100 models
Cache
Vendor
All vendors
| Vendor | Model | Input $/M | Output $/M | Est. cost↑ | Context | Max out | Trend (History) | HQ | Released |
|---|---|---|---|---|---|---|---|---|---|
| Amazon | nova-micro | $0.04 | $0.14 | $0.004060 | 128K | 5K | US | 2024-12-05 | |
| Amazon | nova-lite | $0.06 | $0.24 | $0.006960 | 300K | 5K | US | 2024-12-05 | |
| Mistral | ministral-3b-latest | $0.10 | $0.10 | $0.01 | 256K | 256K* | EU | 2025-12-02 | |
| Meta | muse-spark-1.2-contributor | $0.10 | $0.20 | $0.01 | 1M | 128K | US | 2026-08-05 | |
| gemini-2.5-flash-lite | $0.10 | $0.40 | $0.01 | 1M | 64K Δ8K | US | 2025-07-22 | ||
| Baidu | ernie-4.5-turbo | $0.11 | $0.45 | $0.01 | 128K* | 8K* | CN | 2025-04-25 | |
| Mistral | ministral-8b-latest | $0.15 | $0.15 | $0.02 | 256K | 256K* | EU | 2025-12-02 | |
| Tencent | hunyuan-hy3 | $0.14 | $0.56 | $0.02 | 256K | 256K* | CN | 2026-07-06 | |
| Mistral | mistral-small-latest | $0.15 | $0.60 | $0.02 | 256K | 256K* | EU | 2026-03-16 | |
| Mistral | ministral-14b-latest | $0.20 | $0.20 | $0.02 | 256K | 256K* | EU | 2025-12-02 | |
| AI21 Labs | jamba-mini | $0.20 | $0.40 | $0.02 | 256K | 256K* | IL | 2026-01-08 | |
| DeepSeek | deepseek-v4-flash | $0.22 | $0.66 | $0.02 | 1M | 384K | CN | 2026-04-24 | |
| OpenAI | gpt-5.6-luna | $0.20 | $1.20 | $0.02 | 1M+ | 128K | US | 2026-07-09 | |
| OpenAI | gpt-5.4-nano | $0.20 | $1.25 | $0.03 | 400K | 128K | US | 2026-03-17 | |
| DeepSeek | deepseek-v3.2-exp † | $0.28 | $0.42 | $0.03 | 128K | 8K | CN | 2025-09-29 | |
| DeepSeek | deepseek-v3.2-exp-reasoner † | $0.28 | $0.42 | $0.03 | 128K | 64K | CN | 2025-09-29 | |
| Alibaba | qwen3.6-flash | $0.25 | $1.50 | $0.03 | 1M | 64K | CN | 2026-04-16 | |
| gemini-3.1-flash-lite | $0.25 | $1.50 | $0.03 | 1M | 64K Δ8K | US | 2026-05-07 | ||
| SpaceXAI | grok-3-mini † | $0.30 | $0.50 | $0.03 | 128K | 128K* | US | 2025-02-19 | |
| OpenAI | gpt-5-mini | $0.25 | $2.00 | $0.03 | 400K | 128K | US | 2025-08-07 | |
| Mistral | codestral-latest | $0.30 | $0.90 | $0.03 | 128K | 128K* | EU | 2025-07-30 | |
| MiniMax | minimax-m2.7 | $0.30 | $1.20 | $0.03 | 200K* | 196K* | CN | 2026-03-18 | |
| Alibaba | qwen3.7-plus | $0.32 | $1.28 | $0.04 | 1M | 64K | CN | 2026-05-26 | |
| Amazon | nova-2-lite | $0.30 | $2.50 | $0.04 | 1M | 64K | US | 2025-12-02 | |
| gemini-3.5-flash-lite | $0.30 | $2.50 | $0.04 | 1M | 64K Δ8K | US | 2026-07-21 | ||
| gemini-2.5-flash | $0.30 | $2.50 | $0.04 | 1M | 64K Δ8K | US | 2025-06-17 | ||
