Skip to main content
Back to pricing

Model pricing

What the models behind your agents cost. While an agent works, the tokens it uses are billed at the provider's rates below, passed through at cost, plus the bandwidth fee per token. With BYOK (Bring Your Own Keys), your own provider key pays the provider cost and only the bandwidth fee is billed.

Models outside the direct providers (OpenAI, Anthropic, Google, SpaceXAI) run through OpenRouter, and their ids carry the openrouter/ prefix. Prices sync automatically from the provider and OpenRouter catalogs.

A request through OpenRouter is billed the exact cost OpenRouter reports for it. For a model that runs on its provider's own endpoint (most models from the major providers), the rate below is the most a request costs (off-peak and cached requests cost less); any other OpenRouter model is billed what the host that served it charged, which can differ from the rate below. A router picks the model for each request and is billed the reported cost of the model it picks.

A model marked with a shutdown date is being retired by its provider. It keeps working until that date; after it, requests to it fail and the agent's backup model takes over.

Anthropic(18 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Anthropic: Claude Fable 5
$10.00$50.00$0.50$1.00-1M
Anthropic: Claude Fable 5.1
$10.00$50.00$0.50$0.25-1M
Anthropic: Claude Fable 5.2
$8.00$40.00$0.50$0.20-1M
Anthropic: Claude Haiku 4.5
$1.00$5.00$0.18$0.10-200K
Anthropic: Claude Haiku 5.5
$0.10$0.50 >100K
$0.50$2.50 >100K
$0.13
$0.01$0.05 >100K
-1M
Anthropic: claude-opus-4
$15.00$75.00$0.50$1.50--
Anthropic: Claude Opus 4.1
$15.00$75.00$0.50$1.50-200K
Anthropic: Claude Opus 4.5
$5.00$25.00$0.50$0.50-200K
Anthropic: Claude Opus 4.6
$5.00$25.00$0.50$0.50-1M
Anthropic: Claude Opus 4.7
$5.00$25.00$0.50$0.50-1M
Anthropic: Claude Opus 4.8
$5.00$25.00$0.50$0.50-1M
Anthropic: Claude Opus 5
$5.00$25.00$0.50$0.50-1M
Anthropic: Claude Opus 5.5
$4.00$20.00$0.48$0.20-1M
Anthropic: claude-sonnet-4
$3.00$15.00$0.38$0.30--
Anthropic: Claude Sonnet 4.5
$3.00$6.00 >200K
$15.00$22.50 >200K
$0.50
$0.30$0.60 >200K
-1M
Anthropic: Claude Sonnet 4.6
$3.00$15.00$0.38$0.30-1M
Anthropic: Claude Sonnet 5
$2.00$10.00$0.28$0.20-1M
Anthropic: Claude Sonnet 5.5
$2.00$10.00$0.28$0.10-1M

