AI Model API Prices on OpenRouter
We record the input and output prices per million tokens of 476 AI models from 60 providers as OpenRouter lists them. These are listed prices, not a billing test, and model quality is not rated. Prices as shown in the United States on .
Models by provider
Providers with at least 5 tracked models have their own page listing every model; models of the other providers are listed below the table.
Models of providers with fewer than 5 tracked models (74)
| Provider | Model | Input per 1M tokens | Output per 1M tokens | Context (tokens) | Listed since |
|---|---|---|---|---|---|
| scaledown | ScaleDown: Extract | $0.04 | $0.00 | 1,000,000 | 13 Oct 2026 |
| scaledown | ScaleDown: Summarize | $0.04 | $0.00 | 1,000,000 | 13 Oct 2026 |
| inclusionai | inclusionAI: Ling 3.0 Tiny | $0.02 | $0.05 | 262,144 | 6 Aug 2026 |
| sao10k | Sao10K: Llama 3 8B Lunaris | $0.04 | $0.05 | 8,192 | 13 Aug 2024 |
| inclusionai | inclusionAI: Ling 3.0 Flash | $0.02 | $0.06 | 262,144 | 23 Jul 2026 |
| nex-agi | Nex AGI: Nex-N2.5-Mini | $0.03 | $0.10 | 262,144 | 8 Sep 2026 |
| rekaai | Reka Edge | $0.10 | $0.10 | 16,384 | 20 Mar 2026 |
| gryphe | MythoMax 13B | $0.08 | $0.11 | 8,192 | 2 Jul 2023 |
| prism-ml | PrismML: Ternary Bonsai 2 9B | $0.08 | $0.13 | 262,144 | 16 Oct 2026 |
| inclusionai | inclusionAI: Ling 3.1 Flash | $0.05 | $0.14 | 1,000,000 | 2 Oct 2026 |
| microsoft | Microsoft: Phi 4 | $0.07 | $0.14 | 16,384 | 10 Jan 2025 |
| inference-net | Inference.net: Schematron V2 Turbo | $0.03 | $0.15 | 128,000 | 12 Sep 2026 |
| inception | Inception: Mercury 2.5 | $0.04 | $0.15 | 260,000 | 8 Sep 2026 |
| inclusionai | inclusionAI: Ling 3.0 Flash VL | $0.06 | $0.18 | 131,072 | 10 Sep 2026 |
| upstage | Upstage: Solar Mini 4 | $0.05 | $0.20 | 524,288 | 23 Sep 2026 |
| bytedance | ByteDance: UI-TARS 7B | $0.10 | $0.20 | 128,000 | 22 Jul 2025 |
| rekaai | Reka Flash 3 | $0.10 | $0.20 | 65,536 | 12 Mar 2025 |
| inference-net | Inference.net: Schematron V2 Small | $0.05 | $0.23 | 128,000 | 12 Sep 2026 |
| ibm-granite | IBM: Granite 4.2 8B | $0.06 | $0.25 | 131,072 | 31 Aug 2026 |
| nex-agi | Nex AGI: Nex-N2.5-Pro | $0.08 | $0.25 | 262,144 | 8 Sep 2026 |
| stepfun | StepFun: Step 3.5 Flash | $0.10 | $0.30 | 262,144 | 29 Jan 2026 |
| inception | Inception: Mercury 3 | $0.10 | $0.35 | 1,000,000 | 16 Oct 2026 |
| thedrummer | TheDrummer: UnslopNemo 12B | $0.40 | $0.40 | 1,024,000 | 8 Nov 2024 |
| particle-ai | Particle AI: Particle-1 | $0.05 | $0.50 | 1,048,576 | 28 Oct 2026 |
| prism-ml | PrismML: Ternary Bonsai 2 27B | $0.08 | $0.50 | 262,144 | 18 Sep 2026 |
| thedrummer | TheDrummer: Cydonia 24B V4.1 | $0.30 | $0.50 | 131,072 | 27 Sep 2025 |
| upstage | Upstage: Solar Pro 4 | $0.15 | $0.60 | 524,288 | 10 Aug 2026 |
| ricursiveai | Ricursive: Ripple 65B Preview | $0.20 | $0.60 | 1,048,576 | 4 Nov 2026 |
| undi95 | ReMM SLERP 13B | $0.35 | $0.65 | 6,144 | 22 Jul 2023 |
| inception | Inception: Mercury 2 | $0.25 | $0.75 | 128,000 | 4 Mar 2026 |
| mancer | Mancer: Weaver (alpha) | $0.40 | $0.75 | 8,000 | 2 Aug 2023 |
| thedrummer | TheDrummer: Skyfall 36B V2 | $0.55 | $0.80 | 32,768 | 10 Mar 2025 |
