Developer Plan and Credits
How prepaid credits work for request-based API billing.
The Developer plan is Featherless's usage-based plan: you choose a monthly credit amount (from $50/month) and API usage is billed per token against your balance. Context sizes up to 256K, the fastest response times, one included agent environment, and no model-size limit. Unused credits roll over and don't expire.
How Developer Plan Pricing Works
Choose a monthly credit amount.
That amount is added to your Featherless credit balance each billing cycle after payment succeeds.
You can add a one-time credit top-up from the billing page without changing your monthly credit amount.
Successful API requests reduce your balance.
If your balance reaches zero or below, request-pricing API calls are blocked until more credits are available.
Credits do not expire.
How Request Costs Are Calculated
Only successful requests are charged.
Request cost is based on the model used, input tokens, and output tokens.
Formula: input tokens x input price + output tokens x output price.
Prices are listed per 1M tokens.
How cached input pricing works
Some models have a lower "cached input" rate alongside their standard input rate. When a request reuses a long prompt prefix the platform has recently served — a long system prompt, running chat history, a shared document — eligible input tokens may be billed at the cached rate instead of the full input rate.
It's automatic: no code changes, no cache parameters.
Only sufficiently long repeated prefixes qualify (roughly 1,000+ tokens of exact prefix match). Short or novel prompts bill at the standard input rate.
Each model's page shows its cached rate when it has one (example: GLM-5.3 — $1.40 input / $0.26 cached / $4.40 output per 1M tokens). A "–" means the model always bills at the standard input rate.
For agentic and long-context workloads, cached input pricing can cut input costs substantially.
What each request costs
Every model's page shows its current prices — input, cached input where available, and output, per 1M tokens (per 1M characters for speech models): https://featherless.ai/models
Cost per request = input tokens × input price + output tokens × output price. Only successful requests are charged. Some low-volume niche models carry a pricing multiplier over their model class's base rate the model page always shows the effective price if you are on Developer Plan.
| Family | Model Class | Input | Cached input / 1M tokens | Output / 1M tokens |
|---|---|---|---|---|
| ACE Step | music-ace-step-3b5 | $22 / 1M chars | - | n/a |
| Apertus | apertus-70b | $0.875 / 1M tok | $0.175 | $2.075 |