| Mistral | mistral-large-latest | $0.50 | $1.50 | $0.06 | 256K | 256K* | EU | 2025-12-02 | |
| gemini-3-flash-preview | $0.50 | $3.00 | $0.06 | 1M | 64K Δ8K | US | 2025-12-17 | ||
| DeepSeek | deepseek-v3.1 † | $0.56 | $1.68 | $0.06 | 128K | 8K | CN | 2025-08-21 | |
| DeepSeek | deepseek-v3.1-reasoner † | $0.56 | $1.68 | $0.06 | 128K | 64K | CN | 2025-08-21 | |
| DeepSeek | deepseek-r1 † | $0.55 | $2.19 | $0.06 | 64K | 8K | CN | 2025-01-20 | |
| Z.ai | glm-4.7 | $0.60 | $2.20 | $0.07 | 200K | 128K | CN | 2025-12-22 | |
| Z.ai | glm-4.6 | $0.60 | $2.20 | $0.07 | 200K | 128K | CN | 2025-09-30 | |
| Z.ai | glm-4.5 | $0.60 | $2.20 | $0.07 | 128K | 96K | CN | 2025-07-28 | |
| DeepSeek | deepseek-v4-pro | $0.66 | $1.98 | $0.07 | 1M | 384K | CN | 2026-04-24 | |
| gemini-3.6-flash | $0.75 | $3.75 | $0.09 | 1M | 64K Δ8K | US | 2026-07-21 | ||
| gemini-3.7-flash | $0.75 | $3.75 | $0.09 | 1M | 64K Δ8K | US | 2026-08-13 | ||
| Amazon | nova-pro | $0.80 | $3.20 | $0.09 | 300K | 5K | US | 2024-12-05 | |
| OpenAI | gpt-5.4-mini | $0.75 | $4.50 | $0.09 | 400K | 128K | US | 2026-03-17 | |
| Anthropic | claude-3-5-haiku † | $0.80 | $4.00 | $0.10 | 200K | 8K | US | 2024-10-22 | |
| Baidu | ernie-5.1 | $0.56 | $2.52 | $0.10 | 128K | 64K | CN | 2026-05-08 | |
| ByteDance | doubao-seed-2.1-pro | $0.84 | $4.20 | $0.10 | 256K | 256K* | CN | 2026-06-24 | |
| SpaceXAI | grok-build-0.1 | $1.00 | $2.00 | $0.11 | 256K | 256K* | US | 2026-05-20 | |
| MoonshotAI | kimi-k2.6 | $0.95 | $4.00 | $0.11 | 256K | 256K* Δ32K | CN | 2026-04-21 | |
| MoonshotAI | kimi-k2.7-code | $0.95 | $4.00 | $0.11 | 262K | 262K* Δ32K | CN | 2026-06-12 | |
| Perplexity | sonar | $1.00 | $1.00 | $0.11 | 128K | 128K** | US | 2025-01-27 | |
| Z.ai | glm-5 | $1.00 | $3.20 | $0.11 | 200K | 128K | CN | 2026-02-12 | |
| Anthropic | claude-haiku-4-5 | $1.00 | $5.00 | $0.12 | 200K | 64K | US | 2025-10-15 | |
| SpaceXAI | grok-4.3 | $1.25 | $2.50 | $0.14 | 1M | 1M* | US | 2026-04-30 | |
| SpaceXAI | grok-4.20-0309-reasoning | $1.25 | $2.50 | $0.14 | 1M | 1M* | US | 2026-03-10 | |
| SpaceXAI | grok-4.20-0309-non-reasoning | $1.25 | $2.50 | $0.14 | 1M | 1M* | US | 2026-03-10 | |
| SpaceXAI | grok-4.20-multi-agent-0309 | $1.25 | $2.50 | $0.14 | 1M | 1M* | US | 2026-03-10 | |
| Z.ai | glm-5-turbo | $1.20 | $4.00 | $0.14 | 200K | 128K | CN | 2026-03-15 | |
| Alibaba | qwen3.7-max | $1.25 | $3.75 | $0.14 | 1M | 64K | CN | 2026-05-20 | |