OpenAI(79 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
OpenAI: computer-use-preview
$3.00$12.00$0.32---
OpenAI: GPT-3.5 Turbo (older v0613)
$1.00$2.00$0.12--4K
OpenAI: GPT-3.5 Turbo 16k
$3.00$4.00$0.16--16K
OpenAI: GPT-4
$30.00$60.00$0.50--8K
OpenAI: GPT-4.1
$2.00$8.00$0.24$0.50-1M
OpenAI: GPT-4.1 Mini
$0.40$1.60$0.112$0.10-1M
OpenAI: GPT-4.1 Nano
$0.10$0.40$0.10$0.025-1M
OpenAI: GPT-4o
$2.50$10.00$0.28$1.25-128K
OpenAI: GPT-4o (2024-05-13)
$5.00$15.00$0.38--128K
OpenAI: GPT-4o (2024-08-06)
$2.50$10.00$0.28$1.25-128K
OpenAI: GPT-4o (2024-11-20)
$2.50$10.00$0.28$1.25-128K
OpenAI: GPT-4o-mini
$0.15$0.60$0.10$0.075-128K
OpenAI: GPT-4o-mini (2024-07-18)
$0.15$0.60$0.10$0.075-128K
OpenAI: gpt-4o-mini-transcribe
$1.25$5.00$0.18---
OpenAI: gpt-4o-transcribe
$2.50$10.00$0.28---
OpenAI: GPT-5
$1.25$10.00$0.28$0.125-400K
OpenAI: GPT-5 Image
$10.00$10.00$0.28$1.25-400K
OpenAI: GPT-5 Image Mini
$2.50$2.00$0.12$0.25-400K
OpenAI: GPT-5 Mini
$0.25$2.00$0.12$0.025-400K
OpenAI: GPT-5 Nano
$0.05$0.40$0.10$0.005-400K
OpenAI: GPT-5 Pro
$15.00$120.00$0.50--400K
OpenAI: GPT-5.1
$1.25$10.00$0.28$0.125-400K
OpenAI: GPT-5.1-Codex
$1.25$10.00$0.28$0.13-400K
OpenAI: GPT-5.1-Codex-Max
$1.25$10.00$0.28$0.125-400K
OpenAI: GPT-5.1-Codex-Mini
$0.25$2.00$0.12$0.03-400K
OpenAI: GPT-5.2
$1.75$14.00$0.36$0.175-400K
OpenAI: GPT-5.2 Chat
$1.75$14.00$0.36$0.175-128K
OpenAI: GPT-5.2-Codex
$1.75$14.00$0.36$0.175-400K
OpenAI: GPT-5.2 Pro
$21.00$168.00$0.50--400K
OpenAI: GPT-5.3-Codex
$1.75$14.00$0.36$0.175-400K
OpenAI: GPT-5.4
$2.50$5.00 >272K
$15.00$22.50 >272K
$0.50
$0.25$0.50 >272K
-1M
OpenAI: GPT-5.4 Image 2
$8.00$15.00$0.38$2.00-272K
OpenAI: GPT-5.4 Mini
$0.75$4.50$0.17$0.075-400K
OpenAI: GPT-5.4 Nano
$0.20$1.25$0.105$0.02-400K
OpenAI: GPT-5.4 Pro
$30.00$60.00 >272K
$180.00$270.00 >272K
$0.50--1M
OpenAI: GPT-5.5
$5.00$10.00 >272K
$30.00$45.00 >272K
$0.50
$0.50$1.00 >272K
-1M
OpenAI: GPT-5.5 Pro
$30.00$60.00 >272K
$180.00$270.00 >272K
$0.50--1M
OpenAI: gpt-5.6
$4.00$8.00 >272K
$20.00$30.00 >272K
$0.50
$0.40$0.80 >272K
--
OpenAI: GPT-5.6 Luna
$0.20$0.40 >272K
$1.20$1.80 >272K
$0.116
$0.02$0.04 >272K
-1M
OpenAI: GPT-5.6 Luna Pro
$0.20$0.40 >272K
$1.20$1.80 >272K
$0.116
$0.02$0.04 >272K
-1M
OpenAI: GPT-5.6 Sol
$4.00$8.00 >272K
$20.00$30.00 >272K
$0.50
$0.40$0.80 >272K
-1M
OpenAI: GPT-5.6 Sol Pro
$4.00$8.00 >272K
$20.00$30.00 >272K
$0.50
$0.40$0.80 >272K
-1M
OpenAI: GPT-5.6 Terra
$2.00$4.00 >272K
$12.00$18.00 >272K
$0.44
$0.20$0.40 >272K
-1M
OpenAI: GPT-5.6 Terra Pro
$2.00$4.00 >272K
$12.00$18.00 >272K
$0.44
$0.20$0.40 >272K
-1M
OpenAI: GPT-6 Astra
$10.00$20.00 >272K
$50.00$75.00 >272K
$0.50
$1.00$2.00 >272K
-1M
OpenAI: GPT-6 Astra Pro
$10.00$20.00 >272K
$50.00$75.00 >272K
$0.50
$1.00$2.00 >272K
-1M
OpenAI: GPT-6 Luna
$0.10$0.20 >272K
$0.50$0.75 >272K
$0.10
$0.01$0.02 >272K
-1M
OpenAI: GPT-6 Luna Pro
$0.10$0.20 >272K
$0.50$0.75 >272K
$0.10
$0.01$0.02 >272K
-1M
OpenAI: GPT-6 Sol
$2.00$4.00 >272K
$10.00$15.00 >272K
$0.38
$0.20$0.40 >272K
-1M
OpenAI: GPT-6 Sol Pro
$2.00$4.00 >272K
$10.00$15.00 >272K
$0.38
$0.20$0.40 >272K
-1M
OpenAI: GPT-6.1 Sol
$2.00$4.00 >272K
$10.00$15.00 >272K
$0.38
$0.10$0.20 >272K
-1M
OpenAI: GPT-6.1 Sol Pro
$2.00$4.00 >272K
$10.00$15.00 >272K
$0.38
$0.10$0.20 >272K
-1M
OpenAI: GPT-6.1 Terra
$1.00$2.00 >272K
$5.00$7.50 >272K
$0.23
$0.05$0.10 >272K
-1M
OpenAI: GPT-6.1 Terra Pro
$1.00$2.00 >272K
$5.00$7.50 >272K
$0.23
$0.05$0.10 >272K
-1M
OpenAI: GPT-6.2 Astra
$8.00$16.00 >272K
$40.00$60.00 >272K
$0.50
$0.40$0.80 >272K
-1M
OpenAI: GPT-6.2 Astra Pro
$8.00$16.00 >272K
$40.00$60.00 >272K
$0.50
$0.40$0.80 >272K
-1M
OpenAI: GPT-6.2 Sol
$2.00$4.00 >272K
$10.00$15.00 >272K
$0.38
$0.10$0.20 >272K
-1M
OpenAI: GPT-6.2 Sol Pro
$2.00$4.00 >272K
$10.00$15.00 >272K
$0.38
$0.10$0.20 >272K
-1M
OpenAI: GPT Audio
$2.50$10.00$0.28--128K
OpenAI: GPT Audio Mini
$0.60$2.40$0.128--128K
OpenAI: GPT Chat Latest
$5.00$30.00$0.50$0.50-400K
OpenAI: gpt-image-1
$5.00$40.00$0.50$1.25--
OpenAI: gpt-image-1-miniShuts down 
$2.00$8.00$0.24$0.20--
OpenAI: gpt-image-1.5Shuts down 
$5.00$32.00$0.50$1.25--
OpenAI: gpt-image-2Shuts down 
$5.00$30.00$0.50$1.25--
OpenAI: gpt-image-2.5-flare
$5.00$30.00$0.50$1.25--
OpenAI: gpt-image-2.5-sunburst
$5.00$30.00$0.50$1.25--
OpenAI: gpt-oss-120b
$0.09$0.36$0.10--131K
OpenAI: gpt-oss-20b
$0.075$0.30$0.10$0.0375-131K
OpenAI: gpt-oss-safeguard-20b
$0.075$0.30$0.10$0.0375-131K
OpenAI: o1
$15.00$60.00$0.50$7.50--
OpenAI: o1-mini
$1.10$4.40$0.168$0.55--
OpenAI: o1-pro
$150.00$600.00$0.50---
OpenAI: o3
$2.00$8.00$0.24$0.50-200K
OpenAI: o3-deep-research
$10.00$40.00$0.50$2.50--
OpenAI: o3-mini
$1.10$4.40$0.168$0.55--
OpenAI: o3 Pro
$20.00$80.00$0.50--200K
OpenAI: o4-mini
$1.10$4.40$0.168$0.275--
OpenAI: o4-mini-deep-research
$2.00$8.00$0.24$0.50--

