Support
One eight-turn conversation, priced with the history re-sent on every turn — the way chat actually bills.
Pricing verified:
Between $0.0003 and $0.021 per run, depending on the model. That is a 80× spread for the same job.
A system prompt plus eight turns of conversation, with the full history re-sent each turn, sums to ≈ 6,000 input tokens across the conversation. Eight replies ≈ 900 output tokens.
Cost = (input tokens ÷ 1M × input price) + (output tokens ÷ 1M × output price). Prices come from our daily-verified model data. Batch and cached-input discounts are not applied — they only ever make these numbers smaller.
| Model | Provider | Per run | At 10,000 conversations a month | Context |
|---|---|---|---|---|
| Gemma 2 9B | $0.0003 | $2.61 | 8k tokens | |
| Llama 3.2 1B Instruct | Meta | $0.0003 | $3.42 | 60k tokens |
| Llama 3.1 8B Instruct | Meta | $0.0004 | $3.72 | 16k tokens |
| gpt-oss-safeguard-20b | OpenAI | $0.0006 | $6.00 | 131k tokens |
| Mistral Small 3.2 24B | Mistral | $0.0006 | $6.30 | 128k tokens |
| GPT-5 Nano | OpenAI | $0.0007 | $6.60 | 400k tokens |
| Ministral 3 3B 2512 | Mistral | $0.0007 | $6.90 | 131k tokens |
| Gemini 2.0 Flash Lite | $0.0007 | $7.20 | 1.0M tokens | |
| Mistral 7B Instruct v0.1needs chunking | Mistral | $0.0008 | $8.31 | 3k tokens |
| Devstral Small 1.1 | Mistral | $0.0009 | $8.70 | 131k tokens |
| Mistral Small Creative | Mistral | $0.0009 | $8.70 | 33k tokens |
| Voxtral Small 24B 2507 | Mistral | $0.0009 | $8.70 | 32k tokens |
| Mistral Small 3.1 | Mistral | $0.0009 | $8.70 | 128k tokens |
| Gemini 2.0 Flash | $0.0010 | $9.60 | 1.0M tokens | |
| Gemini 2.5 Flash Lite | $0.0010 | $9.60 | 1.0M tokens | |
| Gemini 2.5 Flash Lite Preview 09-2025 | $0.0010 | $9.60 | 1.0M tokens | |
| GPT-4.1 Nano | OpenAI | $0.0010 | $9.60 | 1.0M tokens |
| Llama 3 8B Instruct | Meta | $0.0010 | $9.66 | 8k tokens |
| Ministral 3 8B 2512 | Mistral | $0.0010 | $10.35 | 262k tokens |
| Mistral Nemo | Mistral | $0.0010 | $10.35 | 131k tokens |
| DeepSeek V4-Flash | DeepSeek | $0.0011 | $10.92 | 1M tokens |
| Gemma 4 26B A4B | $0.0011 | $11.40 | 262k tokens | |
| Llama Guard 4 12B | Meta | $0.0012 | $12.42 | 164k tokens |
| GLM-5.3 Flash | Z.ai | $0.0014 | $13.50 | 1M tokens |
| Ministral 3 14B 2512 | Mistral | $0.0014 | $13.80 | 262k tokens |
| Qwen 3.8 Flash | Alibaba | $0.0014 | $13.83 | 991k tokens |
| GPT-4o Mini | OpenAI | $0.0014 | $14.40 | 128k tokens |
| Mistral Small 4 | Mistral | $0.0014 | $14.40 | 262k tokens |
| Saba | Mistral | $0.0017 | $17.40 | 33k tokens |
| Grok 3 Mini | xAI | $0.0022 | $22.50 | 131k tokens |
| Grok 3 Mini Beta | xAI | $0.0022 | $22.50 | 131k tokens |
| GPT-5.6 Luna | OpenAI | $0.0023 | $22.80 | 1.1M tokens |
| Llama 3.2 11B Vision Instruct | Meta | $0.0024 | $23.80 | 131k tokens |
| Grok Code Fast 1 | xAI | $0.0026 | $25.50 | 256k tokens |