| sao10k | Sao10K: Llama 3.1 Euryale 70B v2.2 | $0.85 | $0.85 | 131,072 | 28 Aug 2024 |
| cognitivecomputations | Venice: Uncensored | $0.20 | $0.90 | 128,000 | 9 Jul 2025 |
| reflection | Reflection: Beam 1.0 501B A23B | $0.30 | $1.00 | 1,048,576 | 16 Oct 2026 |
| stepfun | StepFun: Step 3.7 Flash | $0.20 | $1.15 | 262,144 | 28 May 2026 |
| meituan | Meituan: LongCat 2.0 | $0.30 | $1.20 | 1,048,756 | 20 Jul 2026 |
| morph | Morph: Morph V3 Fast | $0.80 | $1.20 | 262,144 | 7 Jul 2025 |
| relace | Relace: Relace Apply 3 | $0.85 | $1.25 | 256,000 | 26 Sep 2025 |
| perceptron | Perceptron: Perceptron Mk1 | $0.15 | $1.50 | 32,768 | 12 May 2026 |
| perceptron | Perceptron: Perceptron Mk1.5 | $0.15 | $1.50 | 36,864 | 25 Sep 2026 |
| morph | Morph: Morph V3 Large | $0.90 | $1.90 | 262,144 | 7 Jul 2025 |
| moondream | Moondream: Moondream 3 Preview | $0.30 | $2.50 | 32,000 | 15 Oct 2026 |
| moondream | Moondream: Moondream 3.1 | $0.30 | $2.50 | 32,000 | 15 Oct 2026 |
| stepfun | StepFun: Step 5 Preview | $1.00 | $2.70 | 1,048,576 | 8 Oct 2026 |
| elorian | Elorian: Glimpse | $0.60 | $3.00 | 262,144 | 17 Oct 2026 |
| nousresearch | Nous: Hermes 4 405B | $1.00 | $3.00 | 131,072 | 26 Aug 2025 |
| relace | Relace: Relace Search | $1.00 | $3.00 | 256,000 | 8 Dec 2025 |
| unbiased | Pareto 26.10 | $0.80 | $3.20 | 1,048,576 | 15 Oct 2026 |
| sakana | Sakana: Sakana Namazu | $0.95 | $4.00 | 262,144 | 11 Aug 2026 |
| anthracite-org | Magnum v4 72B | $2.50 | $5.00 | 32,768 | 22 Oct 2024 |
| writer | Writer: Palmyra X5 | $0.60 | $6.00 | 1,040,000 | 21 Jan 2026 |
| sakana | Sakana: Fugu Max | $2.00 | $6.00 | 1,000,000 | 11 Sep 2026 |
| unbiased | Pareto 26.9 | $2.50 | $7.50 | 262,144 | 13 Oct 2026 |
| fireworks | Fireworks: Ember-1 | $3.00 | $15.00 | 1,048,576 | 24 Sep 2026 |
| sakana | Sakana: Fugu Ultra | $5.00 | $30.00 | 1,000,000 | 24 Jun 2026 |
| sakana | Sakana: Fugu Ultra v2 | $5.00 | $30.00 | 1,000,000 | 11 Sep 2026 |
Batch variants (2)
OpenRouter lists these as separate batch variants at a different price; batch requests are not answered right away, so these prices are kept apart from live prices.
| Provider | Model | Input per 1M tokens | Output per 1M tokens | Context (tokens) | Listed since |
|---|---|---|---|---|---|
| morph | Morph: Morph V3 Fast (batch) | $0.40 | $0.60 | 81,920 | 7 Jul 2025 |
| morph | Morph: Morph V3 Large (batch) | $0.45 | $0.95 | 262,144 | 7 Jul 2025 |
Free variants (4)
$0 per token on the latest check. A free variant can be slower, capped or withdrawn, so free variants are listed apart from paid prices.
| Provider | Model | Input per 1M tokens | Output per 1M tokens | Context (tokens) | Listed since |
|---|---|---|---|---|---|
| stealth | Crouton Alpha | $0.00 | $0.00 | 1,048,576 | 3 Nov 2026 |
| dots-studio | Dots Studio: Dots3-Note Preview (free) | $0.00 | $0.00 | 512,000 | 14 Aug 2026 |
| recursive | Recursive: Flint (free) | $0.00 | $0.00 | 262,144 | 21 Oct 2026 |
| xingchen-agi | XingChen: Xing4.0 29B A4B (free) | $0.00 | $0.00 | 262,144 | 16 Oct 2026 |
No longer listed: last listed prices (11)
These models are not on OpenRouter’s current list in our latest checks; each row shows the last price listed, with its date, not a current price.
