Compare input, output and cache prices, context windows and release dates for 250 models from 21 providers. Claude prices come straight from Anthropic's official price list.
Updated Sep 24, 2026. Prices in USD per 1M tokens.
USD per 1M tokens, 3 input tokens per output token. Lower is cheaper.
Claude Fable 5.1$20.00
GPT-6 Astra$20.00
Claude Opus 5.5$8.00
Kimi K3$6.00
Gemini 3.1 Pro Preview$4.50
Claude Sonnet 5$4.00
GPT-6 Sol$4.00
Qwen3.8 Max (0902)$3.00
Mistral Medium 3.5$3.00
Grok 4.7$2.40
GLM 5.3$2.15
Claude Haiku 4.5$2.00
Muse Spark 1.3$2.00
Gemini 3.8 Flash$1.50
DeepSeek V4 Pro 0813$0.69
MiniMax M3$0.52
Context window
Maximum input tokens per request. Higher fits more code and documents.
GLM 5.31.31M
GPT-6 Astra1.05M
GPT-6 Sol1.05M
Gemini 3.1 Pro Preview1.05M
Gemini 3.8 Flash1.05M
Kimi K31.05M
Muse Spark 1.31.05M
DeepSeek V4 Pro 08131.05M
MiniMax M31.05M
Claude Fable 5.11M
Claude Opus 5.51M
Claude Sonnet 51M
Qwen3.8 Max (0902)1M
Grok 4.7500K
Mistral Medium 3.5262K
Claude Haiku 4.5200K
Price vs. release date
Blended price per 1M tokens on a log scale. Claude models are highlighted.
Claude API pricing
Official first-party rates from Anthropic. Batch requests are 50% off. Cache reads cost 10% of the base input price (2.5% on Fable 5.1, 5% on Opus 5.5).
Claude Fable 5.1
Slower
For demanding reasoning and long-horizon agentic work
$10.00in$50.00out
Context
1M
Max output
128K
Knowledge
Jun 2026
Thinking
Adaptive (always on)
claude-fable-5-1
Claude Opus 5.5
Moderate
For long-running agentic coding and knowledge work
$4.00in$20.00out
Context
1M
Max output
128K
Knowledge
Jun 2026
Thinking
Adaptive (always on)
claude-opus-5-5
Claude Sonnet 5
Fast
The best combination of speed and intelligence
$2.00in$10.00out
Context
1M
Max output
128K
Knowledge
Jan 2026
Thinking
Adaptive
claude-sonnet-5
Claude Haiku 4.5
Fastest
The fastest model with near-frontier intelligence
$1.00in$5.00out
Context
200K
Max output
64K
Knowledge
Feb 2025
Thinking
Extended
claude-haiku-4-5
Claude API prices per million tokens
Model
Input
Output
5m cache write
1h cache write
Cache read
Batch in / out
Context
Claude Fable 5.1
claude-fable-5-1
$10.00
$50.00
$12.50
$20.00
$0.25
$5.00 / $25.00
1M
Claude Opus 5.5
claude-opus-5-5
$4.00
$20.00
$5.00
$8.00
$0.20
$2.00 / $10.00
1M
Claude Sonnet 5
claude-sonnet-5
$2.00
$10.00
$2.50
$4.00
$0.20
$1.00 / $5.00
1M
Claude Haiku 4.5
claude-haiku-4-5
$1.00
$5.00
$1.25
$2.00
$0.10
$0.50 / $2.50
200K
Claude Fable 5Legacy
claude-fable-5
$10.00
$50.00
$12.50
$20.00
$1.00
$5.00 / $25.00
1M
Claude Opus 5Legacy
claude-opus-5
$5.00
$25.00
$6.25
$10.00
$0.50
$2.50 / $12.50
1M
Claude Opus 4.8Legacy
claude-opus-4-8
$5.00
$25.00
$6.25
$10.00
$0.50
$2.50 / $12.50
1M
Claude Opus 4.7Legacy
claude-opus-4-7
$5.00
$25.00
$6.25
$10.00
$0.50
$2.50 / $12.50
1M
Claude Opus 4.6Legacy
claude-opus-4-6
$5.00
$25.00
$6.25
$10.00
$0.50
$2.50 / $12.50
1M
Claude Sonnet 4.6Legacy
claude-sonnet-4-6
$3.00
$15.00
$3.75
$6.00
$0.30
$1.50 / $7.50
1M
Claude Opus 4.5Legacy
claude-opus-4-5
$5.00
$25.00
$6.25
$10.00
$0.50
$2.50 / $12.50
200K
Claude Sonnet 4.5Legacy
claude-sonnet-4-5
$3.00
$15.00
$3.75
$6.00
$0.30
$1.50 / $7.50
200K
Source: Anthropic pricing docs, checked Sep 24, 2026. US-only inference adds 10%. Amazon Bedrock and Google Cloud set their own prices.