| Mistral Small 3 | Mistral | $0.0026 | $26.05 | 33k tokens |
| Codestral 2508 | Mistral | $0.0026 | $26.10 | 256k tokens |
| DeepSeek V3 | DeepSeek | $0.0026 | $26.10 | 128k tokens |
| Claude 3 Haiku | Anthropic | $0.0026 | $26.25 | 200k tokens |
| Llama 3.1 70B Instruct | Meta | $0.0028 | $27.60 | 131k tokens |
| Gemini 3 Flash Preview | $0.0029 | $28.50 | 1.0M tokens | |
| Llama Guard 3 8B | Meta | $0.0029 | $29.07 | 131k tokens |
| Gemma 4 31B | $0.0032 | $32.13 | 262k tokens | |
| GPT-5 Mini | OpenAI | $0.0033 | $33.00 | 400k tokens |
| GPT-5.1-Codex-Mini | OpenAI | $0.0033 | $33.00 | 400k tokens |
| DeepSeek V4-Pro | DeepSeek | $0.0034 | $33.93 | 1M tokens |
| Muse Glimmer 30B | Meta | $0.0034 | $34.50 | 131k tokens |
| Llama 3 70B Instruct | Meta | $0.0037 | $37.26 | 8k tokens |
| Mixtral 8x7B Instruct | Mistral | $0.0037 | $37.26 | 33k tokens |
| GPT-4.1 Mini | OpenAI | $0.0038 | $38.40 | 1.0M tokens |
| Gemini 2.5 Flash | $0.0040 | $40.50 | 1.0M tokens | |
| Gemini 3.5 Flash-Lite | $0.0040 | $40.50 | 1.0M tokens | |
| Nano Banana (Gemini 2.5 Flash Image) | $0.0040 | $40.50 | 33k tokens | |
| Llama 4 Scout | Meta | $0.0041 | $40.80 | 512k tokens |
| Devstral 2 2512 | Mistral | $0.0042 | $42.00 | 262k tokens |
| Devstral Medium | Mistral | $0.0042 | $42.00 | 131k tokens |
| Mistral Medium 3 | Mistral | $0.0042 | $42.00 | 131k tokens |
| Mistral Medium 3.1 | Mistral | $0.0042 | $42.00 | 131k tokens |
| GPT-3.5 Turbo | OpenAI | $0.0043 | $43.50 | 16k tokens |
| Mistral Large 3 2512 | Mistral | $0.0043 | $43.50 | 262k tokens |
| Gemma 2 27B | $0.0045 | $44.85 | 8k tokens | |
| Llama 4 Maverick | Meta | $0.0050 | $50.40 | 256k tokens |
| DeepSeek R1 | DeepSeek | $0.0053 | $52.71 | 128k tokens |
| Gemini 3.1 Flash | $0.0057 | $57.00 | 1M tokens | |
| GPT Audio Mini | OpenAI | $0.0058 | $57.60 | 128k tokens |
| GPT-3.5 Turbo (older v0613)needs chunking | OpenAI | $0.0078 | $78.00 | 4k tokens |
| Codestral 25.01 | Mistral | $0.0078 | $78.30 | 256k tokens |
| Gemini 3.6 Flash | $0.0079 | $78.75 | 1.0M tokens | |
| Gemini 3.7 Flash | $0.0079 | $78.75 | 1.0M tokens | |
| Claude 3.5 Haiku | Anthropic | $0.0084 | $84.00 | 200k tokens |
| Claude 4 Haiku | Anthropic | $0.0084 | $84.00 | 200k tokens |
| Kimi K2.7 Code | Moonshot | $0.0093 | $93.00 | 256k tokens |
| Claude Haiku 4.5 | Anthropic | $0.010 | $105 | 200k tokens |
| o3 Mini | OpenAI | $0.011 | $106 | 200k tokens |
| o3 Mini High | OpenAI | $0.011 | $106 | 200k tokens |
| o4 Mini | OpenAI | $0.011 | $106 | 200k tokens |
| o4 Mini High | OpenAI | $0.011 | $106 | 200k tokens |
| GPT-3.5 Turbo Instructneeds chunking | OpenAI | $0.011 | $108 | 4k tokens |
| Muse Spark | Meta | $0.011 | $113 | 1.0M tokens |
| GPT-5.2 Mini | OpenAI | $0.012 | $115 | 128k tokens |
| GLM-5.2 | Z.ai | $0.012 | $124 | 1M tokens |
