CtrlAltDebrief

Reasoning LLM API pricing

All 521 models that produce extended step-by-step reasoning before answering, trading latency and reasoning-token cost for harder problem-solving, cheapest input from $0.01 per 1M tokens. Sort by price, context window or benchmark, filter by maker, and copy the exact model ID for any serving provider. Listed prices from LiteLLM, OpenRouter and Vercel.

Models

521

with reasoning

Cheapest input

$0.01

per 1M tokens

Cheapest output

$0.03

per 1M tokens

Max context

5M

tokens

On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
Maker
gpt-oss-120bOpenAIReleased Aug 5, 2025131K
from $0.03
via Wandb
from $0.17
via DeepInfra		11.626%78%23 providers
GLM 5.2ZhipuReleased Jun 13, 20261M
from $0.05
Routed quote
from $1.98
via Scx AI		33.778%89%20 providers
DeepSeek V4 Flash 0423DeepSeekReleased Apr 24, 20261M
from $0.09
via DeepInfra
from $0.18
via DeepInfra		24.262%89%18 providers
DeepSeek V4 Flash 0731DeepSeekReleased Jul 31, 20261M
from $0.016
Routed quote
from $0.153
Routed quote		34.379%91%16 providers
GLM 5.3ZhipuReleased Aug 14, 20261M
from $0.079
Routed quote
from $3.08
via Sail		44.884%92%16 providers
DeepSeek V4 Pro 0423DeepSeekReleased Apr 24, 20261M
from $0.435
via Tencent
from $0.87
via Tencent		30.465%89%16 providers
Kimi K2.7 CodeMoonshotReleased Jun 13, 2026262K
from $0.671
Routed quote
from $3.35
Routed quote		25.867%90%16 providers
gpt-oss-20bOpenAIReleased Mar 1, 2026131K
from $0.0145
via Darkbloom
from $0.07
via Darkbloom		9.014%69%15 providers
Kimi K2.6MoonshotFirst listed Apr 2026262K
from $0.65
via Wandb
from $3.40
via Novita		27.066%91%15 providers
R1DeepSeekReleased Jan 1, 2025164K
from $0.40
via Hyperbolic
from $0.40
via Hyperbolic		11.419%71%14 providers
Kimi K3MoonshotReleased Jul 16, 20261M
from $0.70
Routed quote
from $12.50
via Sail		43.685%94%14 providers
Gemma 4 31BGoogleReleased Apr 2, 2026262K
from $0.09
Routed quote
from $0.34
via Wandb		n/an/an/a13 providers
GLM 5.3 FlashZhipuReleased Aug 26, 20261M
from $0.11
via Sail
from $0.35
via Sail		41.884%91%13 providers
DeepSeek V4.1 FlashDeepSeekReleased Sep 10, 20261M
from $0.01
via Coralbricks
from $0.60
via Sail		39.5n/an/a12 providers
DeepSeek V4 Pro 0813DeepSeekReleased Aug 14, 20261M
from $0.66
Routed quote
from $1.98
Routed quote		36.079%93%12 providers
GLM 5.1ZhipuReleased Apr 7, 2026205K
from $1.05
via DeepInfra
from $3.50
via DeepInfra		26.162%87%12 providers
Qwen3 Next 80B A3B InstructAlibabaFirst listed Sep 2025262K
from $0.09
via DeepInfra
from $0.90
via Fireworks AI		9.6n/a74%11 providers
DeepSeek R1 Distill Llama 70BDeepSeekReleased Jan 1, 2025131K
from $0.20
via DeepInfra
from $0.375
via Nscale		7.9n/a40%11 providers
MiniMax M3MiniMaxReleased Jun 1, 20261M
from $0.23
via Wandb
from $0.96
via Wandb		29.265%93%11 providers
