# LLM API pricing per million tokens - Agent Ping

> List prices for 95 models from 7 providers, USD per 1,000,000 tokens,
> standard tier, taken from each provider's own pricing page. This is also the default
> rate card Agent Ping (https://agentping.io) prices every agent run with.
> Last verified: 2026-10-17. HTML version: https://agentping.io/llm-api-pricing
> JSON version: https://agentping.io/llm-api-pricing.json

Columns: input, cached input (cache read), cache write, output, batch discount. A dash means the
provider publishes no such rate. Status: current, legacy, or retired.

## Anthropic

Source: https://platform.claude.com/docs/en/about-claude/pricing

Cache write is the 5-minute cache; the 1-hour cache is 2x input. Cache reads are 0.1x input on most models, 0.05x on Opus 5.5 and Sonnet 5.5, 0.025x on Fable 5.1 and Mythos 5.1. Batch API is 50% off. Haiku 5.5 prompts over 100k tokens bill at $0.50 / $2.50.

| Model | Model id | Input | Cached input | Cache write | Output | Batch | Status | Notes |
|---|---|---:|---:|---:|---:|---:|---|---|
| Claude Fable 5.1 | `claude-fable-5-1` | $10 | $0.25 | $12.5 | $50 | 50% off | current |  |
| Claude Mythos 5.1 | `claude-mythos-5-1` | $10 | $0.25 | $12.5 | $50 | 50% off | current | Limited availability. |
| Claude Fable 5 | `claude-fable-5` | $10 | $1 | $12.5 | $50 | 50% off | current |  |
| Claude Mythos 5 | `claude-mythos-5` | $10 | $1 | $12.5 | $50 | 50% off | current | Limited availability. |
| Claude Opus 5.5 | `claude-opus-5-5` | $4 | $0.2 | $5 | $20 | 50% off | current |  |
| Claude Opus 5 | `claude-opus-5` | $5 | $0.5 | $6.25 | $25 | 50% off | current |  |
| Claude Opus 4.8 | `claude-opus-4-8` | $5 | $0.5 | $6.25 | $25 | 50% off | current |  |
| Claude Opus 4.7 | `claude-opus-4-7` | $5 | $0.5 | $6.25 | $25 | 50% off | current |  |
| Claude Opus 4.6 | `claude-opus-4-6` | $5 | $0.5 | $6.25 | $25 | 50% off | current |  |
| Claude Opus 4.5 | `claude-opus-4-5` | $5 | $0.5 | $6.25 | $25 | 50% off | current |  |
| Claude Opus 4.1 | `claude-opus-4-1` | $15 | $1.5 | $18.75 | $75 | 50% off | retired | Retired on the Claude API; still on Bedrock and Google Cloud. |
| Claude Opus 4 | `claude-opus-4` | $15 | $1.5 | $18.75 | $75 | 50% off | retired | Retired on the Claude API; still on Google Cloud. |
| Claude Sonnet 5.5 | `claude-sonnet-5-5` | $2 | $0.1 | $2.5 | $10 | 50% off | current |  |
| Claude Sonnet 5 | `claude-sonnet-5` | $2 | $0.2 | $2.5 | $10 | 50% off | current |  |
| Claude Sonnet 4.6 | `claude-sonnet-4-6` | $3 | $0.3 | $3.75 | $15 | 50% off | current |  |
| Claude Sonnet 4.5 | `claude-sonnet-4-5` | $3 | $0.3 | $3.75 | $15 | 50% off | legacy |  |
| Claude Sonnet 4 | `claude-sonnet-4` | $3 | $0.3 | $3.75 | $15 | 50% off | retired | Retired on the Claude API; still on Bedrock and Google Cloud. |
| Claude Haiku 5.5 | `claude-haiku-5-5` | $0.1 | $0.01 | $0.125 | $0.5 | 50% off | current | Prompts over 100k tokens bill at $0.50 input / $2.50 output. |
| Claude Haiku 4.5 | `claude-haiku-4-5` | $1 | $0.1 | $1.25 | $5 | 50% off | legacy |  |
| Claude Haiku 3.5 | `claude-3-5-haiku` | $0.8 | $0.08 | $1 | $4 | 50% off | retired | Retired on the Claude API; still on Google Cloud. |

## OpenAI

Source: https://developers.openai.com/api/docs/pricing

No charge for cache writes. Batch API is 50% off. GPT-5.4 and later, GPT-5.5 and the GPT-6 family bill prompts over 272k input tokens at roughly 2x input and 1.5x output. Pro models have no cached-input rate.

