Chutes API pricing
Updated
Chutes lists standard per-token prices on its own pricing page for 18 models. The cheapest is gemma-4-31B-it-turbo at USD 0.12 input and USD 0.37 output per 1M tokens; the dearest is Kimi K3 at USD 1.85 / USD 9.50. It publishes cached-input prices for all of them, plus fast prices. Checked 2026-11-15.
- Models with a standard price
- 18
- Median input / output
- USD 0.6785 / USD 2.325
- Cached-input prices
- 18 of 18
- Cheapest host for
- 8 of 18 shared models
Which models is Chutes the cheapest provider for?
Of the 18 models that Chutes and at least one other provider both price at the standard tier, Chutes has the lowest price for 8, ranked on a blend of 3 input tokens to 1 output token (1 of them tied with another provider at the same price). It is the dearest for 6.
| Model | Chutes input / output | Next cheapest | Saving on 3:1 blend | Providers |
|---|---|---|---|---|
| Kimi K3 | USD 1.85 / USD 9.50 | Featherless USD 2 / USD 10 | 6% | 18 |
| Qwen3.8 27B | USD 0.039 / USD 1.25 | DeepInfra USD 0.15 / USD 1.875 | 41% | 15 |
| DeepSeek V4 Pro 0813 | USD 0.85 / USD 2.65 | GMI Cloud USD 1.056 / USD 3.168 | 18% | 15 |
| Kimi K2.6 | USD 0.39 / USD 1.80 | CoreWeave Forge USD 0.65 / USD 3.41 | 45% | 13 |
| GLM 5.1 | USD 0.90 / USD 2.90 | SiliconFlow USD 1.19 / USD 3.74 | 23% | 12 |
| Qwen3.6 27B | USD 0.25 / USD 2 | Featherless USD 0.32 / USD 2.70 | 25% | 7 |
| Qwen3.5 27B | USD 0.20 / USD 1.75 | SiliconFlow USD 0.25 / USD 2 | 15% | 7 |
| Qwen3.5 397B A17B | USD 0.45 / USD 3 | DeepInfra USD 0.45 / USD 3 | tie | 7 |
How does Chutes price the most widely hosted models?
The 6 models Chutes sells that the most other providers also sell, with Chutes' rank among them on the 3:1 blend.
| Model | Chutes | Rank | Cheapest |
|---|---|---|---|
| GLM 5.3 | USD 1.225 / USD 3.85 | 4 of 24 | DeepInfra USD 0.5625 / USD 2.50 |
| GLM 5.2 | USD 1.25 / USD 3.95 | 3 of 19 | DeepInfra USD 0.5625 / USD 1.80 |
| Kimi K3 | USD 1.85 / USD 9.50 | 1 of 18 | Chutes (this page) |
| DeepSeek V4.1 Flash 1017 | USD 0.30 / USD 1.20 | 6 of 16 | DeepInfra USD 0.098 / USD 0.294 |
| DeepSeek V4 Pro 0813 | USD 0.85 / USD 2.65 | 1 of 15 | Chutes (this page) |
| Qwen3.8 27B | USD 0.039 / USD 1.25 | 1 of 15 | Chutes (this page) |
Which model makers does Chutes sell?
Chutes prices models from 6 makers. Qwen leads with 6 models. Standard prices, USD per 1M input / output tokens.
| Maker | Models | Cheapest model | Median input / output |
|---|---|---|---|
| Qwen | 6 | Qwen3.8 27B USD 0.039 / USD 1.25 | USD 0.35 / USD 2.50 |
| DeepSeek | 4 | DeepSeek V4.1 Flash 1017 USD 0.30 / USD 1.20 | USD 0.645 / USD 1.26 |
| Moonshot AI | 3 | Kimi K2.6 USD 0.39 / USD 1.80 | USD 0.832 / USD 3.50 |
| Z.ai | 3 | GLM 5.1 USD 0.90 / USD 2.90 | USD 1.225 / USD 3.85 |
| 1 | gemma-4-31B-it-turbo USD 0.12 / USD 0.37 | — | |
| Tencent | 1 | Hy4 USD 0.525 / USD 1.5625 | — |
Chutes price list
USD per 1M tokens: 19 prices for 18 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-15 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means Chutes is cheaper. Of 14 hosted model prices with a maker price to compare, 11 are below the maker's and 0 above.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | standard | USD 1 | USD 0.10 | USD 1 | 131,072 | — | source |
| DeepSeek V4 Flash 0731 | standard | USD 0.44 | USD 0.044 | USD 1.32 | 1,048,576 | — | source |
| DeepSeek V4 Pro 0813 | standard | USD 0.85 | USD 0.15 | USD 2.65 | 1,000,000 | −34% | source |
| DeepSeek V4.1 Flash 1017 | standard | USD 0.30 | USD 0.03 | USD 1.20 | 1,000,000 | same | source |
| gemma-4-31B-it-turbo | standard | USD 0.12 | USD 0.012 | USD 0.37 | 131,072 | — | source |
| GLM 5.1 | standard | USD 0.90 | USD 0.09 | USD 2.90 | 202,752 | −35% | source |
| GLM 5.2 | standard fast | USD 1.25 USD 2.45 | USD 0.125 USD 0.49 | USD 3.95 USD 7.70 | 1,048,576 | −10% | source |
| GLM 5.3 | standard | USD 1.225 | USD 0.245 | USD 3.85 | 1,048,576 | −12% | source |
| Hy4 | standard | USD 0.525 | USD 0.025 | USD 1.5625 | 1,048,576 | — | source |