DeepSeek V3.1DeepSeekReleased Jan 1, 2025164K
from $0.25
via DeepInfra
from $0.95
via DeepInfra		13.7n/a74%11 providers
DeepSeek V3.2DeepSeekReleased Dec 1, 2025164K
from $0.259
Routed quote
from $0.38
via DeepInfra		16.047%75%11 providers
Kimi K2.5MoonshotReleased Jan 27, 2026262K
from $0.45
via DeepInfra
from $2.25
via DeepInfra		23.546%88%11 providers
Claude Haiku 4.5AnthropicReleased Oct 15, 2025200K
from $1.00
via Anthropic
from $5.00
via Anthropic		n/an/an/a11 providers
Gemma 4 26B A4B GoogleReleased Apr 2, 2026262K
from $0.07
via DeepInfra
from $0.255
Routed quote		n/an/an/a10 providers
Qwen3 32BAlibabaFirst listed May 2025131K
from $0.08
via DeepInfra
from $0.23
via Ovhcloud		7.35%54%10 providers
Qwen3 Next 80B A3B ThinkingAlibabaFirst listed Sep 2025262K
from $0.14
via DeepInfra
from $0.90
via Fireworks AI		n/an/an/a10 providers
R1 0528DeepSeekReleased May 28, 2025164K
from $0.20
via Lambda AI
from $0.25
via Hyperbolic		13.1n/a81%10 providers
MiniMax M2.5MiniMaxReleased Jan 15, 20251M
from $0.27
Routed quote
from $1.08
Routed quote		22.8n/a85%10 providers
GLM 4.7ZhipuFirst listed Jan 2026205K
from $0.40
via DeepInfra
from $1.75
via DeepInfra		22.245%86%10 providers
Kimi K2 ThinkingMoonshotReleased Nov 6, 2025262K
from $0.60
via Moonshot
from $1.20
via Gmi		22.0n/a84%10 providers
Qwen3.8 MaxAlibabaReleased Aug 3, 20261M
from $1.65
via DeepInfra
from $4.95
via DeepInfra		40.181%93%10 providers
Qwen3.6 35B A3BAlibabaReleased Jul 20, 2026262K
from $0.05
via Sail
from $0.40
via Sail		18.245%84%9 providers
GPT-5 MiniOpenAIReleased Aug 7, 20251M
from $0.25
via Databricks
from $1.20
via Snowflake		16.84%83%9 providers
MiniMax M2.7MiniMaxReleased Mar 18, 20261M
from $0.25
via DeepInfra
from $0.55
via Pinstripes		22.855%87%9 providers
GLM 4.6ZhipuFirst listed Oct 2025205K
from $0.50
via DeepInfra
from $2.00
via DeepInfra		14.949%63%9 providers
GLM 5ZhipuReleased Feb 12, 20261M
from $0.60
via DeepInfra
from $1.92
Routed quote		27.9n/a82%9 providers
GPT-5OpenAIReleased Aug 7, 2025410K
from $1.25
via Databricks
from $10.00
via Databricks		23.035%85%9 providers
Claude Sonnet 5AnthropicReleased Jun 30, 20261M
from $2.00
via Anthropic
from $10.00
via Anthropic		38.281%91%9 providers
Claude Sonnet 4.6AnthropicReleased Feb 17, 20261M
from $3.00
via Databricks
from $15.00
via Anthropic		24.771%80%9 providers
Claude Opus 5AnthropicReleased Jul 24, 20261M
from $5.00
via Anthropic
from $25.00
via Anthropic		50.889%93%9 providers
Claude Fable 5AnthropicReleased Jun 9, 20261M
from $10.00
via Anthropic
from $50.00
via Anthropic		49.685%93%9 providers
GPT-5 NanoOpenAIReleased Aug 7, 20255M
from $0.05
via Databricks
from $0.40
via Databricks		13.0n/a68%8 providers
Gemini 2.5 FlashGoogleReleased Jun 17, 20251M
from $0.15
via OCI
from $0.60
via OCI		9.8n/a68%8 providers
Qwen3.6 27BAlibabaReleased Apr 24, 2026262K
from $0.15