Google(36 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Google: gemini-2.0-flash
$0.10$0.40$0.10$0.025--
Google: gemini-2.0-flash-lite
$0.075$0.30$0.10---
Google: Gemini 2.5 Flash
$0.30$2.50$0.13$0.03$2.501M
Google: Nano Banana (Gemini 2.5 Flash Image)
$0.30$30.00$0.50$0.03$2.5033K
Google: Gemini 2.5 Flash Lite
$0.10$0.40$0.10$0.01$0.401M
Google: Gemini 2.5 Pro
$1.25$2.50 >200K
$10.00$15.00 >200K
$0.38
$0.125$0.25 >200K
$10.001M
Google: Gemini 2.5 Pro Preview 06-05
$1.25$2.50 >200K
$10.00$15.00 >200K
$0.38
$0.125$0.25 >200K
$10.001M
Google: Gemini 3 Flash Preview
$0.50$3.00$0.14$0.05$3.001M
Google: Nano Banana Pro (Gemini 3 Pro Image)
$2.00$120.00$0.50$0.20$12.00131K
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)
$2.00$12.00$0.32$0.20$12.0066K
Google: Nano Banana 2 (Gemini 3.1 Flash Image)
$0.50$60.00$0.50--131K
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
$0.50$3.00$0.14--66K
Google: Gemini 3.1 Flash Lite
$0.25$1.50$0.11$0.025$1.501M
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
$0.25$30.00$0.50--66K
Google: Gemini 3.1 Flash Lite Preview
$0.25$1.50$0.11$0.025$1.501M
Google: Gemini 3.1 Pro Preview
$2.00$4.00 >200K
$12.00$18.00 >200K
$0.44
$0.20$0.40 >200K
$12.001M
Google: Gemini 3.1 Pro Preview Custom Tools
$2.00$4.00 >200K
$12.00$18.00 >200K
$0.44
$0.20$0.40 >200K
$12.001M
Google: Gemini 3.5 Flash
$1.50$9.00$0.26$0.15$9.001M
Google: Gemini 3.5 Flash Lite
$0.30$2.50$0.13$0.03$2.501M
Google: Gemini 3.6 Flash
$1.50$7.50$0.23$0.15$3.751M
Google: Gemini 3.7 Flash
$1.50$7.50$0.23$0.15$3.751M
Google: Gemini 3.8 Flash
$1.50$7.50$0.23$0.15$4.131M
Google: Gemini 4 Argon
$4.00$20.00$0.48$0.20$10.001M
Google: Gemini 4 Carbon
$4.00$20.00$0.48$0.20$10.001M
Google: Gemini 4 Hydrogen
$1.50$7.50$0.23$0.075$7.501M
Google: Gemini 4 Neon
$3.00$15.00$0.38$0.15$15.001M
Google: Nano Banana 2.1
$1.50$7.50$0.23--66K
Google: Gemini Omni 1.1 Flash
$1.50$17.50$0.43--131K
Google: Gemini Omni 1.2 Flash
$1.50$9.00$0.26--131K
Google: Gemma 2 27B
$0.65$0.65$0.10--8K
Google: Gemma 3 12B
$0.05$0.15$0.10--131K
Google: Gemma 3 27B
$0.08$0.45$0.10$0.04-131K
Google: Gemma 3 4B
$0.04$0.05$0.10$0.02-131K
Google: Gemma 4 26B A4B
$0.0675$0.225$0.10$0.0375-262K
Google: Gemma 4 31B
$0.20$0.40$0.10--262K
Google: imagen-4.0-generate-001
$0.04$0.04$0.10---