All models
GLM 5.3 Prime
Z.ai
$2.80
$8.80
$4.30
$0.56
1M
Sep 23, 2026
Qwen3.8 Max Prime
Qwen
$4.00
$12.00
$6.00
$0.50
1M
Sep 23, 2026
Claude Opus 5.5
Anthropic
$4.00
$20.00
$8.00
$0.20
1M
Sep 22, 2026
Command A+
Cohere
$0.30
$1.50
$0.60
$0.15
192K
Sep 22, 2026
GPT-6 Luna Pro
OpenAI
$0.10
$0.50
$0.20
$0.010
1.05M
Sep 22, 2026
GPT-6 Luna
OpenAI
$0.10
$0.50
$0.20
$0.010
1.05M
Sep 22, 2026
GPT-6 Sol Pro
OpenAI
$2.00
$10.00
$4.00
$0.20
1.05M
Sep 22, 2026
GPT-6 Sol
OpenAI
$2.00
$10.00
$4.00
$0.20
1.05M
Sep 22, 2026
MiMo-V2.6-Pro-UltraSpeed
Xiaomi
$4.35
$8.70
$5.44
$0.036
1.05M
Sep 21, 2026
MiMo-V2.6-FlashOpen
Xiaomi
$0.14
$0.28
$0.18
$0.003
1.05M
Sep 21, 2026
MiMo-V2.6-ProOpen
Xiaomi
$0.43
$0.87
$0.54
$0.004
1.05M
Sep 21, 2026
Grok 4.7
xAI
$1.60
$4.80
$2.40
$0.40
500K
Sep 21, 2026
Qwen3.8 Omni Flash
Qwen
$0.15
$0.47
$0.23
$0.016
1M
Sep 21, 2026
GLM 5.3 FlashX
Z.ai
$0.37
$1.25
$0.59
$0.090
1.05M
Sep 18, 2026
Ling 3.0 Flash VLOpen
inclusionAI
$0.060
$0.18
$0.090
$0.012
262K
Sep 10, 2026
DeepSeek V4.1 FlashOpen
DeepSeek
$0.14
$0.42
$0.21
$0.004
1.05M
Sep 10, 2026
GPT-6 Astra
OpenAI
$10.00
$50.00
$20.00
$1.00
1.05M
Sep 4, 2026
GPT-6 Astra Pro
OpenAI
$10.00
$50.00
$20.00
$1.00
1.05M
Sep 4, 2026
Qwen3.8 Max (0902)
Qwen
$2.00
$6.00
$3.00
$0.25
1M
Sep 3, 2026
Muse Spark 1.3 Contributor
Meta
$0.10
$0.20
$0.13
$0.002
1.05M
Sep 2, 2026
Muse Spark 1.3
Meta
$1.25
$4.25
$2.00
$0.15
1.05M
Sep 2, 2026
Gemini 3.8 Flash
Google
$0.75
$3.75
$1.50
$0.075
1.05M
Sep 2, 2026
Claude Fable 5.1
Anthropic
$10.00
$50.00
$20.00
$0.25
1M
Sep 1, 2026
Hy4 previewOpen
Tencent
$0.83
$2.50
$1.25
$0.042
1.05M
Aug 28, 2026
Ling 3.0 Flash Fin
inclusionAI
$0.060
$0.18
$0.090
$0.012
262K
Aug 27, 2026
Qwen3.8 FlashOpen
Qwen
$0.15
$0.47
$0.23
$0.016
1M
Aug 26, 2026
GLM 5.3 FlashOpen
Z.ai
$0.15
$0.50
$0.24
$0.050
1.31M
Aug 26, 2026
Muse Spark 1.2 Contributor
Meta
$0.10
$0.20
$0.13
$0.002
1.05M
Aug 21, 2026
DeepSeek V4 Flash Vision ExpOpen
DeepSeek
$0.22
$0.66
$0.33
$0.007
1.05M
Aug 21, 2026
Hy-MT2-1.8BOpen
Tencent
$0.044
$0.18
$0.077
-
8K
Aug 20, 2026
Hy-MT2-30B-A3BOpen
Tencent
$0.074
$0.29
$0.13
-
8K
Aug 20, 2026
Hy-MT2-7BOpen
Tencent
$0.074
$0.29
$0.13
-
8K
Aug 19, 2026
GLM 5.3Open
Z.ai
$1.40
$4.40
$2.15
$0.26
1.31M
Aug 18, 2026
Qwen3.8 27BOpen
Qwen
$0.42
$3.00
$1.06
$0.085
1M
Aug 14, 2026
Gemini 3.7 Flash
Google
$0.75
$3.75
$1.50
$0.075
1.05M
Aug 13, 2026
Seed 2.1 Turbo
ByteDance
$0.50
$2.50
$1.00
-
262K
Aug 12, 2026
Qwen3.8 2.4T A95BOpen
Qwen
$2.00
$6.00
$3.00
$0.25
1.05M
Aug 12, 2026
Seed-2.0-Code
ByteDance
$0.50
$3.00
$1.13
-
262K
Aug 12, 2026
DeepSeek V4 Pro 0813Open
DeepSeek
$0.46
$1.39
$0.69
$0.015
1.05M
Aug 12, 2026
Grok 4.6
xAI
$2.00
$6.00
$3.00
$0.50
500K
Aug 12, 2026
Showing 40 of 250 models. Prices in USD per 1M tokens.
Questions about LLM API pricing
How much does the Claude API cost?+
Claude Opus 5.5 costs $4 per million input tokens and $20 per million output tokens. Claude Sonnet 5 costs $2 and $10, Claude Haiku 4.5 costs $1 and $5, and Claude Fable 5.1 costs $10 and $50. The Batch API halves these prices, and cached input is billed at a fraction of the base input price.
What is the blended price?+
The blended price assumes 3 input tokens for every output token, which is close to a typical chat or coding workload. It gives one number per model so you can compare them quickly. Use the cost calculator for your own mix of input and output.
Where does this data come from?+
Claude prices come from Anthropic's official pricing page (checked Sep 24, 2026). Prices for other providers come from the public OpenRouter model catalog, which lists each provider's pay-as-you-go rate. Direct contracts, regional endpoints and cloud marketplaces can be priced differently.
Why can the same prompt cost more on a newer model with the same price?+
Tokenizers differ between models. Anthropic notes that Claude 4.7 and later use a newer tokenizer that produces roughly 30% more tokens for the same text, so compare the cost of real requests, not only the per-token price.