via Libertai
from $0.50
via Libertai		21.461%84%8 providers
QwQ 32BAlibabaReleased Apr 15, 2025131K
from $0.15
via DeepInfra
from $0.20
via Hyperbolic		9.5n/a59%8 providers
Qwen3.7 MaxAlibabaReleased May 21, 20261M
from $1.25
via Novita
from $3.75
via Novita		29.575%92%8 providers
Grok 4.6xAIReleased Aug 10, 2026524K
from $2.00
via xAI
from $6.00
via xAI		44.388%95%8 providers
Claude Sonnet 4.5AnthropicReleased Sep 29, 20251M
from $3.00
via Databricks
from $15.00
via Anthropic		n/an/an/a8 providers
Claude Opus 4.7AnthropicReleased Apr 16, 20261M
from $5.00
via Anthropic
from $25.00
via Anthropic		40.783%91%8 providers
Claude Opus 4.8AnthropicReleased May 28, 20261M
from $5.00
via Anthropic
from $25.00
via Anthropic		41.885%92%8 providers
gpt-oss-120b
OpenAI · 131K CTX
Released Aug 5, 2025
Input $/1M
from$0.03
via Wandb
Output $/1M
from$0.17
via DeepInfra
Intelligence11.623 providers
GLM 5.2
Zhipu · 1M CTX
Released Jun 13, 2026
Input $/1M
from$0.05
Routed quote
Output $/1M
from$1.98
via Scx AI
Intelligence33.720 providers
DeepSeek V4 Flash 0423
DeepSeek · 1M CTX
Released Apr 24, 2026
Input $/1M
from$0.09
via DeepInfra
Output $/1M
from$0.18
via DeepInfra
Intelligence24.218 providers
DeepSeek V4 Flash 0731
DeepSeek · 1M CTX
Released Jul 31, 2026
Input $/1M
from$0.016
Routed quote
Output $/1M
from$0.153
Routed quote
Intelligence34.316 providers
GLM 5.3
Zhipu · 1M CTX
Released Aug 14, 2026
Input $/1M
from$0.079
Routed quote
Output $/1M
from$3.08
via Sail
Intelligence44.816 providers
DeepSeek V4 Pro 0423
DeepSeek · 1M CTX
Released Apr 24, 2026
Input $/1M
from$0.435
via Tencent
Output $/1M
from$0.87
via Tencent
Intelligence30.416 providers
Kimi K2.7 Code
Moonshot · 262K CTX
Released Jun 13, 2026
Input $/1M
from$0.671
Routed quote
Output $/1M
from$3.35
Routed quote
Intelligence25.816 providers
gpt-oss-20b
OpenAI · 131K CTX
Released Mar 1, 2026
Input $/1M
from$0.0145
via Darkbloom
Output $/1M
from$0.07
via Darkbloom
Intelligence9.015 providers
Kimi K2.6
Moonshot · 262K CTX
First listed Apr 2026
Input $/1M
from$0.65
via Wandb
Output $/1M
from$3.40
via Novita
Intelligence27.015 providers
R1
DeepSeek · 164K CTX
Released Jan 1, 2025
Input $/1M
from$0.40
via Hyperbolic
Output $/1M
from$0.40
via Hyperbolic
Intelligence11.414 providers
Kimi K3
Moonshot · 1M CTX
Released Jul 16, 2026
Input $/1M
from$0.70
Routed quote
Output $/1M
from$12.50
via Sail
Intelligence43.614 providers
Gemma 4 31B
Google · 262K CTX
Released Apr 2, 2026
Input $/1M
from$0.09
Routed quote
Output $/1M
from$0.34
via Wandb
Intelligencen/a13 providers
GLM 5.3 Flash
Zhipu · 1M CTX
Released Aug 26, 2026
Input $/1M
from$0.11
via Sail
Output $/1M
from$0.35
via Sail
Intelligence41.813 providers
DeepSeek V4.1 Flash
DeepSeek · 1M CTX
Released Sep 10, 2026
Input $/1M
from$0.01
via Coralbricks
Output $/1M
from$0.60
via Sail
