LLM token prices
Price tables
Answer in brief
What each model on this site costs per 1M tokens on every host that lists it, read on 12 Nov 2026.
Runcrate is first in every table: it is the editor’s choice here, and its price comes from its own live feed.
An API token price is two prices: one per million tokens you send and a higher one per million tokens the model writes. Read both, check whether repeated input is cached at a lower rate, and compare the maker’s rate with the hosts that serve the same model.
What each host charges
DeepSeek V4.1 FlashLowest $0.022Median $0.203Highest $0.30Runcrate $0.147
GLM 5.3Lowest $0.07Median $0.91Highest $1.68Runcrate $0.59
GLM 5.3 FlashLowest $0.04Median $0.14Highest $0.175Runcrate $0.158
Kimi K3Lowest $0.182Median $2.93Highest $3.45Runcrate $2.99
Qwen3.8 27BLowest $0.035Median $0.15Highest $0.99Runcrate $0.158
Lowest, median and highest listed input price per 1M tokens, one price per host, free listings left out, read 12 Nov 2026. The ring marks Runcrate’s live price.
| Model | Input per 1M | Output per 1M | Context | |
|---|---|---|---|---|
| DeepSeek V4.1 Flash on RuncrateOur pickoutput $0.44 per 1M · 1M contextTry Runcrate | $0.147 | $0.44 | 1M | Try Runcrate |
| GLM 5.3 on RuncrateOur pickoutput $2.63 per 1M · 1M contextTry Runcrate | $0.59 | $2.63 | 1M | Try Runcrate |
| GLM 5.3 Flash on RuncrateOur pickoutput $0.525 per 1M · 1M contextTry Runcrate | $0.158 | $0.525 | 1M | Try Runcrate |
| Kimi K3 on RuncrateOur pickoutput $14.96 per 1M · 1M contextTry Runcrate | $2.99 | $14.96 | 1M | Try Runcrate |
| Qwen3.8 27B on RuncrateOur pickoutput $1.97 per 1M · 262K contextTry Runcrate | $0.158 | $1.97 | 262K | Try Runcrate |
DeepSeek V4.1 Flash: other hosts
| Host | Input per 1M | Output per 1M | Context | Read |
|---|---|---|---|---|
| Morphoutput $0.40 per 1M · 1M context | $0.022 | $0.40 | 1M | price read 12 Nov 2026 |
| PrimeIntellectoutput $1.20 per 1M · 1M context | $0.039 | $1.20 | 1M | price read 12 Nov 2026 |
| Waferoutput $0.567 per 1M · 1M context | $0.051 | $0.567 | 1M | price read 12 Nov 2026 |
| OpenInferenceoutput $0.80 per 1M · 1M context | $0.07 | $0.80 | 1M | price read 12 Nov 2026 |
| InferenceNetoutput $0.60 per 1M · 1M context | $0.103 | $0.60 | 1M | price read 12 Nov 2026 |
| DeepInfraoutput $0.336 per 1M · 1M context | $0.112 | $0.336 | 1M | price read 12 Nov 2026 |
| Rekaoutput $0.64 per 1M · 1M context | $0.12 | $0.64 | 1M | price read 12 Nov 2026 |
| Relaceoutput $0.50 per 1M · 1M context | $0.12 | $0.50 | 1M | price read 12 Nov 2026 |
| CoreWeaveoutput $0.65 per 1M · 1M context | $0.13 | $0.65 | 1M | price read 12 Nov 2026 |
| AtlasCloudoutput $0.54 per 1M · 1M context | $0.135 | $0.54 | 1M | price read 12 Nov 2026 |
| StreamLakeoutput $0.59 per 1M · 1M context | $0.147 | $0.59 | 1M | price read 12 Nov 2026 |
| GMICloudoutput $0.72 per 1M · 1M context | $0.18 | $0.72 | 1M | price read 12 Nov 2026 |
| Cohereoutput $0.66 per 1M · 1M context | $0.195 | $0.66 | 1M | price read 12 Nov 2026 |
| Novitaoutput $0.78 per 1M · 1M context | $0.195 | $0.78 | 1M | price read 12 Nov 2026 |
| Alibabaoutput $0.84 per 1M · 1M context | $0.21 | $0.84 | 1M | price read 12 Nov 2026 |
| Fireworksoutput $0.84 per 1M · 1M context | $0.21 | $0.84 | 1M | price read 12 Nov 2026 |
| Mancer 2output $0.75 per 1M · 1M context | $0.212 | $0.75 | 1M | price read 12 Nov 2026 |
| DigitalOceanoutput $0.90 per 1M · 1M context | $0.225 | $0.90 | 1M | price read 12 Nov 2026 |
| Makoraoutput $1.17 per 1M · 1M context | $0.26 | $1.17 | 1M | price read 12 Nov 2026 |
| Crusoeoutput $1.20 per 1M · 1M context | $0.29 | $1.20 | 1M | price read 12 Nov 2026 |
| Baiduoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| BaseTenoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Googleoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Modaloutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Parasailoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| SiliconFlowoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Togetheroutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
| Veniceoutput $1.20 per 1M · 1M context | $0.30 | $1.20 | 1M | price read 12 Nov 2026 |
28 hosts list DeepSeek V4.1 Flash, price read 12 Nov 2026.
GLM 5.3: other hosts
| Host | Input per 1M | Output per 1M | Context | Read |
|---|---|---|---|---|
| Waferoutput $1.40 per 1M · 1M context | $0.07 | $1.40 | 1M | price read 12 Nov 2026 |
| Relaceoutput $4.38 per 1M · 1M context | $0.07 | $4.38 | 1M | price read 12 Nov 2026 |
| InferenceNetoutput $3.60 per 1M · 1M context | $0.08 | $3.60 | 1M | price read 12 Nov 2026 |
| Rekaoutput $3.00 per 1M · 1M context | $0.15 | $3.00 | 1M | price read 12 Nov 2026 |
| AkashMLoutput $4.40 per 1M · 1M context | $0.19 | $4.40 | 1M | price read 12 Nov 2026 |
| Makoraoutput $3.20 per 1M · 1M context | $0.40 | $3.20 | 1M | price read 12 Nov 2026 |
| PrimeIntellectoutput $2.46 per 1M · 1M context | $0.40 | $2.46 | 1M | price read 12 Nov 2026 |
| DeepInfraoutput $2.50 per 1M · 1M context | $0.56 | $2.50 | 1M | price read 12 Nov 2026 |
| Decartoutput $1.88 per 1M · 1M context | $0.60 | $1.88 | 1M | price read 12 Nov 2026 |
| Tenstorrentoutput $2.50 per 1M · 1M context | $0.60 | $2.50 | 1M | price read 12 Nov 2026 |
| Novitaoutput $1.98 per 1M · 1M context | $0.63 | $1.98 | 1M | price read 12 Nov 2026 |
| Morphoutput $2.15 per 1M · 1M context | $0.70 | $2.15 | 1M | price read 12 Nov 2026 |
| Cloudflareoutput $2.20 per 1M · 1M context | $0.70 | $2.20 | 1M | price read 12 Nov 2026 |
| GMICloudoutput $2.20 per 1M · 1M context | $0.70 | $2.20 | 1M | price read 12 Nov 2026 |
| SiliconFlowoutput $2.20 per 1M · 1M context | $0.70 | $2.20 | 1M | price read 12 Nov 2026 |
| CoreWeaveoutput $3.00 per 1M · 1M context | $0.75 | $3.00 | 1M | price read 12 Nov 2026 |
| Sail Researchoutput $3.00 per 1M · 1M context | $0.75 | $3.00 | 1M | price read 12 Nov 2026 |
| DigitalOceanoutput $2.86 per 1M · 1M context | $0.91 | $2.86 | 1M | price read 12 Nov 2026 |
| Fireworksoutput $3.08 per 1M · 1M context | $0.98 | $3.08 | 1M | price read 12 Nov 2026 |
| Inceptronoutput $4.40 per 1M · 1M context | $1.00 | $4.40 | 1M | price read 12 Nov 2026 |
| Alibabaoutput $3.74 per 1M · 1M context | $1.19 | $3.74 | 1M | price read 12 Nov 2026 |
| Friendlioutput $3.96 per 1M · 1M context | $1.26 | $3.96 | 1M | price read 12 Nov 2026 |
| AtlasCloudoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Baiduoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| BaseTenoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Crusoeoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Mistraloutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Modaloutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Nebiusoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Parasailoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| SambaNovaoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Togetheroutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Veniceoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Z.AIoutput $4.40 per 1M · 1M context | $1.40 | $4.40 | 1M | price read 12 Nov 2026 |
| Amazon Bedrockoutput $5.28 per 1M · 1M context | $1.68 | $5.28 | 1M | price read 12 Nov 2026 |
35 hosts list GLM 5.3, price read 12 Nov 2026.