| GLM-5.3 | Z.ai | $0.012 | $124 | 1M tokens |
| Mistral Medium 3.5 | Mistral | $0.016 | $158 | 256k tokens |
| GPT-5 | OpenAI | $0.017 | $165 | 400k tokens |
| GPT-5 Chat | OpenAI | $0.017 | $165 | 128k tokens |
| GPT-5 Codex | OpenAI | $0.017 | $165 | 400k tokens |
| GPT-5.1 | OpenAI | $0.017 | $165 | 400k tokens |
| GPT-5.1 Chat | OpenAI | $0.017 | $165 | 128k tokens |
| GPT-5.1-Codex | OpenAI | $0.017 | $165 | 400k tokens |
| GPT-5.1-Codex-Max | OpenAI | $0.017 | $165 | 400k tokens |
| Gemini 2.5 Pro | $0.017 | $165 | 1.0M tokens | |
| Gemini 2.5 Pro Preview 05-06 | $0.017 | $165 | 1.0M tokens | |
| Gemini 2.5 Pro Preview 06-05 | $0.017 | $165 | 1.0M tokens | |
| GPT-5 Image Mini | OpenAI | $0.017 | $168 | 400k tokens |
| Gemini 3.5 Flash | $0.017 | $171 | 1.0M tokens | |
| Grok 4 | xAI | $0.017 | $174 | 2M tokens |
| Grok 4.5 | xAI | $0.017 | $174 | 500k tokens |
| Grok 4.6 | xAI | $0.017 | $174 | 500k tokens |
| Mixtral 8x22B Instruct | Mistral | $0.017 | $174 | 66k tokens |
| Pixtral Large 2411 | Mistral | $0.017 | $174 | 131k tokens |
| Qwen 3.8 Max | Alibaba | $0.017 | $174 | 1M tokens |
| GPT-4.1 | OpenAI | $0.019 | $192 | 1.0M tokens |
| o3 | OpenAI | $0.019 | $192 | 200k tokens |
| o4 Mini Deep Research | OpenAI | $0.019 | $192 | 200k tokens |
| Claude Sonnet 5 | Anthropic | $0.021 | $210 | 1M tokens |
| GPT-5.6 Sol | OpenAI | $0.021 | $210 | 1.1M tokens |
| GPT-3.5 Turbo 16k | OpenAI | $0.022 | $216 | 16k tokens |
| Qwen 3.7 Max | Alibaba | $0.022 | $217 | 1M tokens |
| GPT-5.6 Terra | OpenAI | $0.023 | $228 | 1.1M tokens |
| Gemini 3.1 Pro | $0.023 | $228 | 2M tokens | |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | $0.023 | $228 | 66k tokens | |
| GPT-5.2 | OpenAI | $0.023 | $231 | 200k tokens |
| GPT-5.3 Chat | OpenAI | $0.023 | $231 | 128k tokens |
| GPT-5.3-Codex | OpenAI | $0.023 | $231 | 400k tokens |
| GPT Audio | OpenAI | $0.024 | $240 | 128k tokens |
| GPT-4o | OpenAI | $0.024 | $240 | 128k tokens |
| Mistral Large 2 | Mistral | $0.026 | $261 | 128k tokens |
| GPT-5.4 | OpenAI | $0.028 | $285 | 272k tokens |
| Claude 3.7 Sonnet (thinking) | Anthropic | $0.032 | $315 | 200k tokens |
| Claude Sonnet 4 | Anthropic | $0.032 | $315 | 200k tokens |
| Claude Sonnet 4.5 | Anthropic | $0.032 | $315 | 1M tokens |
| Claude Sonnet 4.6 | Anthropic | $0.032 | $315 | 1M tokens |
| Grok 3 | xAI | $0.032 | $315 | 131k tokens |
| Grok 3 Beta | xAI | $0.032 | $315 | 131k tokens |
| Kimi K3 | Moonshot | $0.032 | $315 | 1M tokens |
| Claude Opus 4.5 | Anthropic | $0.052 | $525 | 200k tokens |
| Claude Opus 4.6 | Anthropic | $0.052 | $525 | 1M tokens |
| Claude Opus 4.7 | Anthropic | $0.052 | $525 | 1M tokens |
| Claude Opus 4.8 | Anthropic | $0.052 | $525 | 1M tokens |
| Claude Opus 5 | Anthropic | $0.052 | $525 | 1M tokens |
| GPT-5.5 | OpenAI | $0.057 | $570 | 1M tokens |