| Apertus | apertus-8b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| Arcee | arcee-4b5 | $0.3 / 1M tok | $0.06 | $1.2 |
| Arcee MOE | afmoe-399b | $0.25 / 1M tok | - | $0.8 |
| Bamba | bamba-9b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| Bert | bge-large-en | $0.01 / 1M tok | $0.002 | $0.02 |
| Chatterbox | tts-chatterbox | $22 / 1M chars | - | n/a |
| Chatterbox Turbo | tts-chatterbox-turbo | $22 / 1M chars | - | n/a |
| Csm | tts-csm-1b | $22 / 1M chars | - | n/a |
| Deepseek 3 | deepseek-v3-lc | $0.385 / 1M tok | - | $1.625 |
| Deepseek 3.1 | deepseek31-685b | $0.285 / 1M tok | - | $1 |
| Deepseek 3.2 | deepseek-v3.2 | $0.264 / 1M tok | $0.06 | $0.41 |
| Deepseek 4 | deepseek4-1.6t | $1.6 / 1M tok | $0.2 | $3.2 |
| Deepseek 4 | deepseek4-284b | $0.1385 / 1M tok | $0.03 | $0.279 |
| Deepseek 4 | deepseek4-763b | $1 / 1M tok | - | $4 |
| Dia | tts-dia-1b6 | $22 / 1M chars | - | n/a |
| Ernie4 5 | ernie4_5-0b3 | $0.01 / 1M tok | $0.002 | $0.02 |
| Ernie4 5 Moe | ernie4_5_moe-21b | $0.08 / 1M tok | $0.016 | $0.4 |
| Exaone4 | exaone4-32b | $0.265 / 1M tok | $0.053 | $0.65 |
| F5 TTS | tts-f5-tts | $22 / 1M chars | - | n/a |
| Falcon | falcon-7b2 | $0.1 / 1M tok | $0.02 | $0.2 |
| Falcon | falcon-7b7 | $0.1 / 1M tok | $0.02 | $0.2 |
| Gemma | gemma-2b | $0.08 / 1M tok | $0.064 | $0.4 |
| Gemma | Gemma-2b | $0.08 / 1M tok | $0.016 | $0.4 |
| Gemma | gemma-7b | $0.1078 / 1M tok | $0.0862 | $0.28 |
| Gemma 2 | gemma2-27b | $0.65 / 1M tok | $0.13 | $0.65 |
| Gemma 2 | gemma2-2b | $0.08 / 1M tok | $0.064 | $0.4 |
| Gemma 3 | gemma3-0b2 | $0.01 / 1M tok | $0.008 | $0.02 |
| Gemma 3 | gemma3-12b | $0.05 / 1M tok | - | $0.15 |
| Gemma 3 | gemma3-270m | $0.01 / 1M tok | $0.002 | $0.02 |
| Gemma 3 | gemma3-27b | $0.1 / 1M tok | $0.08 | $0.3 |
| Gemma 3 | gemma3-4b | $0.05 / 1M tok | - | $0.1 |
| Gemma 3 | gemma3-8b3 | $0.1078 / 1M tok | $0.0216 | $0.28 |
| Gemma 3 | gemma3t-12b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| Gemma 3 | gemma3t-1b | $0.01 / 1M tok | $0.008 | $0.02 |
| Gemma 3 | gemma3t-27b | $0.265 / 1M tok | $0.053 | $0.65 |
| Gemma 4 | gemma4-25b | $0.1 / 1M tok | $0.08 | $0.2 |
| Gemma 4 | gemma4-26b | $0.07 / 1M tok | $0.05 | $0.34 |
| Gemma 4 | gemma4-31b | $0.12 / 1M tok | $0.1 | $0.36 |
| Gemma 4 | gemma4-5b | $0.1 / 1M tok | $0.08 | $0.2 |
| Gemma 4 | gemma4-7b | $0.1 / 1M tok | $0.08 | $0.2 |
| Gemma 4 | gemma4-e2b | $0.08 / 1M tok | $0.016 | $0.4 |
| Gemma 4 | gemma4-e4b | $0.1 / 1M tok | $0.02 | $0.2 |
| Gemma4 Unified | gemma4unified-12b | $0.3 / 1M tok | $0.24 | $1.2 |
| GLM 4 | glm4-32b | $0.265 / 1M tok | $0.053 | $0.65 |