Intelligence39.512 providers
DeepSeek V4 Pro 0813
DeepSeek · 1M CTX
Released Aug 14, 2026
Input $/1M
from$0.66
Routed quote
Output $/1M
from$1.98
Routed quote
Intelligence36.012 providers
GLM 5.1
Zhipu · 205K CTX
Released Apr 7, 2026
Input $/1M
from$1.05
via DeepInfra
Output $/1M
from$3.50
via DeepInfra
Intelligence26.112 providers
Qwen3 Next 80B A3B Instruct
Alibaba · 262K CTX
First listed Sep 2025
Input $/1M
from$0.09
via DeepInfra
Output $/1M
from$0.90
via Fireworks AI
Intelligence9.611 providers
DeepSeek R1 Distill Llama 70B
DeepSeek · 131K CTX
Released Jan 1, 2025
Input $/1M
from$0.20
via DeepInfra
Output $/1M
from$0.375
via Nscale
Intelligence7.911 providers
MiniMax M3
MiniMax · 1M CTX
Released Jun 1, 2026
Input $/1M
from$0.23
via Wandb
Output $/1M
from$0.96
via Wandb
Intelligence29.211 providers
DeepSeek V3.1
DeepSeek · 164K CTX
Released Jan 1, 2025
Input $/1M
from$0.25
via DeepInfra
Output $/1M
from$0.95
via DeepInfra
Intelligence13.711 providers
DeepSeek V3.2
DeepSeek · 164K CTX
Released Dec 1, 2025
Input $/1M
from$0.259
Routed quote
Output $/1M
from$0.38
via DeepInfra
Intelligence16.011 providers
Kimi K2.5
Moonshot · 262K CTX
Released Jan 27, 2026
Input $/1M
from$0.45
via DeepInfra
Output $/1M
from$2.25
via DeepInfra
Intelligence23.511 providers
Claude Haiku 4.5
Anthropic · 200K CTX
Released Oct 15, 2025
Input $/1M
from$1.00
via Anthropic
Output $/1M
from$5.00
via Anthropic
Intelligencen/a11 providers
Gemma 4 26B A4B
Google · 262K CTX
Released Apr 2, 2026
Input $/1M
from$0.07
via DeepInfra
Output $/1M
from$0.255
Routed quote
Intelligencen/a10 providers
Qwen3 32B
Alibaba · 131K CTX
First listed May 2025
Input $/1M
from$0.08
via DeepInfra
Output $/1M
from$0.23
via Ovhcloud
Intelligence7.310 providers
Qwen3 Next 80B A3B Thinking
Alibaba · 262K CTX
First listed Sep 2025
Input $/1M
from$0.14
via DeepInfra
Output $/1M
from$0.90
via Fireworks AI
Intelligencen/a10 providers
R1 0528
DeepSeek · 164K CTX
Released May 28, 2025
Input $/1M
from$0.20
via Lambda AI
Output $/1M
from$0.25
via Hyperbolic
Intelligence13.110 providers
MiniMax M2.5
MiniMax · 1M CTX
Released Jan 15, 2025
Input $/1M
from$0.27
Routed quote
Output $/1M
from$1.08
Routed quote
Intelligence22.810 providers
GLM 4.7
Zhipu · 205K CTX
First listed Jan 2026
Input $/1M
from$0.40
via DeepInfra
Output $/1M
from$1.75
via DeepInfra
Intelligence22.210 providers
Kimi K2 Thinking
Moonshot · 262K CTX
Released Nov 6, 2025
Input $/1M
from$0.60
via Moonshot
Output $/1M
from$1.20
via Gmi
Intelligence22.010 providers
Qwen3.8 Max
Alibaba · 1M CTX
Released Aug 3, 2026
Input $/1M
from$1.65
via DeepInfra
Output $/1M
from$4.95
via DeepInfra
Intelligence40.110 providers
Qwen3.6 35B A3B
Alibaba · 262K CTX
Released Jul 20, 2026
Input $/1M
from$0.05
via Sail
Output $/1M
from$0.40
via Sail
Intelligence18.29 providers
GPT-5 Mini
OpenAI · 1M CTX
Released Aug 7, 2025