GLM 5.3 Flash: other hosts
| Host | Input per 1M | Output per 1M | Context | Read |
|---|---|---|---|---|
| Relaceoutput $0.0784 per 1M · 1M context | $0.04 | $0.0784 | 1M | price read 12 Nov 2026 |
| Waferoutput $0.184 per 1M · 1M context | $0.042 | $0.184 | 1M | price read 12 Nov 2026 |
| PrimeIntellectoutput $0.25 per 1M · 1M context | $0.0525 | $0.25 | 1M | price read 12 Nov 2026 |
| OpenInferenceoutput $0.30 per 1M · 1M context | $0.06 | $0.30 | 1M | price read 12 Nov 2026 |
| Darkbloomoutput $0.18 per 1M · 262K context | $0.065 | $0.18 | 262K | price read 12 Nov 2026 |
| GMICloudoutput $0.25 per 1M · 1M context | $0.075 | $0.25 | 1M | price read 12 Nov 2026 |
| Tenstorrentoutput $0.25 per 1M · 262K context | $0.075 | $0.25 | 262K | price read 12 Nov 2026 |
| Near AIoutput $0.50 per 1M · 1M context | $0.08 | $0.50 | 1M | price read 12 Nov 2026 |
| Novitaoutput $0.28 per 1M · 1M context | $0.084 | $0.28 | 1M | price read 12 Nov 2026 |
| StreamLakeoutput $0.295 per 1M · 1M context | $0.0885 | $0.295 | 1M | price read 12 Nov 2026 |
| Morphoutput $0.122 per 1M · 1M context | $0.093 | $0.122 | 1M | price read 12 Nov 2026 |
| DekaLLMoutput $0.50 per 1M · 1M context | $0.10 | $0.50 | 1M | price read 12 Nov 2026 |
| InferenceNetoutput $0.35 per 1M · 1M context | $0.108 | $0.35 | 1M | price read 12 Nov 2026 |
| DigitalOceanoutput $0.375 per 1M · 1M context | $0.113 | $0.375 | 1M | price read 12 Nov 2026 |
| CoreWeaveoutput $0.38 per 1M · 1M context | $0.12 | $0.38 | 1M | price read 12 Nov 2026 |
| NextBitoutput $0.45 per 1M · 1M context | $0.12 | $0.45 | 1M | price read 12 Nov 2026 |
| Particle AIoutput $0.50 per 1M · 1M context | $0.12 | $0.50 | 1M | price read 12 Nov 2026 |
| Rekaoutput $0.30 per 1M · 1M context | $0.12 | $0.30 | 1M | price read 12 Nov 2026 |
| Makoraoutput $0.24 per 1M · 1M context | $0.14 | $0.24 | 1M | price read 12 Nov 2026 |
| AtlasCloudoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| BaseTenoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Cohereoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Crusoeoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| DeepInfraoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Fireworksoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Friendlioutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| KToutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Mistraloutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Modaloutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Nebiusoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Parasailoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| SiliconFlowoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Togetheroutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Veniceoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Z.AIoutput $0.50 per 1M · 1M context | $0.15 | $0.50 | 1M | price read 12 Nov 2026 |
| Inceptronoutput $0.50 per 1M · 1M context | $0.175 | $0.50 | 1M | price read 12 Nov 2026 |
| Sail Researchoutput $0.625 per 1M · 1M context | $0.175 | $0.625 | 1M | price read 12 Nov 2026 |
37 hosts list GLM 5.3 Flash, price read 12 Nov 2026.
