNot publishedContext not publishedText -> TextInput: $0.225 – $0.315 / 1M · Output: $1.875 – $2.625 / 1M · Cache read: $0.0225 – $0.0315 / 1M · Cache write: $0.2875 – $0.4025 / 1M · Web search: $10.5 – $14.7 per thousand queries
Live pricing
Google logo

Google: Gemini 3.6 Flash

Usage-based

Gemini 3.6 Flash by Google. Input: text. Output: text. See the current prices and supported requests on its detail page.

by googleNot publishedContext not publishedText -> TextInput: $0.5625 – $0.7875 / 1M · Output: $2.8125 – $3.9375 / 1M · Cache read: $0.05625 – $0.07875 / 1M · Cache write: $0.59375 – $0.83125 / 1M · Web search: $10.5 – $14.7 per thousand queries
Live pricing
Google logo

Google: Gemini 3.7 Flash

Usage-based

Gemini 3.7 Flash API ranks #10 in the LLM2014 logic benchmark with a 57.56 median score, routed through APINEED for stable access and prepaid pricing.

by googleNot publishedContext not publishedText -> TextInput: $0.5625 – $0.7875 / 1M · Output: $2.8125 – $3.9375 / 1M · Cache read: $0.05625 – $0.07875 / 1M · Cache write: $0.59375 – $0.83125 / 1M · Web search: $10.5 – $14.7 per thousand queries
Live pricing
Google logo

Google: gemini-3.8-flash

Usage-based

gemini-3.8-flash by Google. Input: text. Output: text. See the current prices and supported requests on its detail page.

by googleNot publishedContext not publishedText -> TextInput: $0.375 – $0.7875 / 1M · Output: $1.875 – $3.9375 / 1M · Cache read: $0.0375 – $0.07875 / 1M · Cache write: $0.395833333333 – $0.83125 / 1M · Web search: $7 – $14.7 per thousand queries
Live pricing
MiniMax logo

MiniMax: minimax-m3

Usage-based

minimax-m3 API ranks #24 in the LLM2014 logic benchmark with a 37.37 median score, routed through APINEED for stable access and prepaid pricing.

by minimaxNot publishedContext not publishedText -> TextInput: $0.18 – $0.315 / 1M · Output: $0.72 – $1.26 / 1M · Cache read: $0.036 – $0.063 / 1M
Live pricing
Kimi logo

MoonshotAI: kimi-k3

Usage-based

kimi-k3 API ranks #3 in the LLM2014 logic benchmark with a 67.66 median score, routed through APINEED for stable access and prepaid pricing.

by moonshotaiNot publishedContext not publishedText -> TextInput: $2.1 – $3.15 / 1M · Output: $10.5 – $15.75 / 1M · Cache read: $0.21 – $0.315 / 1M
Live pricing
OpenAI logo

OpenAI: gpt-5.6-luna

Usage-based

gpt-5.6-luna API ranks #16 in the LLM2014 logic benchmark with a 51.62 median score, routed through APINEED for stable access and prepaid pricing.

by openaiNot publishedContext not publishedText -> TextInput (Input context tokens > 272000): $0.2 – $0.42 / 1M · Input (Input context tokens ≤ 272000): $0.1 – $0.21 / 1M · Output (Input context tokens > 272000): $0.9 – $1.89 / 1M · Output (Input context tokens ≤ 272000): $0.6 – $1.26 / 1M · Cache read (Input context tokens > 272000): $0.02 – $0.042 / 1M · Cache read (Input context tokens ≤ 272000): $0.01 – $0.021 / 1M · Cache write (Input context tokens > 272000): $0.25 – $0.525 / 1M · Cache write (Input context tokens ≤ 272000): $0.125 – $0.2625 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
OpenAI logo

OpenAI: gpt-5.6-sol

Usage-based

gpt-5.6-sol API ranks #2 in the LLM2014 logic benchmark with a 69.42 median score, routed through APINEED for stable access and prepaid pricing.

by openaiNot publishedContext not publishedText -> TextInput (Input context tokens > 272000): $2 – $4.2 / 1M · Input (Input context tokens ≤ 272000): $1 – $2.1 / 1M · Output (Input context tokens > 272000): $7.5 – $15.75 / 1M · Output (Input context tokens ≤ 272000): $5 – $10.5 / 1M · Cache read (Input context tokens > 272000): $0.2 – $0.42 / 1M · Cache read (Input context tokens ≤ 272000): $0.1 – $0.21 / 1M · Cache write (Input context tokens > 272000): $2.5 – $5.25 / 1M · Cache write (Input context tokens ≤ 272000): $1.25 – $2.625 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
OpenAI logo

OpenAI: gpt-5.6-terra

Usage-based

gpt-5.6-terra by OpenAI. Input: text. Output: text. See the current prices and supported requests on its detail page.

by openaiNot publishedContext not publishedText -> TextInput (Input context tokens > 272000): $2 – $4.2 / 1M · Input (Input context tokens ≤ 272000): $1 – $2.1 / 1M · Output (Input context tokens > 272000): $9 – $18.9 / 1M · Output (Input context tokens ≤ 272000): $6 – $12.6 / 1M · Cache read (Input context tokens > 272000): $0.2 – $0.42 / 1M · Cache read (Input context tokens ≤ 272000): $0.1 – $0.21 / 1M · Cache write (Input context tokens > 272000): $2.5 – $5.25 / 1M · Cache write (Input context tokens ≤ 272000): $1.25 – $2.625 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
OpenAI logo

OpenAI: gpt-6-astra

Usage-based

gpt-6-astra by OpenAI. Input: text. Output: text. See the current prices and supported requests on its detail page.

by openaiNot publishedContext not publishedText -> TextInput (Input context tokens > 272000): $10 – $21 / 1M · Input (Input context tokens ≤ 272000): $5 – $10.5 / 1M · Output (Input context tokens > 272000): $37.5 – $78.75 / 1M · Output (Input context tokens ≤ 272000): $25 – $52.5 / 1M · Cache read (Input context tokens > 272000): $1 – $2.1 / 1M · Cache read (Input context tokens ≤ 272000): $0.5 – $1.05 / 1M · Cache write (Input context tokens > 272000): $12.5 – $26.25 / 1M · Cache write (Input context tokens ≤ 272000): $6.25 – $13.125 / 1M · Web search: $5 – $10.5 / 1K calls
Live pricing
Qwen logo

Qwen: qwen3.6-plus

Usage-based

qwen3.6-plus by Qwen. Input: text. Output: text. See the current prices and supported requests on its detail page.

by qwenNot publishedContext not publishedText -> TextInput (Input context tokens > 256000): $0.91 – $1.365 / 1M · Input (Input context tokens ≤ 256000): $0.2275 – $0.34125 / 1M · Output (Input context tokens > 256000): $2.73 – $4.095 / 1M · Output (Input context tokens ≤ 256000): $1.365 – $2.0475 / 1M · Cache write (Input context tokens > 256000): $1.1375 – $1.70625 / 1M · Cache write (Input context tokens ≤ 256000): $0.284375 – $0.4265625 / 1M
Live pricing
Qwen logo

Qwen: qwen3.7-plus

Usage-based

qwen3.7-plus API ranks #31 in the LLM2014 logic benchmark with a 15.63 median score, routed through APINEED for stable access and prepaid pricing.

by qwenNot publishedContext not publishedText -> TextInput (Input context tokens > 256000): $0.672 – $1.008 / 1M · Input (Input context tokens ≤ 256000): $0.224 – $0.336 / 1M · Output (Input context tokens > 256000): $2.688 – $4.032 / 1M · Output (Input context tokens ≤ 256000): $0.896 – $1.344 / 1M · Cache read (Input context tokens > 256000): $0.1344 – $0.2016 / 1M · Cache read (Input context tokens ≤ 256000): $0.0448 – $0.0672 / 1M · Cache write (Input context tokens > 256000): $0.84 – $1.26 / 1M · Cache write (Input context tokens ≤ 256000): $0.28 – $0.42 / 1M
Live pricing
GLM logo

Z.AI: glm-5.3

20% off

glm-5.3 API ranks #5 in the LLM2014 logic benchmark with a 63.91 median score, routed through APINEED for stable access and prepaid pricing.

by z-aiNot publishedContext not publishedText -> TextInput: $1.12 / 1M · Output: $3.52 / 1M · Cache read: $0.208 / 1M · 20% off
Live pricing