Octavius(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Octavius: Octo-1
$0.15$0.80$0.10$0.03-1M

aion-labs(6 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
AionLabs: Aion-2.0
$0.80$1.60$0.112$0.20-131K
AionLabs: Aion-3.0
$3.00$6.00$0.20$0.75-131K
AionLabs: Aion-3.0-Mini
$0.70$1.40$0.108$0.18-131K
AionLabs: Aion 3.5
$3.00$6.00$0.20$0.75-262K
AionLabs: Aion 3.5 Mini
$0.70$1.40$0.108$0.18-262K
AionLabs: Aion-RP 1.0 (8B)
$0.80$1.60$0.112--33K

Amazon(5 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Amazon: Nova 2 Lite
$0.30$2.50$0.13--1M
Amazon: Nova Lite 1.0
$0.06$0.24$0.10--300K
Amazon: Nova Micro 1.0
$0.035$0.14$0.10--128K
Amazon: Nova Premier 1.0
$2.50$12.50$0.33$0.625-1M
Amazon: Nova Pro 1.0
$0.80$3.20$0.144--300K

anthracite-org(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
anthracite-org: Magnum v4 72B
$2.50$5.00$0.18$2.50-33K

baidu(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Baidu: ERNIE-Light-DT-1.0
$1.13$3.94$0.159$0.113-1M

bytedance(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
ByteDance: UI-TARS 7B
$0.10$0.20$0.10$0.10-128K

bytedance-seed(3 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
ByteDance Seed: Seed 2.1 Turbo
$0.50$2.50$0.13--262K
ByteDance Seed: Seed-2.0-Lite
$0.25$0.50 >128K
$2.00$4.00 >128K
$0.16--262K
ByteDance Seed: Seed-2.0-Mini
$0.10$0.20 >128K
$0.40$0.80 >128K
$0.10--262K

cognitivecomputations(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Venice: Uncensored
$0.20$0.90$0.10--128K

Cohere(5 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Cohere: Command A
$2.50$10.00$0.28--256K
Cohere: Command A+
$0.30$1.50$0.11$0.15-192K
Cohere: Command R (08-2024)
$0.15$0.60$0.10--128K
Cohere: Command R+ (08-2024)
$2.50$10.00$0.28--128K
Cohere: Command R7B (12-2024)
$0.0375$0.15$0.10--128K

DeepSeek(14 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
DeepSeek: DeepSeek V3
$0.2574$1.03$0.101--164K
DeepSeek: DeepSeek V3 0324
$0.25$1.00$0.10--164K
DeepSeek: DeepSeek V3.1
$0.25$0.95$0.10$0.13-164K
DeepSeek: R1 0528
$0.571$2.29$0.126--164K
DeepSeek: DeepSeek V3.1 Terminus
$0.27$1.00$0.10--164K
DeepSeek: DeepSeek V3.2
$0.26$0.38$0.10$0.13-164K
DeepSeek: DeepSeek V3.2 Exp
$0.27$0.41$0.10--164K
DeepSeek: DeepSeek V4 Flash 0423
$0.09$0.18$0.10$0.018-1M
DeepSeek: DeepSeek V4 Flash 0731
$0.0443$0.30$0.10$0.035-1M
DeepSeek: DeepSeek V4 Flash Vision Exp
$0.2156$0.6468$0.10$0.0069-1M
DeepSeek: DeepSeek V4 Pro 0423
$0.90$1.50$0.11$0.20-1M
DeepSeek: DeepSeek V4 Pro 0813
$1.32$3.96$0.159$0.044-1M
DeepSeek: DeepSeek V4.1 Flash
$0.0498$0.1992$0.10$0.001-1M
DeepSeek: DeepSeek V4.1 Flash 1017
$0.30$1.20$0.104$0.006-1M

elorian(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Elorian: Glimpse
$0.60$3.00$0.14$0.06-262K

fireworks(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Fireworks: Ember-1
$3.00$15.00$0.38$0.30-1M

gryphe(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
gryphe: MythoMax 13B
$0.30$0.50$0.10$0.20-8K

ibm-granite(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
IBM: Granite 4.2 8B
$0.06$0.15$0.10$0.015-131K