| Meta | muse-spark-1.1 | $1.25 | $4.25 | $0.14 | 1M | 128K | US | 2026-07-09 | |
| Meta | muse-spark-1.2 | $1.25 | $4.25 | $0.14 | 1M | 128K | US | 2026-08-05 | |
| Z.ai | glm-5.3 | $1.40 | $4.40 | $0.16 | 1M | 128K | CN | 2026-08-14 | |
| Z.ai | glm-5.2 | $1.40 | $4.40 | $0.16 | 1M | 128K | CN | 2026-06-16 | |
| Z.ai | glm-5.1 | $1.40 | $4.40 | $0.16 | 200K | 128K | CN | 2026-04-07 | |
| gemini-2.5-pro | $1.25 | $10.00 | $0.17 | 1M | 64K Δ8K | US | 2025-06-17 | ||
| OpenAI | gpt-5 | $1.25 | $10.00 | $0.17 | 400K | 128K | US | 2025-08-07 | |
| Mistral | mistral-medium-latest | $1.50 | $7.50 | $0.18 | 256K | 256K* | EU | 2026-04-28 | |
| gemini-3.5-flash | $1.50 | $9.00 | $0.19 | 1M | 64K Δ8K | US | 2026-05-19 | ||
| MoonshotAI | kimi-k2.7-code-highspeed | $1.90 | $8.00 | $0.22 | 262K | 262K* Δ32K | CN | 2026-06-15 | |
| Alibaba | qwen3.8-max | $2.00 | $6.00 | $0.22 | 1M | 128K | CN | 2026-08-03 | |
| Mistral | mistral-large-2411 † | $2.00 | $6.00 | $0.22 | 128K | 128K* | EU | 2024-11-18 | |
| SpaceXAI | grok-4.5 | $2.00 | $6.00 | $0.22 | 500K | 500K* | US | 2026-07-08 | |
| SpaceXAI | grok-4.6 | $2.00 | $6.00 | $0.22 | 500K | 500K | US | 2026-08-12 | |
| OpenAI | gpt-5.3-codex | $1.75 | $14.00 | $0.23 | 400K | 128K | US | 2026-02-05 | |
| AI21 Labs | jamba-large | $2.00 | $8.00 | $0.23 | 256K | 256K* | IL | 2025-07-03 | |
| Amazon | nova-premier | $2.00 | $8.00 | $0.23 | 1M | 25K | US | 2025-10-31 | |
| OpenAI | gpt-4.1 | $2.00 | $8.00 | $0.23 | 1M | 32K | US | 2025-04-14 | |
| OpenAI | o3 | $2.00 | $8.00 | $0.23 | 200K | 100K | US | 2025-04-16 | |
| Perplexity | sonar-deep-research | $2.00 | $8.00 | $0.23 | 128K | 128K** | US | 2025-03-07 | |
| Anthropic | claude-sonnet-5 | $2.00 | $10.00 | $0.24 | 1M | 128K | US | 2026-06-30 | |
| Perplexity | sonar-reasoning-pro | $2.00 | $8.00 | $0.24 | 128K | 128K** | US | 2025-03-07 | |
| gemini-3.1-pro-preview | $2.00 | $12.00 | $0.25 | 1M | 64K Δ8K | US | 2026-02-19 | ||
| gemini-3-pro-preview † | $2.00 | $12.00 | $0.25 | 1M | 64K Δ8K | US | 2025-11-18 | ||
| OpenAI | gpt-5.6-terra | $2.00 | $12.00 | $0.25 | 1M+ | 128K | US | 2026-07-09 | |
| Cohere | command-a | $2.50 | $10.00 | $0.29 | 256K | 8K* | US | 2025-03-13 | |
| OpenAI | gpt-5.4 | $2.50 | $15.00 | $0.31 | 1.05M | 128K | US | 2026-03-05 | |
| Anthropic | claude-sonnet-4-6 | $3.00 | $15.00 | $0.36 | 1M | 128K | US | 2026-02-17 | |
| Anthropic | claude-sonnet-4-5 | $3.00 | $15.00 | $0.36 | 200K | 64K | US | 2025-09-29 | |