| Model | Model id | Input | Cached input | Cache write | Output | Batch | Status | Notes |
|---|---|---:|---:|---:|---:|---:|---|---|
| GPT-6 Astra | `gpt-6-astra` | $10 | $1 | - | $50 | 50% off | current | Over 272k input tokens: $20 / $75. |
| GPT-6.1 Sol | `gpt-6.1-sol` | $2 | $0.1 | - | $10 | 50% off | current | Over 272k input tokens: $4 / $15. |
| GPT-6 Sol | `gpt-6-sol` | $2 | $0.2 | - | $10 | 50% off | current | Over 272k input tokens: $4 / $15. |
| GPT-6 Luna | `gpt-6-luna` | $0.1 | $0.01 | - | $0.5 | 50% off | current | Over 272k input tokens: $0.20 / $0.75. |
| GPT-5.6 Sol | `gpt-5.6-sol` | $4 | $0.4 | - | $20 | 50% off | current | Over 272k input tokens: $8 / $30. |
| GPT-5.6 Terra | `gpt-5.6-terra` | $2 | $0.2 | - | $12 | 50% off | current | Over 272k input tokens: $4 / $18. |
| GPT-5.6 Luna | `gpt-5.6-luna` | $0.2 | $0.02 | - | $1.2 | 50% off | current | Over 272k input tokens: $0.40 / $1.80. |
| GPT-5.5 | `gpt-5.5` | $5 | $0.5 | - | $30 | 50% off | current | Over 272k input tokens: $10 / $45. |
| GPT-5.5 Pro | `gpt-5.5-pro` | $30 | - | - | $180 | 50% off | current | No cached-input rate. Over 272k input tokens: $60 / $270. |
| GPT-5.4 | `gpt-5.4` | $2.5 | $0.25 | - | $15 | 50% off | current | Over 272k input tokens: $5 / $22.50. |
| GPT-5.4 Mini | `gpt-5.4-mini` | $0.75 | $0.075 | - | $4.5 | 50% off | current |  |
| GPT-5.4 Nano | `gpt-5.4-nano` | $0.2 | $0.02 | - | $1.25 | 50% off | current |  |
| GPT-5.4 Pro | `gpt-5.4-pro` | $30 | - | - | $180 | 50% off | current | No cached-input rate. Over 272k input tokens: $60 / $270. |
| GPT-5.2 | `gpt-5.2` | $1.75 | $0.175 | - | $14 | 50% off | current |  |
| GPT-5.2 Pro | `gpt-5.2-pro` | $21 | - | - | $168 | 50% off | current | No cached-input rate. |
| GPT-5.1 | `gpt-5.1` | $1.25 | $0.125 | - | $10 | 50% off | current |  |
| GPT-5 | `gpt-5` | $1.25 | $0.125 | - | $10 | 50% off | current |  |
| GPT-5 Mini | `gpt-5-mini` | $0.25 | $0.025 | - | $2 | 50% off | current |  |
| GPT-5 Nano | `gpt-5-nano` | $0.05 | $0.005 | - | $0.4 | 50% off | current |  |
| GPT-5 Pro | `gpt-5-pro` | $15 | - | - | $120 | 50% off | current | No cached-input rate. |
| GPT-4.1 | `gpt-4.1` | $2 | $0.5 | - | $8 | 50% off | legacy |  |
| GPT-4.1 Mini | `gpt-4.1-mini` | $0.4 | $0.1 | - | $1.6 | 50% off | legacy |  |
| GPT-4.1 Nano | `gpt-4.1-nano` | $0.1 | $0.025 | - | $0.4 | 50% off | legacy |  |
| GPT-4o | `gpt-4o` | $2.5 | $1.25 | - | $10 | 50% off | legacy |  |
| GPT-4o Mini | `gpt-4o-mini` | $0.15 | $0.075 | - | $0.6 | 50% off | legacy |  |
| o3 | `o3` | $2 | $0.5 | - | $8 | 50% off | legacy |  |
| o3-pro | `o3-pro` | $20 | - | - | $80 | 50% off | legacy | No cached-input rate. |
| o3-mini | `o3-mini` | $1.1 | $0.55 | - | $4.4 | 50% off | legacy |  |
| o4-mini | `o4-mini` | $1.1 | $0.275 | - | $4.4 | 50% off | legacy |  |
| o1 | `o1` | $15 | $7.5 | - | $60 | 50% off | legacy |  |

## Google Gemini

Source: https://ai.google.dev/gemini-api/docs/pricing

Paid tier, text input. Context caching bills storage per hour instead of a per-token write. Batch is 50% off. Pro models bill prompts over 200k tokens at 2x input and 1.5x output. Gemini 4 Argon list price doubles on 1 December 2026; the 3.6 and 3.8 Flash introductory prices end 1 January 2027.