inclusionai(4 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
inclusionAI: Ling 3.0 Flash
$0.021$0.063$0.10$0.0042-262K
inclusionAI: Ling 3.0 Flash VL
$0.06$0.18$0.10$0.012-131K
inclusionAI: Ling 3.0 Tiny
$0.015$0.045$0.10$0.003-262K
inclusionAI: Ling 3.1 Flash
$0.06$0.18$0.10$0.012-1M

inference-net(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Inference.net: Schematron V2 Small
$0.05$0.23$0.10$0.05-128K
Inference.net: Schematron V2 Turbo
$0.03$0.15$0.10$0.03-128K

kt(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
KT: Mi:dm K 3.0 Pro
$0.20$0.80$0.10$0.04-262K

liquid(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
LiquidAI: LFM2.5-24B-A2B
$0.05$0.70$0.10$0.025-128K
LiquidAI: LFM3-1.7B
$0.08$0.20$0.10$0.02-262K

mancer(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Mancer: Weaver (alpha)
$0.30$0.50$0.10$0.30-8K

Meta(9 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Meta: Muse Ember
$0.10$0.50$0.10$0.004-1M
Meta: Muse Glimmer 30B
$0.35$1.50$0.11$0.04-131K
Meta: Muse Spark 1.1
$1.25$4.25$0.165$0.15-1M
Meta: Muse Spark 1.2
$1.25$4.25$0.165$0.15-1M
Meta: Muse Spark 1.2 Contributor
$0.10$0.20$0.10$0.002-1M
Meta: Muse Spark 1.3
$1.25$4.25$0.165$0.15-1M
Meta: Muse Spark 1.3 Contributor
$0.10$0.20$0.10$0.002-1M
Meta: Muse Spark Open
$1.25$4.25$0.165$0.15-1M
Meta: Muse Wonder
$4.00$20.00$0.48$0.20-1M

Meta(7 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Meta: Llama 3.1 70B Instruct
$0.72$0.72$0.10--131K
Meta: Llama 3.1 8B Instruct
$0.02$0.04$0.10--131K
Meta: Llama 3.2 3B Instruct
$0.05$0.33$0.10--131K
Meta: Llama 3.3 70B Instruct
$0.71$0.71$0.10$0.71-131K
Meta: Llama 4 Maverick
$0.35$1.00$0.10$0.17-524K
Meta: Llama 4 Scout
$0.10$0.30$0.10--1M
Meta: Llama Guard 4 12B
$0.18$0.18$0.10--164K

microsoft(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Microsoft: Phi 4
$0.07$0.14$0.10--16K

MiniMax(4 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
MiniMax: MiniMax M2.5
$0.27$0.95$0.10$0.03-198K
MiniMax: MiniMax M2.7
$0.60$1.80$0.116--197K
MiniMax: MiniMax M3
$0.30$1.20$0.104$0.06-1M
MiniMax: MiniMax M3.1 Flash
$0.15$0.60$0.10$0.015-1M

Mistral(21 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Mistral: Codestral 2508
$0.30$0.90$0.10$0.03-256K
Mistral: Devstral 2 2512
$0.40$2.00$0.12$0.04-262K
Mistral: Ministral 3 14B 2512
$0.20$0.20$0.10$0.02-262K
Mistral: Ministral 3 3B 2512
$0.10$0.10$0.10$0.01-131K
Mistral: Ministral 3 8B 2512
$0.15$0.15$0.10$0.015-262K
Mistral: Mistral Large
$2.00$6.00$0.20$0.20-128K
Mistral: Mistral Large 2407
$2.00$6.00$0.20$0.20-131K
Mistral: Mistral Large 3 2512
$0.50$1.50$0.11$0.05-262K
Mistral: Mistral Large 4
$0.70$2.10$0.122$0.07-1M
Mistral: Mistral Medium 3
$0.44$2.20$0.124$0.044-131K
Mistral: Mistral Medium 3.5
$1.50$7.50$0.23--262K
Mistral: Mistral Medium 3.1
$0.44$2.20$0.124$0.044-131K
Mistral: Mistral Nemo
$0.15$0.15$0.10$0.015-131K
Mistral: Saba
$0.20$0.60$0.10$0.02-33K
Mistral: Mistral Small 3
$0.05$0.08$0.10--33K
Mistral: Mistral Small 4
$0.15$0.60$0.10$0.015-262K
Mistral: Mistral Small 3.1 24B
$0.351$0.555$0.10--128K
Mistral: Mistral Small 3.2 24B
$0.075$0.20$0.10--256K
Mistral: Mixtral 8x22B Instruct
$2.00$6.00$0.20$0.20-66K
Mistral: Pixtral Large 2502
$2.00$6.00$0.20--128K
Mistral: Voxtral Small 24B 2507
$0.10$0.30$0.10$0.01-33K

moondream(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Moondream: Moondream 3 Preview
$0.30$2.50$0.13--32K
Moondream: Moondream 3.1
$0.30$2.50$0.13--32K

Moonshot(8 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
MoonshotAI: Kimi K2 0711
$0.57$2.30$0.126--131K
MoonshotAI: Kimi K2 0905
$0.60$2.50$0.13--262K
MoonshotAI: Kimi K2 Thinking
$0.60$2.50$0.13$0.15-262K
MoonshotAI: Kimi K2.5
$0.50$2.50$0.13$0.15-262K
MoonshotAI: Kimi K2.6
$0.95$4.00$0.16$0.16-262K
MoonshotAI: Kimi K2.7 Code
$0.95$4.00$0.16$0.19-262K
MoonshotAI: Kimi K3
$3.00$15.00$0.38$0.30-1M
MoonshotAI: Kimi K3.1 Pro
$2.00$10.00$0.28$0.20-1M

morph(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Morph: Morph V3 Fast
$0.80$1.20$0.104--262K
Morph: Morph V3 Large
$0.90$1.90$0.118--262K

motif-technologies(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Motif Technologies: Motif 3
$0.30$1.20$0.104$0.06-262K

nex-agi(3 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Nex AGI: Nex-N2.5-Mini
$0.025$0.10$0.10$0.0025-262K
Nex AGI: Nex-N2.5-Pro
$0.075$0.25$0.10$0.015-262K
Nex AGI: Nex-N2.6
$0.12$0.40$0.10$0.024-262K

nousresearch(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Nous: Hermes 4 405B
$1.00$3.00$0.14$0.20-131K

NVIDIA(6 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
NVIDIA: Nemotron 3 Nano 30B A3B
$0.06$0.24$0.10$0.012-262K
NVIDIA: Nemotron 3 Super
$0.075$0.40$0.10--262K
NVIDIA: Nemotron 3 Ultra
$0.50$2.20$0.124$0.10-262K
NVIDIA: Nemotron 3.5 Content Safety
$0.20$0.20$0.10--131K
NVIDIA: Nemotron 3.5 Lightning
$0.07$0.20$0.10$0.04-1M
NVIDIA: Nemotron 3.5 Super VL
$0.15$0.47$0.10$0.02-1M

OpenRouter(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
OpenRouter: Auto Router
Varies - billed the reported cost of the model it picks2M

particle-ai(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Particle AI: Particle-1
$0.07$0.50$0.10$0.03-1M

perceptron(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Perceptron: Perceptron Mk1
$0.15$1.50$0.11--33K
Perceptron: Perceptron Mk1.5
$0.15$1.50$0.11--37K

perplexity(5 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Perplexity: Sonar
$1.00$1.00$0.10--127K
Perplexity: Sonar Deep Research
$2.00$8.00$0.24-$3.00128K
Perplexity: Sonar Pro
$3.00$15.00$0.38--200K
Perplexity: Sonar Pro Search
$3.00$15.00$0.38--200K
Perplexity: Sonar Reasoning Pro
$2.00$8.00$0.24--128K

prism-ml(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
PrismML: Ternary Bonsai 2 27B
$0.075$0.50$0.10$0.0375-262K
PrismML: Ternary Bonsai 2 9B
$0.08$0.13$0.10$0.04-262K