Input $/1M
from$0.25
via Databricks
Output $/1M
from$1.20
via Snowflake
Intelligence16.89 providers
MiniMax M2.7
MiniMax · 1M CTX
Released Mar 18, 2026
Input $/1M
from$0.25
via DeepInfra
Output $/1M
from$0.55
via Pinstripes
Intelligence22.89 providers
GLM 4.6
Zhipu · 205K CTX
First listed Oct 2025
Input $/1M
from$0.50
via DeepInfra
Output $/1M
from$2.00
via DeepInfra
Intelligence14.99 providers
GLM 5
Zhipu · 1M CTX
Released Feb 12, 2026
Input $/1M
from$0.60
via DeepInfra
Output $/1M
from$1.92
Routed quote
Intelligence27.99 providers
GPT-5
OpenAI · 410K CTX
Released Aug 7, 2025
Input $/1M
from$1.25
via Databricks
Output $/1M
from$10.00
via Databricks
Intelligence23.09 providers
Claude Sonnet 5
Anthropic · 1M CTX
Released Jun 30, 2026
Input $/1M
from$2.00
via Anthropic
Output $/1M
from$10.00
via Anthropic
Intelligence38.29 providers
Claude Sonnet 4.6
Anthropic · 1M CTX
Released Feb 17, 2026
Input $/1M
from$3.00
via Databricks
Output $/1M
from$15.00
via Anthropic
Intelligence24.79 providers
Claude Opus 5
Anthropic · 1M CTX
Released Jul 24, 2026
Input $/1M
from$5.00
via Anthropic
Output $/1M
from$25.00
via Anthropic
Intelligence50.89 providers
Claude Fable 5
Anthropic · 1M CTX
Released Jun 9, 2026
Input $/1M
from$10.00
via Anthropic
Output $/1M
from$50.00
via Anthropic
Intelligence49.69 providers
GPT-5 Nano
OpenAI · 5M CTX
Released Aug 7, 2025
Input $/1M
from$0.05
via Databricks
Output $/1M
from$0.40
via Databricks
Intelligence13.08 providers
Gemini 2.5 Flash
Google · 1M CTX
Released Jun 17, 2025
Input $/1M
from$0.15
via OCI
Output $/1M
from$0.60
via OCI
Intelligence9.88 providers
Qwen3.6 27B
Alibaba · 262K CTX
Released Apr 24, 2026
Input $/1M
from$0.15
via Libertai
Output $/1M
from$0.50
via Libertai
Intelligence21.48 providers
QwQ 32B
Alibaba · 131K CTX
Released Apr 15, 2025
Input $/1M
from$0.15
via DeepInfra
Output $/1M
from$0.20
via Hyperbolic
Intelligence9.58 providers
Qwen3.7 Max
Alibaba · 1M CTX
Released May 21, 2026
Input $/1M
from$1.25
via Novita
Output $/1M
from$3.75
via Novita
Intelligence29.58 providers
Grok 4.6
xAI · 524K CTX
Released Aug 10, 2026
Input $/1M
from$2.00
via xAI
Output $/1M
from$6.00
via xAI
Intelligence44.38 providers
Claude Sonnet 4.5
Anthropic · 1M CTX
Released Sep 29, 2025
Input $/1M
from$3.00
via Databricks
Output $/1M
from$15.00
via Anthropic
Intelligencen/a8 providers
Claude Opus 4.7
Anthropic · 1M CTX
Released Apr 16, 2026
Input $/1M
from$5.00
via Anthropic
Output $/1M
from$25.00
via Anthropic
Intelligence40.78 providers
Claude Opus 4.8
Anthropic · 1M CTX
Released May 28, 2026
Input $/1M
from$5.00
via Anthropic
Output $/1M
from$25.00
via Anthropic
Intelligence41.88 providers
1–50 of 568 models
Page 1 of 12
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 184 prices older, back to Jul 19, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI