> ## Documentation Index > Fetch the complete documentation index at: https://impossibl.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Supported models and pricing > Every model the gateway serves, how each request is priced against your credit balance, and how to top up with a hosted Stripe invoice in one call. Pick a model with the `provider/model` convention and pass it as the `model` field. The live, authoritative list (with current pricing) is always at `GET /v1/models`. ## Available models ### Audio transcription | Model | Endpoint | Price | | ----------------------- | ------------------------------- | ----------------------- | | `openai/gpt-transcribe` | `POST /v1/audio/transcriptions` | \$0.0045 / audio minute | See [Audio transcription](/docs/audio-transcription) for a copy-paste file upload and streaming example. ### Image generation `openai/gpt-image-2` generates images via `POST /v1/images/generations`, billed per token at the rates in the table below (text input plus image output tokens). See [Image generation](/docs/image-generation) for the request shape and options. ### Token-priced models | Model | Context | Input / 1M | Output / 1M | | ---------------------------------- | --------- | ---------- | ----------- | | `openai/gpt-5.6-sol` | 1050K | \$5.00 | \$30.00 | | `openai/gpt-5.6-luna` | 1050K | \$1.00 | \$6.00 | | `openai/gpt-5.6-terra` | 1050K | \$2.50 | \$15.00 | | `openai/gpt-image-2` | 32K | \$5.00 | \$30.00 | | `openai/gpt-5.5` | 1050K | \$5.00 | \$30.00 | | `openai/gpt-5.5-pro` | 1050K | \$30.00 | \$180.00 | | `openai/gpt-5.4` | 1050K | \$2.50 | \$15.00 | | `openai/gpt-5.4-mini` | 400K | \$0.75 | \$4.50 | | `openai/gpt-5.4-nano` | 400K | \$0.20 | \$1.25 | | `openai/gpt-5.4-pro` | 1050K | \$30.00 | \$180.00 | | `openai/gpt-5.3-codex` | 400K | \$1.75 | \$14.00 | | `openai/gpt-5.1` | 400K | \$1.25 | \$10.00 | | `openai/gpt-5.2` | 400K | \$1.75 | \$14.00 | | `openai/gpt-5.2-codex` | 400K | \$1.75 | \$14.00 | | `openai/gpt-5.1-codex` | 400K | \$1.25 | \$10.00 | | `openai/gpt-5.1-codex-mini` | 400K | \$0.25 | \$2.00 | | `openai/gpt-chat-latest` | 400K | \$5.00 | \$30.00 | | `openai/gpt-5` | 400K | \$1.25 | \$10.00 | | `openai/gpt-5-pro` | 400K | \$15.00 | \$120.00 | | `openai/gpt-5-codex` | 400K | \$1.25 | \$10.00 | | `openai/gpt-5-mini` | 400K | \$0.25 | \$2.00 | | `openai/gpt-5-nano` | 400K | \$0.05 | \$0.40 | | `openai/gpt-4.1` | 1M | \$2.00 | \$8.00 | | `openai/gpt-4.1-mini` | 1M | \$0.40 | \$1.60 | | `openai/gpt-4.1-nano` | 1M | \$0.10 | \$0.40 | | `openai/gpt-4o` | 128K | \$2.50 | \$10.00 | | `openai/gpt-4o-mini` | 128K | \$0.15 | \$0.60 | | `openai/gpt-4-turbo` | 128K | \$10.00 | \$30.00 | | `openai/gpt-3.5-turbo` | 16K | \$0.50 | \$1.50 | | `openai/o3` | 200K | \$2.00 | \$8.00 | | `openai/o3-mini` | 200K | \$1.10 | \$4.40 | | `openai/o4-mini` | 200K | \$1.10 | \$4.40 | | `openai/o1` | 200K | \$15.00 | \$60.00 | | `anthropic/claude-opus-5` | 1M | \$5.00 | \$25.00 | | `anthropic/claude-fable-5` | 1M | \$10.00 | \$50.00 | | `anthropic/claude-opus-4-8` | 1M | \$5.00 | \$25.00 | | `anthropic/claude-opus-4-7` | 1M | \$5.00 | \$25.00 | | `anthropic/claude-opus-4-6` | 1M | \$5.00 | \$25.00 | | `anthropic/claude-sonnet-5` | 1M | \$3.00 | \$15.00 | | `anthropic/claude-sonnet-4-6` | 1M | \$3.00 | \$15.00 | | `anthropic/claude-haiku-4-5` | 200K | \$1.00 | \$5.00 | | `anthropic/claude-opus-4-5` | 