| Anthropic | claude-sonnet-4 † | $3.00 | $15.00 | $0.36 | 200K | 64K | US | 2025-05-22 | |
| MoonshotAI | kimi-k3 | $3.00 | $15.00 | $0.36 | 1M | 1M Δ131K | CN | 2026-07-16 | |
| SpaceXAI | grok-4 † | $3.00 | $15.00 | $0.36 | 256K | 256K* | US | 2025-07-09 | |
| SpaceXAI | grok-3 † | $3.00 | $15.00 | $0.36 | 128K | 128K* | US | 2025-02-19 | |
| Perplexity | sonar-pro | $3.00 | $15.00 | $0.37 | 200K | 128K** | US | 2025-01-21 | |
| Anthropic | claude-opus-5 | $5.00 | $25.00 | $0.60 | 1M | 128K | US | 2026-07-24 | |
| Anthropic | claude-opus-4-8 | $5.00 | $25.00 | $0.60 | 1M | 128K | US | 2026-05-28 | |
| Anthropic | claude-opus-4-7 | $5.00 | $25.00 | $0.60 | 1M | 128K | US | 2026-04-16 | |
| Anthropic | claude-opus-4-6 | $5.00 | $25.00 | $0.60 | 1M | 128K | US | 2026-02-05 | |
| Anthropic | claude-opus-4-5 | $5.00 | $25.00 | $0.60 | 200K | 64K | US | 2025-11-01 | |
| OpenAI | gpt-5.6-sol | $5.00 | $30.00 | $0.62 | 1M+ | 128K | US | 2026-07-09 | |
| Anthropic | claude-fable-5 | $10.00 | $50.00 | $1.20 | 1M | 128K | US | 2026-06-09 | |
| Anthropic | claude-mythos-5 | $10.00 | $50.00 | $1.20 | 1M | 128K | US | 2026-06-09 | |
| OpenAI | gpt-5.6-cyber | $12.50 | $75.00 | $1.55 | 400K | 128K | US | 2026-08-10 | |
| Anthropic | claude-opus-4-1 † | $15.00 | $75.00 | $1.80 | 200K | 32K | US | 2025-08-05 | |
| Anthropic | claude-opus-4 † | $15.00 | $75.00 | $1.80 | 200K | 32K | US | 2025-05-22 | |
| NVIDIA | nemotron-3-ultra | n/a | n/a | Free | 1M | 64K* | no history | US | 2026-06-04 |
| * | Max output derived from context size: the vendor sets no separate max output limit, only requires prompt tokens plus output tokens to stay within the context window. |
| ** | A real vendor-published limit that applies API-wide rather than being stated per model. |
| Δ | The API's default output when you don't explicitly request more. The number above it is still the true ceiling. |
| † | Retired model. No longer available via the vendor's API. |
| Deprecated model. | |
| No published cache-hit pricing for this model, showing the regular price instead. | |
| Includes a per-request search fee, already included into Est. cost. (Hover bullet for details) | |
| Separate citation/reasoning/search-query token charges apply, not included in Est. cost. (Hover bullet for details) | |
| Has a prompt cache-write price, a one-time per-session cost not included in Est. cost. (Hover bullet for details) | |
| Model-specific access note. (Hover bullet for details) |