Qwen(40 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Qwen: Qwen2.5 72B Instruct
$0.36$0.40$0.10--33K
Qwen: Qwen2.5 Coder 32B Instruct
$0.66$1.00$0.10--33K
Qwen: Qwen-Plus
$0.26$0.78 >256K
$0.78$2.34 >256K
$0.127
$0.052$0.156 >256K
-1M
Qwen: Qwen2.5 VL 72B Instruct
$0.80$1.00$0.10$0.40-128K
Qwen: Qwen3 14B
$0.12$0.24$0.10--41K
Qwen: Qwen3 235B A22B Instruct 2507
$0.14$0.80$0.10$0.05-262K
Qwen: Qwen3 235B A22B Thinking 2507
$0.45$3.50$0.15--128K
Qwen: Qwen3 30B A3B
$0.12$0.50$0.10--41K
Qwen: Qwen3 30B A3B Instruct 2507
$0.10$0.30$0.10$0.10-262K
Qwen: Qwen3 32B
$0.08$0.28$0.10--131K
Qwen: Qwen3 Coder 480B A35B
$0.30$1.00$0.10$0.10-262K
Qwen: Qwen3 Coder 30B A3B Instruct
$0.07$0.28$0.10--262K
Qwen: Qwen3 Coder Flash
$0.195$0.325 >32K$0.52 >128K
$0.975$1.63 >32K$2.60 >128K
$0.132
$0.039$0.065 >32K$0.104 >128K
-1M
Qwen: Qwen3 Coder Next
$0.12$0.80$0.10$0.07-262K
Qwen: Qwen3 Next 80B A3B Instruct
$0.10$1.10$0.102$0.07-262K
Qwen: Qwen3 VL 235B A22B Instruct
$0.21$1.90$0.118$0.10-262K
Qwen: Qwen3 VL 30B A3B Instruct
$0.15$0.60$0.10--262K
Qwen: Qwen3 VL 8B Instruct
$0.25$0.75$0.10$0.12-262K
Qwen: Qwen3.5-122B-A10B
$0.26$2.08$0.122--262K
Qwen: Qwen3.5-27B
$0.195$1.56$0.111--262K
Qwen: Qwen3.5-35B-A3B
$0.1625$1.30$0.106$0.05-262K
Qwen: Qwen3.5 397B A17B
$0.39$2.34$0.127$0.22-262K
Qwen: Qwen3.5-9B
$0.17$0.25$0.10--262K
Qwen: Qwen3.5-Flash
$0.065$0.26$0.10--1M
Qwen: Qwen3.5 Plus 2026-02-15
$0.26$0.325 >256K
$1.56$1.95 >256K
$0.119--1M
Qwen: Qwen3.5 Plus 2026-04-20
$0.30$0.375 >256K
$1.80$2.25 >256K
$0.125--1M
Qwen: Qwen3.6 27B
$0.45$2.70$0.134--262K
Qwen: Qwen3.6 35B A3B
$0.10$0.90$0.10$0.025-262K
Qwen: Qwen3.6 Flash
$0.1875$0.75 >256K
$1.13$3.00 >256K
$0.14--1M
Qwen: Qwen3.6 Plus
$0.325$1.30 >256K
$1.95$3.90 >256K
$0.158--1M
Qwen: Qwen3.7 Flash
$0.03$0.10 >32K$0.20 >256K
$0.13$0.40 >32K$0.80 >256K
$0.10
$0.006$0.02 >32K$0.04 >256K
-1M
Qwen: Qwen3.7 Max
$1.48$4.42$0.169$0.295-1M
Qwen: Qwen3.7 Plus
$0.32$0.96 >256K
$1.28$3.84 >256K
$0.157
$0.064$0.192 >256K
-1M
Qwen: Qwen3.8 2.4T A95B
$2.00$6.00$0.20$0.25-1M
Qwen: Qwen3.8 27B
$0.425$2.55$0.131$0.085-1M
Qwen: Qwen3.8 Flash
$0.15$0.47$0.10$0.016-1M
Qwen: Qwen3.8 Max (0902)
$2.00$6.00$0.20$0.25-1M
Qwen: Qwen3.8 Max Prime
$4.00$12.00$0.32$0.50-1M
Qwen: Qwen3.8 Omni Flash
$0.15$0.47$0.10$0.016-1M
Qwen: Qwen4 Max
$1.50$4.50$0.17$0.075-1M

radixark(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
RadixArk: DaisyRose 27B
$0.15$1.88$0.118$0.0375-262K

reflection(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Reflection: Beam 1.0 501B A23B
$0.25$1.00$0.10$0.05-1M

rekaai(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
rekaai: Reka Edge
$0.10$0.10$0.10--16K
rekaai: Reka Flash 3
$0.10$0.20$0.10--66K

relace(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Relace: Relace Apply 3
$0.85$1.25$0.105--256K
Relace: Relace Search
$1.00$3.00$0.14--256K

ricursiveai(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Ricursive: Ripple 65B Preview
$0.10$0.30$0.10$0.025-1M

sakana(4 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Sakana: Fugu Max
$2.00$6.00$0.20$0.25-1M
Sakana: Fugu Ultra
$5.00$10.00 >272K
$30.00$45.00 >272K
$0.50
$0.50$1.00 >272K
-1M
Sakana: Fugu Ultra v2
$5.00$10.00 >272K
$30.00$45.00 >272K
$0.50
$0.50$1.00 >272K
-1M
Sakana: Sakana Namazu
$0.95$4.00$0.16$0.15-262K

sao10k(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Sao10K: Llama 3 8B Lunaris
$0.04$0.05$0.10--8K
Sao10K: Llama 3.1 Euryale 70B v2.2
$0.85$0.85$0.10--131K

scaledown(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
ScaleDown: Extract
$0.04Free$0.10--1M
ScaleDown: Summarize
$0.04Free$0.10--1M

stepfun(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
StepFun: Step 3.7 Flash
$0.20$1.15$0.103$0.04-262K
StepFun: Step 5 Preview
$1.00$2.70$0.134$0.10-1M

tencent(7 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Tencent: Hy-MT2-1.8B
$0.044$0.177$0.10--8K
Tencent: Hy-MT2-30B-A3B
$0.074$0.295$0.10--8K
Tencent: Hy-MT2-7B
$0.074$0.295$0.10--8K
Tencent: Hy3
$0.14$0.58$0.10$0.035-262K
Tencent: Hy4
$0.417$1.25$0.105$0.021-1M
Tencent: Hy4 flash
$0.035$0.1405$0.10$0.0015-1M
Tencent: Hy4 preview
$0.834$2.50$0.13$0.042-1M