| Model | Model id | Input | Cached input | Cache write | Output | Batch | Status | Notes |
|---|---|---:|---:|---:|---:|---:|---|---|
| Gemini 4 Argon | `gemini-4-argon` | $2 | $0.1 | - | $10 | 50% off | current | Rises to $4 / $20 on 1 December 2026. Not on the free tier. |
| Gemini 3.8 Flash | `gemini-3.8-flash` | $0.75 | $0.075 | - | $3.75 | 50% off | current | Introductory; $1.50 / $7.50 from 1 January 2027. |
| Gemini 3.6 Flash | `gemini-3.6-flash` | $0.75 | $0.075 | - | $3.75 | 50% off | legacy | Introductory; $1.50 / $7.50 from 1 January 2027. |
| Gemini 3.5 Flash-Lite | `gemini-3.5-flash-lite` | $0.3 | $0.03 | - | $2.5 | 50% off | current |  |
| Gemini 3.1 Flash-Lite | `gemini-3.1-flash-lite` | $0.25 | $0.025 | - | $1.5 | 50% off | current |  |
| Gemini 3.1 Pro Preview | `gemini-3.1-pro-preview` | $2 | $0.2 | - | $12 | 50% off | current | Over 200k tokens: $4 / $18. |
| Gemini 3 Flash Preview | `gemini-3-flash-preview` | $0.5 | $0.05 | - | $3 | 50% off | legacy |  |
| Gemini 2.5 Pro | `gemini-2.5-pro` | $1.25 | $0.125 | - | $10 | 50% off | legacy | Over 200k tokens: $2.50 / $15. |
| Gemini 2.5 Flash | `gemini-2.5-flash` | $0.3 | $0.03 | - | $2.5 | 50% off | legacy |  |
| Gemini 2.5 Flash-Lite | `gemini-2.5-flash-lite` | $0.1 | $0.01 | - | $0.4 | 50% off | legacy |  |

## xAI

Source: https://docs.x.ai/docs/models

Every model bills a prompt of 200k tokens or more at 2x on all tokens in the request. Priority processing is also 2x. No batch tier.

| Model | Model id | Input | Cached input | Cache write | Output | Batch | Status | Notes |
|---|---|---:|---:|---:|---:|---:|---|---|
| Grok 4.7 | `grok-4.7` | $2 | $0.5 | - | $6 | - | current | Prompts of 200k tokens or more: $4 / $12. |
| Grok 4.6 | `grok-4.6` | $2 | $0.5 | - | $6 | - | current | Prompts of 200k tokens or more: $4 / $12. |
| Grok 4.5 | `grok-4.5` | $2 | $0.3 | - | $6 | - | legacy | Prompts of 200k tokens or more: $4 / $12. |
| Grok 4.3 | `grok-4.3` | $1.25 | $0.2 | - | $2.5 | - | current | Prompts of 200k tokens or more: $2.50 / $5. |
| Grok 4.20 Reasoning | `grok-4.20-0309-reasoning` | $1.25 | $0.2 | - | $2.5 | - | legacy | Prompts of 200k tokens or more: $2.50 / $5. |
| Grok 4.20 Non-reasoning | `grok-4.20-0309-non-reasoning` | $1.25 | $0.2 | - | $2.5 | - | legacy | Prompts of 200k tokens or more: $2.50 / $5. |
| Grok 4.20 Multi-agent | `grok-4.20-multi-agent-0309` | $1.25 | $0.2 | - | $2.5 | - | legacy | Prompts of 200k tokens or more: $2.50 / $5. |
| Grok Build 0.1 | `grok-build-0.1` | $1 | $0.2 | - | $2 | - | current | Prompts of 200k tokens or more: $2 / $4. |

## Mistral AI

Source: https://docs.mistral.ai/inference/pricing

Cached input is 0.1x. Batch is 50% off. Mistral Large 4 is listed at a sale price (list is $1.36 / $4.18) with no published end date. The -latest aliases are priced the same as the dated id they point to.