| GLM 4 | glm4-9b | $0.1078 / 1M tok | $0.0862 | $0.28 |
| GLM 4.6 | glm46-357b | $0.55 / 1M tok | $0.11 | $2.2 |
| GLM 4.7 | glm47-357b | $0.55 / 1M tok | $0.11 | $2.2 |
| GLM 4.7 | glm47-flash | $0.0653 / 1M tok | $0.0131 | $0.4 |
| GLM 5 | glm5-754b | $0.95 / 1M tok | $0.19 | $3.15 |
| GLM 5.1 | glm51-754b | $1.3 / 1M tok | $0.26 | $4.3 |
| GLM 5.2 | glm52-753b | $1.4 / 1M tok | $0.15 | $4.4 |
| Glm Moe Dsa | glm-moe-dsa-753b3 | $1 / 1M tok | - | $4 |
| Glm5 Next | glm5-next-321b3 | $0.15 / 1M tok | $0.03 | $0.5 |
| Gpt Bigcode | gptbigcode-1b | $0.01 / 1M tok | $0.002 | $0.02 |
| GPT OSS | gpt-oss-120b | $0.15 / 1M tok | $0.02 | $0.6 |
| GPT OSS | gpt-oss-20b | $0.04 / 1M tok | - | $0.15 |
| GPT OSS | gptoss-21b | $0.075 / 1M tok | - | $0.3 |
| GPT-SW3 | gpt-sw3-126m | $0.01 / 1M tok | $0.002 | $0.02 |
| GPT-SW3 | gpt-sw3-1b3 | $0.01 / 1M tok | $0.002 | $0.02 |
| GPT-SW3 | gpt-sw3-20b | $0.265 / 1M tok | $0.053 | $0.65 |
| GPT-SW3 | gpt-sw3-356m | $0.01 / 1M tok | $0.002 | $0.02 |
| GPT-SW3 | gpt-sw3-6b7 | $0.1 / 1M tok | $0.02 | $0.2 |
| Gpt2 | gpt-sw3-40b | $0.265 / 1M tok | $0.053 | $0.65 |
| GPT2-SW3 | gpt2-sw3-126m | $0.01 / 1M tok | $0.002 | $0.02 |
| GPT2-SW3 | gpt2-sw3-6b7 | $0.1 / 1M tok | $0.02 | $0.2 |
| Granite | granite-2b | $0.08 / 1M tok | $0.016 | $0.4 |
| Granite | granite-8b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| Granitemoe | granitemoe-1b | $0.01 / 1M tok | $0.002 | $0.02 |
| Granitemoe | granitemoe-3b | $0.08 / 1M tok | $0.016 | $0.4 |
| Hy V3 | hy-v3-298b8 | $1 / 1M tok | - | $4 |
| Hyperclovax Vlm | hcxvision-3b | $0.08 / 1M tok | $0.016 | $0.4 |
| Internlm3 | internlm3-8b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| K2 Horizon | k2-horizon-1b1 | $0.3 / 1M tok | - | $1.2 |
| K2 Horizon | k2-horizon-34b8 | $0.5 / 1M tok | - | $2 |
| K2 Horizon | k2-horizon-36b | $1 / 1M tok | - | $4 |
| K2 Horizon | k2-horizon-375b | $1 / 1M tok | - | $4 |
| K2 Horizon | k2-horizon-5b1 | $0.3 / 1M tok | - | $1.2 |
| K2 Horizon | k2-horizon-9b | $0.3 / 1M tok | - | $1.2 |
| Kimi 2 | kimi-k2 | $0.6 / 1M tok | - | $2.5 |
| Kimi 2.5 | kimi-k25 | $0.8 / 1M tok | $0.154 | $3.4 |
| Kimi 3 | kimi3-2780b | $3 / 1M tok | $0.3 | $15 |
| Kimi Linear | kimi-linear-48b | $0.08 / 1M tok | $0.016 | $0.4 |
| Kokoro | tts-kokoro-82m | $22 / 1M chars | - | n/a |
| Laguna S 2 | laguna-s-21 | $1 / 1M tok | $0.2 | $4 |
| LFM 2 | lfm2-0b3 | $0.01 / 1M tok | $0.008 | $0.02 |
| LFM 2 | lfm2-0b7 | $0.01 / 1M tok | $0.002 | $0.02 |
| LFM 2 | lfm2-1b | $0.01 / 1M tok | $0.008 | $0.02 |
| LFM 2 | lfm2-1b2 | $0.01 / 1M tok | $0.002 | $0.02 |