| Provider | Model | Input per 1M tokens | Output per 1M tokens | Context (tokens) | Listed since |
|---|---|---|---|---|---|
| poolside | Poolside: Laguna S 2.1 (free) (last listed on OpenRouter 31 Oct 2026) | $0.00 | $0.00 | 262,144 | 21 Jul 2026 |
| poolside | Poolside: Laguna XS 2.1 (free) (last listed on OpenRouter 31 Oct 2026) | $0.00 | $0.00 | 262,144 | 2 Jul 2026 |
| ibm-granite | IBM: Granite 4.0 Micro (last listed on OpenRouter 26 Oct 2026) | $0.02 | $0.11 | 131,000 | 20 Oct 2025 |
| poolside | Poolside: Laguna XS 2.1 (last listed on OpenRouter 31 Oct 2026) | $0.06 | $0.12 | 262,144 | 2 Jul 2026 |
| poolside | Poolside: Laguna S 2.1 (last listed on OpenRouter 31 Oct 2026) | $0.09 | $0.18 | 1,048,576 | 21 Jul 2026 |
| upstage | Upstage: Solar Pro 3 (last listed on OpenRouter 29 Oct 2026) | $0.15 | $0.60 | 131,072 | 27 Jan 2026 |
| microsoft | WizardLM-2 8x22B (last listed on OpenRouter 19 Oct 2026) | $0.62 | $0.62 | 65,535 | 16 Apr 2024 |
| nousresearch | Nous: Hermes 3 70B Instruct (last listed on OpenRouter 2 Nov 2026) | $0.70 | $0.70 | 131,072 | 18 Aug 2024 |
| sao10k | Sao10K: Llama 3.3 Euryale 70B (last listed on OpenRouter 19 Oct 2026) | $0.65 | $0.75 | 131,072 | 18 Dec 2024 |
| arcee-ai | Arcee AI: Trinity Large Thinking (last listed on OpenRouter 26 Oct 2026) | $0.25 | $0.80 | 262,144 | 1 Apr 2026 |
| nousresearch | Nous: Hermes 3 405B Instruct (last listed on OpenRouter 2 Nov 2026) | $1.00 | $1.00 | 131,072 | 16 Aug 2024 |
Unknown means no value was recorded at our latest check; it is never shown as zero. Prices in USD as OpenRouter lists them; we do not add taxes.
How these numbers are produced
Each row is one model at one provider in our ai-models section. Prices are the input and output prices per one million tokens from the latest check of that model; the context length is the value read on the same pass. The table is sorted by our latest output price, lowest first; rows without an output price come last, and after them, greyed, rows of providers whose terms restrict independent comparisons (list of these providers).
A provider gets its own page when we track at least 5 of its models.
Each model links to its page with dates, the source link and the full history.
What changed
Listed prices on OpenRouter move often. Confirmed changes in AI model prices, subscription limits and terms are listed day by day on What changed in AI models, prices and terms; every model page keeps its own history.
Measured Lab AI API Price Watch
$1.90 per 1M tokens
Median OpenRouter output price per 1M tokens across paid models listed on the date (free and batch variants excluded). Based on 327 · . Methodology
327 records are in this figure; each has its own page with dates and sources.
Measured Lab AI API Price Watch — major-vendor flagships (direct vendor price)
$4.50 per 1M tokens
Median official direct output price per 1M tokens across flagship models of major vendors. Based on 19 · 9 Nov 2026.
Measured Lab AI API Price Watch — major-vendor flagships (OpenRouter price)
$4.28 per 1M tokens
Median OpenRouter output price per 1M tokens across flagship models of major vendors. Based on 30 · 9 Nov 2026.
More on AI: Subscription limits · Terms tracker · What's new
API prices from the providers’ own lists: cache and long-context prices · cheapest per task · long-context cliff · caching and batch
How to cite this
Measured Lab, “Measured Lab AI API Price Watch”, $1.90 per 1M tokens, based on 327 models, as of 9 Nov 2026; methodology; licence CC BY 4.0.
Measured Lab, “Measured Lab AI API Price Watch — major-vendor flagships (direct vendor price)”, $4.50 per 1M tokens, based on 19 models, as of 9 Nov 2026; methodology; licence CC BY 4.0.
Measured Lab, “Measured Lab AI API Price Watch — major-vendor flagships (OpenRouter price)”, $4.28 per 1M tokens, based on 30 models, as of 9 Nov 2026; methodology; licence CC BY 4.0.
Image, video and speech APIs: prices per image, per second of video and per minute of audio
What typical tasks cost
Per-token prices are hard to compare, so we priced three typical tasks (1,000 chat replies, summarizing 100 documents and a day of coding assistant use) on 15 current models. At the providers' own prices, 1,000 chat replies cost from $0.25 (GPT-6 Luna) to $25.00 (Claude Fable 5.1 and GPT-6 Astra). Calculated LLM API pricing comparison by task
Not building on an API? Ready-made AI tools for writing, speech and images charge per month or per credit instead of per token: AI tool prices and the usage each plan includes.
Model comparisons: two models on the same three tasks, side by side