| Claude 3.5 Sonnet | Anthropic | $0.063 | $630 | 200k tokens |
| GPT-5 Image | OpenAI | $0.069 | $690 | 400k tokens |
| GPT-4 Turbo | OpenAI | $0.087 | $870 | 128k tokens |
| GPT-4 Turbo (older v1106) | OpenAI | $0.087 | $870 | 128k tokens |
| GPT-4 Turbo Preview | OpenAI | $0.087 | $870 | 128k tokens |
| o3 Deep Research | OpenAI | $0.096 | $960 | 200k tokens |
| Claude Fable 5 | Anthropic | $0.105 | $1,050 | 1M tokens |
| Claude Fable 5.1 | Anthropic | $0.105 | $1,050 | 1M tokens |
| Claude Mythos 5 | Anthropic | $0.105 | $1,050 | 1M tokens |
| Claude Mythos 5.1 | Anthropic | $0.105 | $1,050 | 1M tokens |
| GPT-6 Astra | OpenAI | $0.105 | $1,050 | 1.1M tokens |
| o1 | OpenAI | $0.144 | $1,440 | 200k tokens |
| Claude Opus 4 | Anthropic | $0.158 | $1,575 | 200k tokens |
| Claude Opus 4.1 | Anthropic | $0.158 | $1,575 | 200k tokens |
| o3 Pro | OpenAI | $0.192 | $1,920 | 200k tokens |
| GPT-5 Pro | OpenAI | $0.198 | $1,980 | 400k tokens |
| GPT-4 | OpenAI | $0.234 | $2,340 | 8k tokens |
| GPT-4 (older v0314) | OpenAI | $0.234 | $2,340 | 8k tokens |
| o1-pro | OpenAI | $1.44 | $14,400 | 200k tokens |
“Needs chunking” means the model's context window can't hold this job in a single pass, so the real cost is higher than the figure shown and quality usually suffers.
Chat bills quadratically, not linearly: every turn re-sends the whole history, so a sixteen-turn conversation costs roughly four times an eight-turn one rather than twice. Prompt caching targets exactly this and can cut the input side by up to 90% on a stable system prompt.
$0.0003 on Gemma 2 9B, the cheapest capable option, rising to $0.021 on Claude Sonnet 5 at the top end. GPT-5.6 Luna is the value pick at $0.0023 per run. The job is priced at 6,000 input and 900 output tokens — see the working below.
A system prompt plus eight turns of conversation, with the full history re-sent each turn, sums to ≈ 6,000 input tokens across the conversation. Eight replies ≈ 900 output tokens.
$2.61 a month on Gemma 2 9B, $22.80 on GPT-5.6 Luna, and $210 on Claude Sonnet 5. Batch APIs typically halve these figures for work that can wait, and prompt caching cuts the input side further when the same context is reused.
Chat bills quadratically, not linearly: every turn re-sends the whole history, so a sixteen-turn conversation costs roughly four times an eight-turn one rather than twice. Prompt caching targets exactly this and can cut the input side by up to 90% on a stable system prompt.
Yes. Every figure on this page is computed from our model pricing data, which is checked daily against each provider's official pricing page. When a provider changes a price, these numbers change with it.
Newsletter
Pricing changes, new model releases, and updated recommendations — delivered when it matters.
No spam. Useful updates only. Affiliate disclosures always clearly labeled.