| Lfm2 Moe | lfm2-moe-24b | $0.265 / 1M tok | $0.053 | $0.65 |
| LightOnOCR 2 | lightonocr-2 | $0.3 / 1M tok | $0.06 | $1.2 |
| Llama 2 | llama2-13b | $0.375 / 1M tok | - | $0.525 |
| Llama 2 | llama2-34b | $0.265 / 1M tok | $0.212 | $0.65 |
| Llama 2 | llama2-70b | $0.875 / 1M tok | $0.7 | $2.075 |
| Llama 2 | llama2-7b | $0.1 / 1M tok | $0.08 | $0.2 |
| Llama 2 | llama2-solar-10b7 | $0.1078 / 1M tok | $0.0862 | $0.28 |
| Llama 2 | tinyllama-1b1 | $0.01 / 1M tok | $0.008 | $0.02 |
| Llama 3 | llama-34b | $0.265 / 1M tok | $0.212 | $0.65 |
| Llama 3 | llama3-15b | $0.1078 / 1M tok | $0.0862 | $0.28 |
| Llama 3 | llama3-70b | $0.875 / 1M tok | $0.7 | $2.075 |
| Llama 3 | llama3-8b | $0.0925 / 1M tok | $0.074 | $0.095 |
| Llama 3 | tts-llama3-3b | $22 / 1M chars | - | n/a |
| Llama 3.1 | llama31-70b | $0.72 / 1M tok | - | $0.72 |
| Llama 3.1 | llama31-8b | $0.05 / 1M tok | $0.028 | $0.08 |
| Llama 3.2 | llama32-1b | $0.027 / 1M tok | - | $0.201 |
| Llama 3.2 | llama32-3b | $0.0509 / 1M tok | - | $0.335 |
| Llama 3.3 | llama33-70b | $0.65 / 1M tok | $0.52 | $0.75 |
| Mamba | mamba-0b7 | $0.01 / 1M tok | $0.002 | $0.02 |
| Mellum | mellum-4b | $0.1 / 1M tok | $0.02 | $0.2 |
| Mimo | mimo-7b | $0.1 / 1M tok | $0.02 | $0.2 |
| Mimo 2 | mimo2-flash | $0.1078 / 1M tok | $0.0216 | $0.28 |
| Mimo 2.5 | mimo25-311b | $0.149 / 1M tok | $0.028 | $0.493 |
| MiniMax 2 | minimax-m2 | $0.2775 / 1M tok | $0.0555 | $1.11 |
| MiniMax 2.1 | minimax-m21 | $0.3 / 1M tok | $0.06 | $1.2 |
| MiniMax 2.5 | minimax-m25 | $0.295 / 1M tok | $0.059 | $1.2 |
| Minimax M2 | minimax-m2-228b7 | $0.3 / 1M tok | $0.06 | $1.2 |
| MiniMax M3 | minimax-m3 | $0.55 / 1M tok | $0.06 | $2.2 |
| Mistral | mistral-large | $0.125 / 1M tok | $0.025 | $1.15 |
| Mistral | mistral-nemo | $0.2175 / 1M tok | $0.2 | $0.2475 |
| Mistral | mistral-nemo-12b-lc | $0.3 / 1M tok | - | $1.2 |
| Mistral | mistral-v01-7b | $0.1 / 1M tok | $0.08 | $0.2 |
| Mistral | mistral-v02-7b | $0.1 / 1M tok | $0.08 | $0.2 |
| Mistral | mixtral-8x22b | $0.125 / 1M tok | $0.025 | $1.15 |
| Mistral 3 | mistral-24b | $0.175 / 1M tok | $0.04 | $0.29 |
| Mistral 3 | mistral3-3b | $0.08 / 1M tok | $0.016 | $0.4 |
| Mistral 3.1 | mistral-24b-2503 | $0.2168 / 1M tok | - | $0.4025 |
| Mistral 3.5 | mistral-3.5 | $1 / 1M tok | $0.2 | $4 |
| Muse Glimmer | glimmer-30b | $0.3 / 1M tok | $0.04 | $1.1 |
| Nanbeige | nanbeige41-3b | $0.1 / 1M tok | $0.02 | $0.2 |
| Nemotron 3 | nemotron3-120b | $0.125 / 1M tok | $0.025 | $1.15 |
| Nemotron H | nemotronh-31b | $0.05 / 1M tok | - | $0.2 |
| Nemotron-nas | decilm-49b | $0.4 / 1M tok | $0.08 | $0.4 |
| Nomic Bert | nomic-v15 | $0.01 / 1M tok | $0.002 | $0.02 |