thedrummer(3 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
TheDrummer: Cydonia 24B V4.1
$0.30$0.50$0.10$0.15-131K
TheDrummer: Skyfall 36B V2
$0.55$0.80$0.10$0.25-33K
TheDrummer: UnslopNemo 12B
$0.40$0.40$0.10--1M

thinkingmachines(4 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Thinking Machines: Inkling
$1.00$4.05$0.161$0.17-524K
Thinking Machines: Inkling 2 Mini
$0.075$0.30$0.10$0.015-1M
Thinking Machines: Inkling 2 Small
$0.30$1.00$0.10$0.03-1M
Thinking Machines: Inkling Small
$0.45$1.20$0.104$0.10-524K

TypeSafe(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
TypeSafe: Jev Router
Varies - billed the reported cost of the model it picks1M

unbiased(3 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
unbiased: Pareto 26.10
$0.80$3.20$0.144$0.03-1M
unbiased: Pareto 26.10 Preview
$0.80$3.20$0.144$0.03-1M
unbiased: Pareto 26.9
$2.50$7.50$0.23$0.25-262K

undi95(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
undi95: ReMM SLERP 13B
$0.30$0.50$0.10$0.20-6K

upstage(2 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Upstage: Solar Mini 4
$0.05$0.20$0.10$0.005-524K
Upstage: Solar Pro 4
$0.15$0.60$0.10$0.03-524K

writer(1 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Writer: Palmyra X5
$0.60$6.00$0.20--1M

SpaceXAI(6 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
SpaceXSI: Grok 4.20
$1.25$2.50 >200K
$2.50$5.00 >200K
$0.18
$0.20$0.40 >200K
-2M
SpaceXSI: Grok 4.20 Multi-Agent
$1.25$2.50 >200K
$2.50$5.00 >200K
$0.18
$0.20$0.40 >200K
-2M
SpaceXSI: Grok 4.3
$1.25$2.50 >200K
$2.50$5.00 >200K
$0.18
$0.20$0.40 >200K
-1M
SpaceXSI: Grok 4.5
$2.00$4.00 >200K
$6.00$12.00 >200K
$0.32
$0.30$0.60 >200K
-500K
SpaceXSI: Grok 4.6
$2.00$4.00 >200K
$6.00$12.00 >200K
$0.32
$0.50$1.00 >200K
-500K
SpaceXSI: Grok 4.7
$2.00$4.00 >200K
$6.00$12.00 >200K
$0.32
$0.50$1.00 >200K
-500K

xiaomi(5 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Xiaomi: MiMo-V2.5
$0.40$2.00$0.12$0.08-1M
Xiaomi: MiMo-V2.5-Pro
$0.48$1.80$0.116$0.096-262K
Xiaomi: MiMo-V2.6-Flash
$0.14$0.28$0.10$0.0028-1M
Xiaomi: MiMo-V2.6-Pro
$0.435$0.87$0.10$0.0036-1M
Xiaomi: MiMo-V2.6-Pro-UltraSpeed
$4.35$8.70$0.254$0.036-1M

Z.ai(17 models)

ModelInput / 1M tokensOutput / 1M tokensBandwidth / 1MCache Read / 1MReasoning / 1MContext
Z.ai: GLM 4.5
$0.60$2.20$0.124$0.11-131K
Z.ai: GLM 4.5 Air
$0.20$1.10$0.102$0.03-131K
Z.ai: GLM 4.5V
$0.60$1.80$0.116$0.11-66K
Z.ai: GLM 4.6
$0.60$2.20$0.124$0.11-205K
Z.ai: GLM 4.6V
$0.30$0.90$0.10$0.05-131K
Z.ai: GLM 4.7
$0.60$2.20$0.124$0.11-205K
Z.ai: GLM 4.7 Flash
$0.0605$0.40$0.10--200K
Z.ai: GLM 5
$1.00$3.20$0.144$0.20-205K
Z.ai: GLM 5 Turbo
$1.20$4.00$0.16$0.24-203K
Z.ai: GLM 5.1
$1.40$4.40$0.168$0.26-205K
Z.ai: GLM 5.2
$1.40$4.40$0.168$0.26-1M
Z.ai: GLM 5.3
$1.40$4.40$0.168$0.26-1M
Z.ai: GLM 5.3 Flash
$0.15$0.50$0.10$0.03-1M
Z.ai: GLM 5.3 FlashX
$0.37$1.25$0.105$0.075-1M
Z.ai: GLM 5.3 FlashX Legal
$0.37$1.25$0.105$0.075-1M
Z.ai: GLM 5.3 Prime
$1.68$5.28$0.186$0.336-1M
Z.ai: GLM 5V Turbo
$1.20$4.00$0.16$0.24-203K