200K | \$5.00 | \$25.00 | | `anthropic/claude-sonnet-4-5` | 200K | \$3.00 | \$15.00 | | `google/gemini-3.6-flash` | 1048.576K | \$1.50 | \$7.50 | | `google/gemini-3.5-flash` | 1M | \$1.50 | \$9.00 | | `google/gemini-3.5-flash-lite` | 1048.576K | \$0.30 | \$2.50 | | `google/gemini-3.1-pro-preview` | 1M | \$2.00 | \$12.00 | | `google/gemini-3.1-flash-lite` | 1M | \$0.25 | \$1.50 | | `google/gemini-2.5-pro` | 1M | \$1.25 | \$10.00 | | `google/gemini-2.5-flash` | 1M | \$0.30 | \$2.50 | | `google/gemini-2.5-flash-lite` | 1M | \$0.10 | \$0.40 | | `xai/grok-4.5` | 500K | \$2.00 | \$6.00 | | `xai/grok-4.3` | 1M | \$1.25 | \$2.50 | | `xai/grok-4.20-0309-reasoning` | 1M | \$1.25 | \$2.50 | | `xai/grok-4.20-0309-non-reasoning` | 1M | \$1.25 | \$2.50 | | `xai/grok-4.20-multi-agent-0309` | 1M | \$1.25 | \$2.50 | | `xai/grok-build-0.1` | 256K | \$1.00 | \$2.00 | | `meta/llama-3.3-70b` | 128K | \$0.71 | \$0.71 | | `mistral/mistral-large-3` | 128K | \$0.50 | \$1.50 | | `microsoft/phi-4` | 16K | \$0.125 | \$0.50 | | `deepseek/deepseek-v4-flash` | 1M | \$0.19 | \$0.51 | | `deepseek/deepseek-v4-pro` | 1M | \$1.74 | \$3.48 | | `deepseek/deepseek-v3-2` | 163.84K | \$0.58 | \$1.68 | | `deepseek/deepseek-v3-2-speciale` | 163.84K | \$0.58 | \$1.68 | | `zai/glm-5.2` | 1M | \$1.40 | \$4.40 | | `zai/glm-5.1` | 200K | \$1.40 | \$4.40 | | `zai/glm-5` | 200K | \$1.00 | \$3.20 | | `zai/glm-5-turbo` | 200K | \$1.20 | \$4.00 | | `zai/glm-4.7` | 200K | \$0.60 | \$2.20 | | `zai/glm-4.6` | 200K | \$0.60 | \$2.20 | | `zai/glm-4.5` | 128K | \$0.60 | \$2.20 | | `zai/glm-4.5-air` | 128K | \$0.20 | \$1.10 | | `moonshotai/kimi-k3` | 1048.576K | \$3.00 | \$15.00 | | `qwen/qwen3.7-max` | 1048.576K | \$2.50 | \$7.50 | | `qwen/qwen3.7-plus` | 1048.576K | \$0.40 | \$1.60 | | `qwen/qwen3.6-flash` | 1048.576K | \$0.25 | \$1.50 | | `qwen/qwen3.8-max-preview` | 1048.576K | \$2.50 | \$7.50 | | `xiaomi/mimo-v2.5` | 1024K | \$0.14 | \$0.28 | | `minimaxai/minimax-m3` | 524.3K | \$0.30 | \$1.20 | | `tencent/hy3` | 262.144K | \$0.20 | \$0.80 | | `cerebras/gpt-oss-120b` | 128K | \$0.35 | \$0.75 | | `cerebras/zai-glm-4.7` | 128K | \$2.25 | \$2.75 | | `cerebras/gemma-4-31b` | 128K | \$0.99 | \$1.49 | | `groq/gpt-oss-120b` | 128K | \$0.15 | \$0.60 | | `groq/gpt-oss-20b` | 128K | \$0.075 | \$0.30 | | `groq/llama-3.3-70b-versatile` | 128K | \$0.59 | \$0.79 | | `groq/llama-3.1-8b-instant` | 128K | \$0.05 | \$0.08 | | `fireworks/glm-5.2` | 1040K | \$1.40 | \$4.40 | | `fireworks/glm-5.2-fast` | 1040K | \$2.10 | \$6.60 | | `fireworks/qwen3.7-plus` | 262.144K | \$0.40 | \$1.60 | | `fireworks/gpt-oss-120b` | 128K | \$0.15 | \$0.60 | | `fireworks/gpt-oss-20b` | 128K | \$0.07 | \$0.30 | | `thinkingmachines/inkling` | 65.536K | \$1.87 | \$4.68 | | `thinkingmachines/inkling-256k` | 262.144K | \$3.74 | \$9.36 | Token prices are USD per 1M tokens. More providers and models are added over time. `anthropic/claude-sonnet-5` is currently promo-priced at **$2.00 / $10.00** (through 2026-08-31) — `GET /v1/models` always returns the effective price you're billed at. Fireworks also supports serverless passthrough for any public serverless model in the Fireworks catalog. Use either `fireworks/` or the full `fireworks/accounts/fireworks/models/` id. Unlisted passthrough models are billed at the conservative fallback price configured in the gateway. ## Credits Usage