| Olmo | olmo-1b | $0.01 / 1M tok | $0.002 | $0.02 |
| OLMo 3 | olmo3-32b | $0.265 / 1M tok | $0.053 | $0.65 |
| OLMo 3 | olmo3-7b | $0.1 / 1M tok | $0.02 | $0.2 |
| Ouro | ouro-1b | $0.01 / 1M tok | $0.002 | $0.02 |
| Ouro | ouro-2b | $0.08 / 1M tok | $0.016 | $0.4 |
| OvisOCR 2 | ovisocr-2 | $0.3 / 1M tok | $0.06 | $1.2 |
| Panguembedded | panguembedded-8b | $0.1 / 1M tok | $0.02 | $0.2 |
| Phi | phi-1b4 | $0.01 / 1M tok | $0.002 | $0.02 |
| Phi 2 | phi2-3b | $0.08 / 1M tok | $0.064 | $0.4 |
| Phi 3 | phi3-4b | $0.1 / 1M tok | $0.08 | $0.2 |
| Phi 3 | phi3v-4b | $0.1 / 1M tok | $0.02 | $0.2 |
| Phi 4 | phi4-14b | $0.07 / 1M tok | - | $0.14 |
| Phi 4 | phi4-3b8 | $0.08 / 1M tok | $0.016 | $0.35 |
| Phimoe | phimoe-42b | $0.875 / 1M tok | $0.175 | $2.075 |
| QRWKV | qrwkv-32b-32k | $0.265 / 1M tok | $0.053 | $0.65 |
| QRWKV | qrwkv-72b-32k | $0.875 / 1M tok | $0.175 | $2.075 |
| Qwen | qwenlmheadmodel-7b | $0.1 / 1M tok | $0.02 | $0.2 |
| Qwen 1.5 | qwen15-0b5 | $0.01 / 1M tok | $0.002 | $0.02 |
| Qwen 1.5 | qwen15-14b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| Qwen 1.5 | qwen15-1b8 | $0.01 / 1M tok | $0.008 | $0.02 |
| Qwen 1.5 | qwen15-32b | $0.265 / 1M tok | $0.053 | $0.65 |
| Qwen 1.5 | qwen15-4b | $0.1 / 1M tok | $0.02 | $0.2 |
| Qwen 1.5 | qwen15-72b | $0.875 / 1M tok | $0.175 | $2.075 |
| Qwen 1.5 | qwen15-7b | $0.1 / 1M tok | $0.02 | $0.2 |
| Qwen 2 | qwen2-0b5 | $0.01 / 1M tok | $0.008 | $0.02 |
| Qwen 2 | qwen2-14b-lc | $0.1078 / 1M tok | $0.0862 | $0.28 |
| Qwen 2 | qwen2-1b5 | $0.01 / 1M tok | $0.008 | $0.02 |
| Qwen 2 | qwen2-32b | $0.265 / 1M tok | $0.053 | $0.65 |
| Qwen 2 | qwen2-72b | $3 / 1M tok | - | $5 |
| Qwen 2 | qwen2-7b | $0.1 / 1M tok | $0.08 | $0.2 |
| Qwen 2.5 | qwen25-0b5 | $0.01 / 1M tok | $0.008 | $0.02 |
| Qwen 2.5 | qwen25-14b | $0.1078 / 1M tok | $0.0862 | $0.28 |
| Qwen 2.5 | qwen25-1b5 | $0.01 / 1M tok | $0.008 | $0.02 |
| Qwen 2.5 | qwen25-32b | $0.68 / 1M tok | - | $1.2 |
| Qwen 2.5 | qwen25-3b | $0.08 / 1M tok | $0.064 | $0.4 |
| Qwen 2.5 | qwen25-72b | $0.37 / 1M tok | - | $0.4 |
| Qwen 2.5 | qwen25-7b | $0.17 / 1M tok | $0.136 | $0.2 |
| Qwen 2.5 | qwen25vl-32b | $0.265 / 1M tok | $0.053 | $0.65 |
| Qwen 2.5 | qwen25vl-3b | $0.08 / 1M tok | $0.016 | $0.4 |
| Qwen 2.5 | qwen25vl-72b | $0.8 / 1M tok | - | $1 |
| Qwen 2.5 | qwen25vl-7b | $0.1 / 1M tok | - | $0.2 |
| Qwen 3 | qwen3-0b6 | $0.01 / 1M tok | $0.008 | $0.02 |
| Qwen 3 | qwen3-14b | $0.12 / 1M tok | - | $0.24 |
| Qwen 3 | qwen3-1b7 | $0.08 / 1M tok | $0.064 | $0.4 |
| Qwen 3 | qwen3-235b | $0.455 / 1M tok | - | $1.82 |
| Qwen 3 | qwen3-32b | $0.102 / 1M tok | $0.0816 | $0.493 |