Kimi K3: other hosts
| Host | Input per 1M | Output per 1M | Context | Read |
|---|---|---|---|---|
| Relaceoutput $11.01 per 1M · 1M context | $0.182 | $11.01 | 1M | price read 12 Nov 2026 |
| InferenceNetoutput $15.00 per 1M · 1M context | $0.234 | $15.00 | 1M | price read 12 Nov 2026 |
| Waferoutput $9.60 per 1M · 1M context | $0.276 | $9.60 | 1M | price read 12 Nov 2026 |
| Sail Researchoutput $16.58 per 1M · 1M context | $0.345 | $16.58 | 1M | price read 12 Nov 2026 |
| Makoraoutput $17.00 per 1M · 1M context | $1.20 | $17.00 | 1M | price read 12 Nov 2026 |
| Chutesoutput $9.50 per 1M · 1M context | $1.85 | $9.50 | 1M | price read 12 Nov 2026 |
| Io Netoutput $14.00 per 1M · 1M context | $2.30 | $14.00 | 1M | price read 12 Nov 2026 |
| DigitalOceanoutput $12.95 per 1M · 1M context | $2.55 | $12.95 | 1M | price read 12 Nov 2026 |
| DeepInfraoutput $14.25 per 1M · 1M context | $2.85 | $14.25 | 1M | price read 12 Nov 2026 |
| Amazon Bedrockoutput $15.00 per 1M · 1M context | $3.00 | $15.00 | 1M | price read 12 Nov 2026 |
| BaseTenoutput $15.00 per 1M · 1M context | $3.00 | $15.00 | 1M | price read 12 Nov 2026 |
| Fireworksoutput $15.00 per 1M · 1M context | $3.00 | $15.00 | 1M | price read 12 Nov 2026 |
| KToutput $15.00 per 1M · 1M context | $3.00 | $15.00 | 1M | price read 12 Nov 2026 |
| Modaloutput $15.00 per 1M · 1M context | $3.00 | $15.00 | 1M | price read 12 Nov 2026 |
| Moonshot AIoutput $15.00 per 1M · 1M context | $3.00 | $15.00 | 1M | price read 12 Nov 2026 |
| Parasailoutput $15.00 per 1M · 1M context | $3.00 | $15.00 | 1M | price read 12 Nov 2026 |
| Togetheroutput $15.00 per 1M · 1M context | $3.00 | $15.00 | 1M | price read 12 Nov 2026 |
| Alibabaoutput $17.25 per 1M · 1M context | $3.45 | $17.25 | 1M | price read 12 Nov 2026 |
18 hosts list Kimi K3, price read 12 Nov 2026.