| Model | Model id | Input | Cached input | Cache write | Output | Batch | Status | Notes |
|---|---|---:|---:|---:|---:|---:|---|---|
| Mistral Large 4 | `mistral-large-2610` | $0.68 | $0.07 | - | $2.09 | 50% off | current | Sale price; list is $1.36 / $4.18. |
| Mistral Large 4 | `mistral-large-latest` | $0.68 | $0.07 | - | $2.09 | 50% off | current | Sale price; list is $1.36 / $4.18. |
| Mistral Large 3 | `mistral-large-2512` | $0.5 | $0.05 | - | $1.5 | 50% off | legacy |  |
| Mistral Medium 3.5 | `mistral-medium-2604` | $1.5 | $0.15 | - | $7.5 | 50% off | current |  |
| Mistral Medium 3.5 | `mistral-medium-latest` | $1.5 | $0.15 | - | $7.5 | 50% off | current |  |
| Mistral Small 4 | `mistral-small-2603` | $0.15 | $0.015 | - | $0.6 | 50% off | current |  |
| Mistral Small 4 | `mistral-small-latest` | $0.15 | $0.015 | - | $0.6 | 50% off | current |  |
| Ministral 3 14B | `ministral-14b-2512` | $0.2 | $0.02 | - | $0.2 | 50% off | current |  |
| Ministral 3 14B | `ministral-14b-latest` | $0.2 | $0.02 | - | $0.2 | 50% off | current |  |
| Ministral 3 8B | `ministral-8b-2512` | $0.15 | $0.015 | - | $0.15 | 50% off | current |  |
| Ministral 3 8B | `ministral-8b-latest` | $0.15 | $0.015 | - | $0.15 | 50% off | current |  |
| Ministral 3 3B | `ministral-3b-2512` | $0.1 | $0.01 | - | $0.1 | 50% off | current |  |
| Ministral 3 3B | `ministral-3b-latest` | $0.1 | $0.01 | - | $0.1 | 50% off | current |  |
| Codestral | `codestral-2508` | $0.3 | $0.03 | - | $0.9 | 50% off | current |  |
| Codestral | `codestral-latest` | $0.3 | $0.03 | - | $0.9 | 50% off | current |  |

## DeepSeek

Source: https://api-docs.deepseek.com/quick_start/pricing

Peak rates (01:00 to 04:00 and 06:00 to 10:00 UTC, Monday to Friday). Off-peak is half on every line. Cache hits are billed as cached input. No batch tier.

| Model | Model id | Input | Cached input | Cache write | Output | Batch | Status | Notes |
|---|---|---:|---:|---:|---:|---:|---|---|
| DeepSeek V4.1 Flash | `deepseek-flash` | $0.3 | $0.006 | - | $1.2 | - | current | Off-peak: $0.15 / $0.003 cached / $0.60. |
| DeepSeek V4 Flash (alias) | `deepseek-v4-flash` | $0.3 | $0.006 | - | $1.2 | - | legacy | Retired id, served by V4.1 Flash at Flash prices. |
| DeepSeek V4 Pro | `deepseek-v4-pro` | $1.32 | $0.044 | - | $3.96 | - | current | Off-peak: $0.66 / $0.022 cached / $1.98. |

## Cohere

Source: https://cohere.com/pricing

Cohere publishes no cached-input or batch rate. Command A+ pricing is taken from Cohere's OpenRouter listing because cohere.com does not expose it in HTML; confirm against your invoice. Deprecated models are listed at their existing-customer rates.

| Model | Model id | Input | Cached input | Cache write | Output | Batch | Status | Notes |
|---|---|---:|---:|---:|---:|---:|---|---|
| Command A+ | `command-a-plus-05-2026` | $0.3 | - | - | $1.5 | - | current | From Cohere's OpenRouter listing; not shown on cohere.com. |
| Command A | `command-a-03-2025` | $2.5 | - | - | $10 | - | current |  |
| Command R+ (08-2024) | `command-r-plus-08-2024` | $2.5 | - | - | $10 | - | legacy |  |
| Command R (08-2024) | `command-r-08-2024` | $0.15 | - | - | $0.6 | - | legacy |  |
| Command R7B | `command-r7b-12-2024` | $0.0375 | - | - | $0.15 | - | legacy |  |
| Command R+ (04-2024) | `command-r-plus-04-2024` | $3 | - | - | $15 | - | retired | Deprecated September 2025; existing-customer rate. |
| Command R (03-2024) | `command-r-03-2024` | $0.5 | - | - | $1.5 | - | retired | Deprecated September 2025; existing-customer rate. |
| Command | `command` | $1 | - | - | $2 | - | retired | Deprecated September 2025; existing-customer rate. |
| Command Light | `command-light` | $0.3 | - | - | $0.6 | - | retired | Deprecated September 2025; existing-customer rate. |

## Notes

- Long prompts cost more on several models (Claude Haiku 5.5 over 100k tokens, Gemini Pro over 200k, every Grok model at 200k, GPT-5.4 and later over 272k). The table lists the base tier; the surcharge is in the notes column.
- DeepSeek is listed at peak rates; off-peak is half on every line.
- Dated model ids (for example claude-sonnet-4-5-20250929) price the same as their undated row.
- Reasoning tokens bill as output on every provider that has them.