| Qwen 3 | qwen3-4b | $0.1 / 1M tok | $0.08 | $0.2 |
| Qwen 3 | qwen3-8b | $0.117 / 1M tok | - | $0.455 |
| Qwen 3 | qwen3-coder-480b | $0.38 / 1M tok | $0.076 | $1.55 |
| Qwen 3 | qwen3-embedding-0b6 | $0.01 / 1M tok | $0.002 | $0.02 |
| Qwen 3 | qwen3-embedding-4b | $0.02 / 1M tok | - | $0 |
| Qwen 3 | qwen3-embedding-8b | $0.01 / 1M tok | - | $0 |
| Qwen 3 | qwen3moe-30b | $0.125 / 1M tok | - | $0.45 |
| Qwen 3 | qwen3moe-80b | $0.16 / 1M tok | $0.036 | $1.15 |
| Qwen 3 | qwen3vl-235b | $0.98 / 1M tok | - | $3.95 |
| Qwen 3 | qwen3vl-2b | $0.08 / 1M tok | $0.016 | $0.4 |
| Qwen 3 | qwen3vl-32b | $0.104 / 1M tok | - | $0.416 |
| Qwen 3 | qwen3vl-4b | $0.1 / 1M tok | $0.08 | $0.2 |
| Qwen 3 | qwen3vl-8b | $0.1818 / 1M tok | - | $1.3513 |
| Qwen 3 | qwen3vlmoe-30b | $0.175 / 1M tok | - | $0.65 |
| Qwen 3 Next | qwen3next-80b | $0.125 / 1M tok | - | $1.15 |
| Qwen 3.5 | qwen3.5-27b | $0.3 / 1M tok | - | $2.4 |
| Qwen 3.5 | qwen3.5-2b | $0.08 / 1M tok | $0.016 | $0.4 |
| Qwen 3.5 | qwen3.5-397b | $0.55 / 1M tok | - | $3.5 |
| Qwen 3.5 | qwen3.5-4b | $0.1 / 1M tok | $0.02 | $0.2 |
| Qwen 3.5 | qwen3.5-9b | $0.17 / 1M tok | - | $0.25 |
| Qwen3 5 | qwen3_5-27b | $0.4 / 1M tok | $0.15 | $3 |
| Qwen3 5 | qwen3_5-2b | $0.08 / 1M tok | $0.064 | $0.4 |
| Qwen3 5 | qwen3_5-4b | $0.1 / 1M tok | $0.08 | $0.2 |
| Qwen3 5 | qwen3_5-9b | $0.1078 / 1M tok | $0.0862 | $0.28 |
| Qwen3 5 | qwen3-5vl-27b8 | $0.32 / 1M tok | $0.064 | $2.7 |
| Qwen3 5 Moe | qwen3_5moe-35b | $0.1 / 1M tok | $0.07 | $1 |
| Qwen3 5 Moe | qwen3-5-moevl-35b | $0.186 / 1M tok | $0.032 | $1.1138 |
| Qwen3 Moe | qwen3moe-235b | $0.45 / 1M tok | - | $3.5 |
| Qwen3 Tts | tts-qwen3-tts-1b7 | $22 / 1M chars | - | n/a |
| Qwen4 Exp | qwen4-expvl-180b | $0.15 / 1M tok | $0.03 | $0.5 |
| RWKV 5 | rwkv5-7b | $0.1 / 1M tok | $0.02 | $0.2 |
| RWKV 6 | rwkv6-14b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| RWKV 6 | rwkv6-7b | $0.1 / 1M tok | $0.02 | $0.2 |
| RWKV 6 | rwkv6moe-37b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| RWKV 7 | rwkv7-13b3 | $0.3 / 1M tok | - | $1.2 |
| RWKV 7 | rwkv7-2b9 | $0.3 / 1M tok | - | $1.2 |
| RWKV 7 | rwkv7-7b2 | $0.3 / 1M tok | - | $1.2 |
| Stablelm | stablelm-2b | $0.08 / 1M tok | $0.016 | $0.4 |
| Step 3.5 | step-3.5-199b | $0.1 / 1M tok | - | $0.3 |
| Step3p7 | step3p7vl-201b4 | $0.2 / 1M tok | $0.04 | $1.15 |
| Surya | surya2-ocr | $0.3 / 1M tok | $0.06 | $1.2 |
| Talkie | talkie-13b | $0.1078 / 1M tok | $0.0216 | $0.28 |
| Zamba2 | zamba2-7b | $0.3 / 1M tok | $0.06 | $1.2 |
Model-Specific Pricing
These models use prices that differ from their default model class price.