Qwen3.8 27B: other hosts
| Host | Input per 1M | Output per 1M | Context | Read |
|---|---|---|---|---|
| Darkbloomoutput $1.50 per 1M · 262K context | $0.035 | $1.50 | 262K | price read 12 Nov 2026 |
| Chutesoutput $1.25 per 1M · 262K context | $0.039 | $1.25 | 262K | price read 12 Nov 2026 |
| DekaLLMoutput $2.50 per 1M · 262K context | $0.04 | $2.50 | 262K | price read 12 Nov 2026 |
| Ionstreamoutput $1.95 per 1M · 262K context | $0.04 | $1.95 | 262K | price read 12 Nov 2026 |
| Modaloutput $2.30 per 1M · 262K context | $0.04 | $2.30 | 262K | price read 12 Nov 2026 |
| Near AIoutput $1.35 per 1M · 262K context | $0.04 | $1.35 | 262K | price read 12 Nov 2026 |
| PrimeIntellectoutput $0.395 per 1M · 262K context | $0.056 | $0.395 | 262K | price read 12 Nov 2026 |
| Waferoutput $2.20 per 1M · 262K context | $0.06 | $2.20 | 262K | price read 12 Nov 2026 |
| DeepInfraoutput $1.88 per 1M · 262K context | $0.15 | $1.88 | 262K | price read 12 Nov 2026 |
| Mancer 2output $1.25 per 1M · 262K context | $0.15 | $1.25 | 262K | price read 12 Nov 2026 |
| Rekaoutput $2.50 per 1M · 262K context | $0.15 | $2.50 | 262K | price read 12 Nov 2026 |
| Tenstorrentoutput $1.60 per 1M · 262K context | $0.15 | $1.60 | 262K | price read 12 Nov 2026 |
| StreamLakeoutput $1.05 per 1M · 1M context | $0.175 | $1.05 | 1M | price read 12 Nov 2026 |
| AkashMLoutput $1.98 per 1M · 262K context | $0.225 | $1.98 | 262K | price read 12 Nov 2026 |
| Parasailoutput $2.20 per 1M · 262K context | $0.24 | $2.20 | 262K | price read 12 Nov 2026 |
| CoreWeaveoutput $3.00 per 1M · 262K context | $0.40 | $3.00 | 262K | price read 12 Nov 2026 |
| Novitaoutput $3.00 per 1M · 1M context | $0.42 | $3.00 | 1M | price read 12 Nov 2026 |
| Alibabaoutput $2.55 per 1M · 1M context | $0.425 | $2.55 | 1M | price read 12 Nov 2026 |
| Cloudflareoutput $3.20 per 1M · 262K context | $0.45 | $3.20 | 262K | price read 12 Nov 2026 |
| GMICloudoutput $3.20 per 1M · 1M context | $0.45 | $3.20 | 1M | price read 12 Nov 2026 |
| Nebiusoutput $3.00 per 1M · 1M context | $0.45 | $3.00 | 1M | price read 12 Nov 2026 |
| Veniceoutput $3.20 per 1M · 262K context | $0.45 | $3.20 | 262K | price read 12 Nov 2026 |
| Cerebrasoutput $1.49 per 1M · 66K context | $0.99 | $1.49 | 66K | price read 12 Nov 2026 |
23 hosts list Qwen3.8 27B, price read 12 Nov 2026.
DeepSeek V4.1 Flash price tableGLM 5.3 price tableGLM 5.3 Flash price tableKimi K3 price tableQwen3.8 27B price table
How to read the tables
The first table is Runcrate, this site’s editor’s choice, with its live input and output price. When Runcrate does not serve a model, the row says so and names the nearest model it does serve.
The second table holds every other host that lists the model. Prices are per 1M tokens, with input and output apart. A free listing is shown as free and is left out of the lowest, median and highest figures.
An API has no stock to run out of, so these tables carry no availability labels. Read the context beside the price: two hosts can serve the same model with different limits.
Questions and answers
Runcrate is our editor’s choice for API token prices: 125 models behind one OpenAI-compatible API, one prepaid balance, and the best developer platform we know. Runcrate publishes this site.
Find both prices for your model, input and output, per million tokens. Then count the input and output tokens of a day of your own requests and multiply.
Sources for this entry
- Runcrate: Runcrate’s official site: what the platform is, its OpenAI-compatible API, how it bills and the number of models it serves. Read 12 Nov 2026.
- Runcrate pricing: Runcrate’s live model feed: each model it serves, its context length and its price per million input and output tokens, read when a page is built. Read 12 Nov 2026.
- Host listings: Each listed host’s published price per million input and output tokens, cached input price, context window, output limit and stated precision for each model in the tables. Read 12 Nov 2026.
- Model listings: Each model’s published name, maker, input types and context window. Read 12 Nov 2026.
Checklists are original editorial guidance. Published prices do not establish availability.
Continue this reading path
Cite this entry
API Token Prices. “Price tables.” Content reviewed 12 Nov 2026. https://apitokenprices.com/prices