| Kimi K2.6 | standard | USD 0.39 | USD 0.039 | USD 1.80 | 262,144 | −57% | source |
| Kimi K2.7 Code | standard | USD 0.832 | USD 0.167 | USD 3.50 | 262,144 | −12% | source |
| Kimi K3 | standard | USD 1.85 | USD 0.185 | USD 9.50 | 1,048,576 | −37% | source |
| Qwen3.5 27B | standard | USD 0.20 | USD 0.02 | USD 1.75 | 262,144 | −29% | source |
| Qwen3.5 397B A17B | standard | USD 0.45 | USD 0.045 | USD 3 | 262,144 | −19% | source |
| Qwen3.6 27B | standard | USD 0.25 | USD 0.025 | USD 2 | 262,144 | −49% | source |
| Qwen3.8 2.4T A95B | standard | USD 2 | USD 0.25 | USD 6 | 1,000,000 | same | source |
| Qwen3.8 27B | standard | USD 0.039 | USD 0.0039 | USD 1.25 | 262,144 | −70% | source |
| Qwen3.8 Max (0902) | standard | USD 2 | USD 0.25 | USD 6 | 1,000,000 | same | source |
- Cached "—" means Chutes' page shows no cache price for that row; budget cached tokens at the input price.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does Chutes publish?
- fast (1 row). Across 1 model with both prices, median fast input is 1.96× standard and median output 1.95× standard. Chutes row note: “Fast variant, model ID zai-org/GLM-5.2-Fast.”
Cached input: 18 of 18 standard prices include a cache-read price, a median 10% of the input price. What cached input means.
What we recorded about Chutes' pricing page: Prices from the "Model pricing" table on chutes.ai/pricing (columns Cached input, Input price, Output price, per 1M tokens, USD view), cross-checked against Chutes' own public model list https://llm.chutes.ai/v1/models, which also gives exact context length and quantization. Chutes also accepts TAO; USD prices are used. Private GPU deployments (per second) excluded.
Is Chutes cheaper than the model makers' own APIs?
Mostly yes. Of 14 standard prices for models whose maker sells its own API, 11 are below the maker's price, 0 above and 3 the same, on the 3:1 blend. The median difference is 24% below the maker. The biggest saving is Qwen3.8 27B, 70% below Alibaba Cloud.
BroadNet Inference and Chutes
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 2 models that Chutes prices: Qwen3.8 27B at USD 0.175 / USD 2.17 against Chutes' USD 0.039 / USD 1.25 (Chutes is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against Chutes' USD 1.225 / USD 3.85 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.
More on Chutes
- Chutes' own pricing page (the source; checked 2026-11-15)
- All 41 providers compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)
Questions
How much does the Chutes API cost per token?
Chutes' standard prices run from USD 0.12 input and USD 0.37 output per 1M tokens (gemma-4-31B-it-turbo) to USD 1.85 / USD 9.50 (Kimi K3). The median across 18 standard prices is USD 0.6785 input and USD 2.325 output per 1M, which is USD 0.0000006785 per input token. Input, cached input and output are billed separately.
What is the cheapest model on Chutes?
gemma-4-31B-it-turbo, at USD 0.12 input and USD 0.37 output per 1M tokens (USD 0.1825 on a 3:1 input-to-output blend). The cheapest from other makers: Qwen3.8 27B (Qwen) at USD 0.039 / USD 1.25; DeepSeek V4.1 Flash 1017 (DeepSeek) at USD 0.30 / USD 1.20; Kimi K2.6 (Moonshot AI) at USD 0.39 / USD 1.80.
Is Chutes cheaper than other providers?
It depends on the model. Of 18 models that other providers also price, Chutes is the cheapest standard price for 8 (1 of them tied with another provider), for example Kimi K3, Qwen3.8 27B and DeepSeek V4 Pro 0813; another provider is cheaper for 10; and it is the dearest for 6. Its median rank is 2 of a median 12 providers, on a 3:1 input-to-output blend.
Does Chutes have batch, cached or priority pricing?
Cached input: yes, for 18 of 18 standard prices, at a median 10% of the input price. Other tiers: fast on 1 row (median input 1.96× standard).
How much does a chatbot cost per month on Chutes?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 11.63 on gemma-4-31B-it-turbo, USD 59.40 on DeepSeek V3.2 (the middle of Chutes' list) and USD 247.59 on Kimi K3. Try your own numbers.