| Model | Family | Model Class | Input | Cached input / 1M tokens | Output / 1M tokens |
|---|---|---|---|---|---|
| ACE-Step/ACE-Step-v1-3.5B | ACE Step | music-ace-step-3b5 | $3 / 1M chars | - | n/a |
| canopylabs/orpheus-3b-0.1-ft | Llama 3 | tts-llama3-3b | $15 / 1M chars | - | n/a |
| deepseek-ai/DeepSeek-V4-Flash | Deepseek 4 | deepseek4-284b | $0.14 / 1M tok | $0.03 | $0.28 |
| deepseek-ai/DeepSeek-V4-Flash-0731 | Deepseek 4 | deepseek4-284b | $0.14 / 1M tok | $0.03 | $0.28 |
| deepseek-ai/DeepSeek-V4-Pro | Deepseek 4 | deepseek4-1.6t | $1.6 / 1M tok | $0.2 | $3.2 |
| deepseek-ai/DeepSeek-V4.1-Flash | Deepseek 4 | deepseek4-763b | $0.3 / 1M tok | $0.03 | $1.2 |
| featherless-ai/gemma-4-26B-A4B-classifier | Gemma 4 | gemma4-26b | $0.28 / 1M tok | $0.05 | $0 |
| featherless-ai/Qwen3.6-35B-A3B-classifier | Qwen3 5 Moe | qwen3-5-moevl-35b | $0.28 / 1M tok | $0.032 | $0 |
| featherless-ai/Qwen3.8-27B-classifier | Qwen3 5 | qwen3_5-27b | $0.3 / 1M tok | $0.15 | $0 |
| featherless-ai/RWKV-mid-classifier | RWKV 7 | rwkv7-7b2 | $0.1 / 1M tok | - | $0 |
| featherless-ai/RWKV-small-classifier | RWKV 7 | rwkv7-2b9 | $0.03 / 1M tok | - | $0 |
| featherless-ai/RWKV-std-classifier | RWKV 7 | rwkv7-13b3 | $0.2 / 1M tok | - | $0 |
| hexgrad/Kokoro-82M | Kokoro | tts-kokoro-82m | $4 / 1M chars | - | n/a |
| nari-labs/Dia-1.6B | Dia | tts-dia-1b6 | $6 / 1M chars | - | n/a |
| Qwen/Qwen3-TTS-12Hz-1.7B-Base | Qwen3 Tts | tts-qwen3-tts-1b7 | $20 / 1M chars | - | n/a |
| Qwen/Qwen3-VL-30B-A3B-Instruct | Qwen 3 | qwen3vlmoe-30b | $0.15 / 1M tok | - | $0.5 |
| ResembleAI/chatterbox | Chatterbox | tts-chatterbox | $25 / 1M chars | - | n/a |
| ResembleAI/chatterbox-turbo | Chatterbox Turbo | tts-chatterbox-turbo | $25 / 1M chars | - | n/a |
| sesame/csm-1b | Csm | tts-csm-1b | $7 / 1M chars | - | n/a |
| SWivid/F5-TTS | F5 TTS | tts-f5-tts | $10 / 1M chars | - | n/a |
| zai-org/GLM-5.3 | Glm Moe Dsa | glm-moe-dsa-753b3 | $1.4 / 1M tok | $0.26 | $4.4 |
| zai-org/GLM-5.3-Flash | Glm5 Next | glm5-next-321b3 | $0.15 / 1M tok | $0.03 | $0.5 |
Live Balance And Recent Usage
Your billing page shows your up-to-date live credit balance.
Recent usage may take a short time to appear in detailed usage views.
Usage activity shows spend, request count, input and output tokens, models used, and request-level details.
The billing page also lets eligible request-pricing organizations add one-time credits using the saved billing method on file.
Low Balance And Out-Of-Credits Emails
We send a low-balance email when your credit balance reaches $5.
We send an out-of-credits email when your balance reaches zero or below.
Alerts are sent to the organization billing email.
Alert settings can be changed from your billing page.
Choosing A Monthly Credit Amount
Start with the amount you expect to spend in a month.
You can increase your monthly amount later if usage grows.
If you are unsure, start with a smaller tier and monitor usage from the billing page.
For high-volume usage, you can add one-time credits from the billing page or contact support for custom needs.
Changing Your Monthly Credit Amount
Increasing your monthly credit amount takes effect immediately after successful payment.
The upgrade is prorated for the remaining time in your current billing cycle.
Your billing cycle date stays the same.
Decreasing your monthly credit amount is scheduled for your next billing cycle.
Switching From A Chat Plan To Developer Plan
Switching from a chat monthly plan to a Developer Plan changes your organization to credit-based billing.
The change can take effect immediately after successful payment.
You can only switch to a monthly credit amount that is the same as or higher than your current fixed-plan monthly amount.
Switching from a fixed chat plan to a lower monthly credit amount is blocked.
Any remaining value from your current billing period may be applied as prorated credit when you switch.
Your billing cycle date stays the same where possible.
Switching From Developer Plan To A Chat Plan
You can switch back to a fixed monthly chat plan.
Unused credits stay on your organization and do not expire.
Stored credits are only used while your organization is on request pricing.
Cancelling Developer Plan
Cancelling stops future monthly credit top-ups.
Existing credits remain available until used.
Once your credit balance reaches zero or below, request-pricing API calls are blocked unless you restart request pricing or add more credits.
Refunds And Adjustments
Refunds or account adjustments may reduce your credit balance.
Contact support if you have questions about a balance change.