is billed from a **prepaid credit balance**. Credits are denominated in **micro-USD**: * **1 credit = $0.000001**, so **$1.00 = 1,000,000 credits** * Buying $10 in credits adds 10,000,000 credits. The fixed 5% platform fee is $0.50, making the pre-tax total \$10.50 * New accounts get a signup bonus so the first call works immediately ## How a request is priced ``` cost_credits = ⌈ input_tokens × input_price + output_tokens × output_price ⌉ ``` where `input_price` / `output_price` are the per-1M-token prices above. Provider usage is billed at the provider's list price with no usage markup (`PRICE_MARKUP=1.0`). Because a credit is one micro-USD, the "per 1M" division cancels: `tokens × price` is already micro-USD. The amount is rounded **up**, deducted atomically when the request finishes, and recorded in the usage ledger (`GET /v1/usage`). Some models carry more than the two base rates, and the formula extends the same way — each token class times its own rate, summed, rounded up once. `GET /v1/models` reports every rate that applies to a model: * `audio_input_per_mtok_usd` — audio input tokens priced above the text rate (see [Audio & video input](/docs/audio-video#billing)) * `cached_input_per_mtok_usd` / `cache_write_per_mtok_usd` — prompt-cache reads and writes * `context_price_tiers` — long-context brackets: once the prompt crosses a tier's threshold, its rates apply to the request Audio transcription uses duration instead: ``` cost_credits = ⌈ audio_seconds ÷ 60 × 0.0045 × 1,000,000 ⌉ ``` The gateway prefers duration usage reported by OpenAI and otherwise reads the uploaded audio file's duration. It charges only after the transcription completes successfully. Example — `gpt-4o-mini`, 11 input + 3 output tokens: `⌈11 × 0.15 + 3 × 0.60⌉ = ⌈3.45⌉ = 4 credits` (\$0.000004). For self-hosted deployments, `PRICE_MARKUP` multiplies this provider-usage formula to set a margin. AI API production keeps it at `1.0`. The separate fixed 5% platform fee applies only when prepaid credits are purchased. If your balance is empty, model endpoints return `402` (see [Errors](/docs/errors)). Check your balance with `GET /v1/account`. Requests routed through your own provider credential ([BYOK](/docs/byok)) skip this formula entirely — they're billed 0 credits, since the provider charges you directly. ## Topping up Buy credits with a hosted Stripe Invoice: ```bash theme={null} curl -X POST https://api.impossibl.com/v1/billing/invoice \ -H "Authorization: Bearer imp-rt-..." \ -H 'content-type: application/json' \ -d '{"amount_usd": 10}' ``` ```json theme={null} { "invoice_url": "https://invoice.stripe.com/i/...", "invoice_id": "in_...", "credit_amount_cents": 1000, "platform_fee_cents": 50, "invoice_amount_cents": 1050 } ``` Open `invoice_url` and pay. Credits are added automatically once the invoice is paid, and Stripe retries cannot double-credit them. The minimum top-up is \*\*$5**, and fractional amounts are rounded down to a whole dollar. A fixed 5% platform fee is added to the net credit amount, so $10 of credits has a $0.50 fee and costs $10.50 before tax. The invoice has a single `Impossible Credits` line item covering the credits and fee. Stripe Tax adds VAT or sales tax on top when enabled. `GET /v1/billing` shows your balance, the minimum top-up, the fixed platform fee rate, and the provider-usage multiplier.